CN114039977B

CN114039977B - Method, system and device for realizing application task based on edge calculation

Info

Publication number: CN114039977B
Application number: CN202111329908.3A
Authority: CN
Inventors: 郭广路; 陈振
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2021-11-10
Filing date: 2021-11-10
Publication date: 2024-03-26
Anticipated expiration: 2041-11-10
Also published as: CN114039977A

Abstract

The embodiment of the invention provides a method and a device for realizing an application task based on edge calculation, which are applied to a target edge node and comprise the following steps: receiving a processing request sent by a client through a proxy server; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and calling at least one target application container in the target edge node according to the address information of the target edge node and the private network address of the at least one target application container, and processing the processing request to obtain a processing result. According to the embodiment of the invention, the public network address is not required to be set for each application container, so that the cost of edge calculation and the difficulty of system construction can be reduced.

Description

Method, system and device for realizing application task based on edge calculation

Technical Field

The present invention relates to the field of edge computing technologies, and in particular, to a method, a system, and an apparatus for implementing an application task based on edge computing.

Background

The edge calculation can realize that most of user data operation and data control sink to the local equipment closest to the user without depending on a cloud, so that the processing efficiency of data is greatly improved, and the loads of the cloud and a central database are reduced, and the edge calculation method is widely applied.

In existing edge computing, edge nodes are deployed around places to provide services with edge nodes that are nearby to external devices. Since the container is a standardized unit that is packaged from the dependencies required for the code to run, a container for executing services can be created in each edge node, enabling edge computation based on the containers in each edge node. Specifically, when providing services to the outside, the containers in each edge node need to be configured with an independent public network IP, so that after initiating a service request, an external device determines a target edge node and a target container for completing the services according to the address of the edge node and the public network IP of the container corresponding to the services in the service request, thereby completing the corresponding services by using the target container.

However, in the prior art, configuring an independent public network IP for all containers in each edge node results in higher edge computing cost, and related hardware support is required to be provided by a machine room corresponding to the edge node, so that the difficulty of system construction is increased.

Disclosure of Invention

The embodiment of the invention aims to provide a method, a system and a device for realizing an application task based on edge computing, which are used for solving the problems that in the prior art, when the related application task is realized by adopting the edge computing based on application containers, independent public network IP is required to be configured for all containers in each edge node, so that the edge computing cost is higher and the system construction difficulty is increased. The specific technical scheme is as follows:

in a first aspect of the present invention, there is provided a method for implementing an application task based on edge computing, applied to an edge computing system, where the edge computing system includes at least one edge node, a central control server and a client, and each edge node includes at least one application container and one proxy server, and the method includes:

the central control server acquires the identification information of a target application task, and determines the address information of at least one target edge node for processing the target application task by combining the prestored corresponding relation between the identification information of the application task and the address information of the edge node for processing the application task; generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task, wherein each accessible address corresponds to the address information of one target edge node; transmitting the at least one accessible address to the client;

The client receives the at least one accessible address sent by the central control server, and generates a processing request for the target application task according to the at least one accessible address, wherein the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task; transmitting the processing request to the at least one target edge node according to the address information of the at least one target edge node;

a proxy server in the target edge node receives a processing request aiming at the target application task, which is sent by the client; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and according to the address information of the target edge node and the private network address of the at least one target application container, calling the at least one target application container to process the processing request, so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

In a second aspect of the embodiment of the present invention, a method for implementing an application task based on edge computation is provided, and the method is applied to a target edge node, where the target edge node includes at least one application container and a proxy server, and the method includes:

the proxy server receives a processing request for a target application task sent by a client, wherein the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and calling at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the at least one target application container so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

In a third aspect of the present invention, a method for implementing an application task based on edge computation is provided, and the method is applied to a client, and includes:

Receiving at least one accessible address corresponding to a target application task sent by a central control server, wherein each accessible address corresponds to address information of a target edge node;

generating a processing request aiming at the target application task according to the at least one accessible address, wherein the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task;

transmitting the processing request to the at least one target edge node according to the address information of the at least one target edge node, so that the at least one target edge node determines a private network address of at least one target application container for processing the target application task according to the identification information of the target application task, and calls the at least one target application container to process the processing request to obtain a processing result;

and receiving the processing result fed back by the at least one target edge node.

In a fourth aspect of the present invention, there is provided a method for implementing an application task based on edge computation, applied to a central control server, the method comprising:

Acquiring identification information of a target application task, and determining address information of at least one target edge node for processing the target application task by combining the prestored corresponding relation between the identification information of the application task and the address information of the edge node for processing the application task;

generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task, wherein each accessible address corresponds to the address information of one target edge node;

the at least one accessible address is sent to the client.

In a fifth aspect of the present invention, there is provided an edge computing system comprising: at least one edge node, a central control server and a client, wherein each edge node comprises at least one application container and one proxy server;

the central control server is used for acquiring the identification information of the target application task and determining the address information of at least one target edge node for processing the target application task by combining the prestored corresponding relation between the identification information of the application task and the address information of the edge node for processing the application task; generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task, and sending the at least one accessible address to the client, wherein each accessible address corresponds to the address information of one target edge node;

The client is configured to receive the at least one accessible address sent by the central control server, and generate a processing request for the target application task according to the at least one accessible address, where the processing request includes address information of at least one target edge node for processing the target application task, and identification information of the target application task; transmitting the processing request to the at least one target edge node according to the address information of the at least one target edge node;

the proxy server in the target edge node is used for receiving a processing request aiming at the target application task, which is sent by the client; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and according to the address information of the target edge node and the private network address of the at least one target application container, calling the at least one target application container to process the processing request, so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

In a sixth aspect of the embodiment of the present invention, there is further provided a target edge node, where the target edge computing includes at least one application container and a proxy server, where the application container is configured to process an application task and obtain a processing result, and the proxy server is configured to receive a processing request for the target application task sent by a client, where the processing request includes address information of at least one target edge node that processes the target application task and identification information of the target application task; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and calling at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the at least one target application container so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

In a seventh aspect of the present invention, there is also provided an apparatus for implementing an application task based on edge computation, applied to a client, the apparatus including:

The accessible address receiving module is used for receiving at least one accessible address corresponding to a target application task sent by the central control server, and each accessible address corresponds to address information of one target edge node;

a processing request generating module, configured to generate a processing request for the target application task according to the at least one accessible address, where the processing request includes address information of at least one target edge node that processes the target application task, and identification information of the target application task;

a processing request sending module, configured to send the processing request to the at least one target edge node according to address information of the at least one target edge node, so that the at least one target edge node determines a private network address of at least one target application container for processing the target application task according to identification information of the target application task, and invokes the at least one target application container to process the processing request, so as to obtain a processing result;

and the processing result receiving module is used for receiving the processing result fed back by the at least one target edge node.

In an eighth aspect of the present invention, there is also provided an apparatus for implementing an application task based on edge computation, applied to a central control server, the apparatus including:

the edge node determining module is used for acquiring the identification information of the target application task and determining the address information of at least one target edge node for processing the target application task by combining the prestored corresponding relation between the identification information of the application task and the address information of the edge node for processing the application task;

the accessible address generating module is used for generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task, and each accessible address corresponds to the address information of one target edge node;

and the accessible address sending module is used for sending the at least one accessible address to the client.

In yet another aspect of the present invention, there is also provided an electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus;

The memory is used for storing a computer program;

the processor is configured to execute the method for implementing the edge computing-based application task according to any one of the above when executing the program stored in the memory.

In yet another aspect of the present invention, there is also provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for implementing any of the edge-computing based application tasks described above.

Compared with the prior art, the method and the device for realizing the application task based on the edge calculation have the following advantages:

the embodiment of the invention provides a method and a device for realizing an application task based on edge calculation, which are applied to a target edge node, wherein the target edge node comprises at least one application container and a proxy server, and the method comprises the following steps: the proxy server receives a processing request for a target application task sent by a client, wherein the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and calling at least one target application container in the target edge node according to the address information of the target edge node and the private network address of the at least one target application container so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

According to the embodiment of the invention, the accessible address of the target application task is generated according to the identification information of the target application task and the address information of the target edge node for processing the target application task, the corresponding relation between the accessible address and the target edge node is established, each edge node corresponds to one accessible address of the application task, and the client can realize interaction with the edge node through the accessible address; when the related application tasks are realized based on the edge calculation of the application container, after the target edge node receives the processing request, the private network address of the target application container for processing the target application task is determined directly according to the corresponding relation between the identification information of the preset application task in the target edge node and the private network address of the application container, and then the target application container is called to complete the application tasks.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

FIG. 1 is a schematic diagram of an edge computing system according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating the interaction steps of a method for implementing an application task based on edge computation according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating specific steps of a method for implementing an application task based on edge computation according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating steps of another method for implementing an application task based on edge computation according to an embodiment of the present invention;

FIG. 5 is a flowchart illustrating steps of a method for implementing an application task based on edge computation according to an embodiment of the present invention;

FIG. 6 is a flowchart illustrating steps of another implementation method of an application task based on edge computation according to an embodiment of the present invention;

FIG. 7 is a flowchart illustrating steps of a method for implementing an application task based on edge computation according to an embodiment of the present invention;

FIG. 8 is a block diagram illustrating a target edge node according to an embodiment of the present invention;

FIG. 9 is a block diagram of an implementation device of an application task based on edge computation in an embodiment of the present invention;

FIG. 10 is a block diagram of an implementation device of an application task based on edge computation according to an embodiment of the present invention;

fig. 11 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

The implementation method of the application task based on the edge calculation provided by the embodiment of the invention is applied to an edge calculation system, and the edge calculation system comprises the following steps: at least one edge node, a central control server and a client, each edge node comprises at least one application container and a proxy server.

Referring to fig. 1, a schematic structural diagram of an edge computing system according to an embodiment of the present invention is shown. As shown in fig. 1, the implementation system of the application task based on edge computing in the embodiment of the present invention may include a central control server 10, at least one edge node 20 deployed in an edge machine room, and an Internet-based client 30.

The central control server 10 is configured to, when implementing an application task based on edge computing, deploy a plurality of edge nodes 20 in an edge computer room, and specifically, may deploy an application container for processing the application task in the edge nodes 20. Meanwhile, the central control server 10 may also perform configuration of application tasks in the edge machine room, that is, configure application containers specifically used for processing application tasks in the edge node 20. The accessible address list of the plurality of application tasks can be configured, and the accessible address list of the plurality of application tasks is sent to the client 30 through the application management center (i.e. the application registration discovery and scheduling center in fig. 1), so that when the user needs to implement the target application task, the client 30 searches the accessible address of the target application task according to the accessible address list, thereby determining a target edge node for processing the application task according to the accessible address in the edge machine room, and a target application container in the target edge node.

By way of example, a central control server may be built based on Kubernetes, which is an open source for managing containerized applications on multiple hosts in a cloud platform, with the goal of letting the containerized applications deployed simple and efficient, kubernetes provides a mechanism for application deployment, planning, updating, and maintenance.

The edge node 20 is an integral open platform on the edge side of the network near the user, and includes core capabilities of building a network, computing, storing, and applying. The edge node is positioned between the user and the cloud center, and is closer to the user (data source) than the traditional cloud center, so that the edge node can be utilized to provide nearest service nearby, and part of key business application is sunk to the edge of the access network, so that the width and time delay loss caused by network transmission and multistage forwarding are reduced, and the basic requirements of the industry in the aspects of real-time business, application intelligence, safety, privacy protection and the like are met. The edge node 20 includes at least one application container and a proxy server therein.

An application container refers to a lightweight virtualized operating system that can run application tasks and their dependencies in a resource-isolated process. However, all components necessary to run the application tasks will be packaged as a mirror image and can be reused. When the mirror image is executed, the application container can run in an isolated environment, different processes can have isolated running environments and resources by utilizing the characteristics of the namespace isolation and the resource isolation of the kernel of the operating system, the memory, the CPU and the disk of the host are not shared, meanwhile, the application container is a lighter technology than virtualization, the response time is shorter, and the time required for starting the application container is generally less than 1 second.

In embodiments of the present invention, application containers may be implemented using application container engine (docker) technology. The dock technology is the most popular container technology of the current Linux operating system, and can adopt an open-source application container engine, so that an issuer can package application tasks and rely on packages to a portable mirror image and then issue the package to any popular Linux or Windows machine, and virtualization can be realized.

The proxy server may monitor the public network address and default ports of the host (the edge node 20), etc. The proxy server may read, from the application container included in the edge node 20, the identification information of the application task deployed by the central control server 10 for the application container, and store the correspondence between the private network address of the application container and the identification information of the application task. When the edge node needs to execute the target application task, the proxy server can determine the target application container for executing the target application task according to the corresponding relation between the private network address of the stored application container and the identification information of the application task, thereby calling the target application container to execute the target application task and realizing the single proxy of the edge node. Wherein the proxy server may be a hypertext transfer protocol (HTTP) proxy device, such as an nginnx reverse proxy server or the like.

An implementation method of an application task based on edge computing according to an embodiment of the present invention will be described in detail below with reference to the edge computing system shown in fig. 1. Referring to fig. 2, a flowchart of interaction steps of a method for implementing an application task based on edge computing according to an embodiment of the present invention is shown, where the method is applied to the edge computing system shown in fig. 1, and specifically includes:

step 101, a central control server acquires identification information of a target application task, and determines address information of at least one target edge node for processing the target application task by combining a corresponding relation between the prestored identification information of the application task and address information of the edge node for processing the application task.

In this step, the user may input or select identification information of the target application task to be implemented through the central control server, that is, the central control server may acquire the identification information of the target application task.

Further, the central control server may determine address information of at least one target edge node for processing the target application task in combination with a correspondence between pre-stored identification information of the application task and address information of an edge node for processing the application task.

Step 102, the central control server generates at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task.

Wherein each accessible address corresponds to address information of a target edge node.

In this step, after determining address information of at least one target edge node that processes the target application task, the central control server may generate at least one accessible address of the target application task according to the address information of the at least one target edge node and identification information corresponding to the target application task.

For example, if the identification information of the target application task is: the address information of at least one target edge node for processing the target application task apps/foo is: address information of edge node 1: http://123.123.223.1:80, and address information of edge node 2: the accessible addresses of the target application task may be generated as http://123.123.223.2:80, http://123.123.223.1:80/apps/foo and http://123.123.223.2:80/apps/foo.

In the embodiment of the invention, a flow scheduler can be arranged in the central control server, and the flow scheduler is utilized to generate the accessible address of the target application task.

Step 103, the central control server sends the at least one accessible address to the client.

In this step, after generating at least one accessible address of the target application task, the central control server may send the at least one accessible address to the client, so that the client may generate a processing request for the target application task according to the at least one accessible address. The processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task. The client may send the processing request to the at least one target edge node according to the address information of the at least one target edge node, so that the at least one target edge node determines a private network address of at least one target application container for processing the target application task according to the identification information of the target application task, and may call the at least one target application container to process the processing request, thereby obtaining a processing result.

Step 104, the client receives the at least one accessible address sent by the central control server.

In this step, the client may acquire an accessible address list including a plurality of application tasks from the central control server, and further screen at least one accessible address corresponding to the target application task from the accessible address list, where the at least one accessible address is generated by the central control server according to address information of at least one target edge node that processes the target application task and identification information of the target application task.

Optionally, the address information of the target edge node includes public network address and port information corresponding to the target edge node.

For example, in the accessible address http://123.123.223.1:80/apps/foo, the address information of the target edge node: http://123.123.223.1:80 is for executing application tasks: public network address and port of the edge node of apps/foo, the public network address of this edge node is: http://123.123.223.1, port is the default port 80.

Step 105, the client generates a processing request for the target application task according to the at least one accessible address, where the processing request includes address information of at least one target edge node for processing the target application task and identification information of the target application task.

In this step, after the client obtains at least one accessible address corresponding to the target application task, because the accessible address is generated by the central control server according to address information of at least one target edge node for processing the target application task and identification information of the target application task, the client may generate a processing request for the target application task according to the at least one accessible address, so that the processing request may include address information of at least one target edge node for processing the target application task and identification information of the target application task.

Step 106, the client sends the processing request to the at least one target edge node according to the address information of the at least one target edge node.

In this step, after generating a processing request for a target application task, the client may send the processing request to the target edge node according to address information of the target edge node, so that the target edge node determines a private network address of at least one target application container for processing the target application task according to identification information of the target application task, and may call the target application container to process the processing request, thereby obtaining a processing result.

In step 107, the proxy server in the target edge node receives a processing request for the target application task sent by the client.

In this step, the proxy server in the target edge node may receive a processing request for the target application task sent by the client 30, where the processing request includes address information of at least one target edge node for processing the target application task and identification information of the target application task.

Specifically, the client may acquire an accessible address list including a plurality of application tasks from the central control server, and the client 30 screens an accessible address corresponding to a target application task from the accessible address list, and since the accessible address is generated by the central control server 10 according to address information of at least one target edge node for processing the target application task and identification information of the target application task, the client may generate a processing request for the target application task according to the accessible address, and send the processing request to the target edge node.

And step 108, the proxy server determines the private network address of at least one target application container for processing the target application task according to the corresponding relation between the pre-stored identification information of the application task and the private network address of the application container.

In this step, after receiving a processing request for a target application task sent by a client, a proxy server in a target edge node may determine a private network address of a target application container corresponding to the identification information of the target application task according to the identification information for processing the target application task included in the processing request and a correspondence between the prestored identification information of the application task and the private network address of the application container.

And step 109, the proxy server calls at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the at least one target application container, processes the processing request to obtain a processing result, and feeds back the processing result to the client.

In this step, after receiving a processing request of a target application task and determining a private network address of at least one target application container for processing the target application task in the target edge node, the proxy server in the target edge node may call the target application container in the target edge node according to address information of the target edge node and the private network address of the target application container, so as to process the processing request by using the target application container, obtain a processing result of the target application task, and further feed back the processing result to the client, so as to implement the application task.

Step 110, the client receives the processing result fed back by the target edge node.

In this step, after the client sends the processing request for the target application task to the target edge node, after the target edge node obtains the processing result of the target application task according to the processing request, the processing result returned by the target edge node may be received, and finally, the processing of the target application task is completed.

In summary, in the embodiment of the present invention, the accessible address of the target application task is generated according to the identification information of the target application task and the address information of the target edge node for processing the target application task, so that the correspondence between the accessible address and the target edge node is established, so that each edge node corresponds to the accessible address of an application task, and the client can implement interaction with the edge node through the accessible address; when the related application tasks are realized based on the edge calculation of the application container, after the target edge node receives the processing request, the private network address of the target application container for processing the target application task is determined directly according to the corresponding relation between the identification information of the preset application task in the target edge node and the private network address of the application container, and then the target application container is called to complete the application task.

Referring to fig. 3, a flowchart illustrating steps of a method for implementing an application task based on edge computation according to an embodiment of the present invention is shown, where the method is applied to a target edge node, and the target edge node includes at least one application container and a proxy server, and specifically includes:

in step 201, the proxy server receives a processing request for a target application task sent by a client, where the processing request includes address information of at least one target edge node for processing the target application task and identification information of the target application task.

It should be noted that, the processing request is generated by the client according to at least one accessible address of the target application task acquired from the central control server, where the at least one accessible address is generated by the central server according to identification information of the target application task and address information of at least one target edge node for processing the target application task, and each accessible address corresponds to address information of one target edge node.

In this step, referring to fig. 1, a target edge node in an edge machine room may receive a processing request for a target application task sent by a client 30, where the processing request includes address information of at least one target edge node for processing the target application task and identification information of the target application task.

Specifically, the client may acquire an accessible address list including a plurality of application tasks from the central control server, and the client 30 screens out at least one accessible address corresponding to a target application task from the accessible address list, and since the accessible address is generated by the central control server 10 according to address information of at least one target edge node for processing the target application task and identification information of the target application task, the client may generate a processing request for the target application task according to the at least one accessible address and send the processing request to the target edge node.

For example, the central control server contains a list of accessible addresses for a plurality of application tasks as shown in table 1 below:

numbering device	Accessible address
		1	http://123.123.223.1:80/apps/foo
2	http://123.123.223.2:80/apps/foo
		3	http://123.123.223.1:443/apps/foo
4	http://123.123.223.2:443/apps/foo
		5	http://123.123.223.1:80/apps/soo

TABLE 1

The accessible address list may include address information of an edge node for processing an application task, and identification information of the application task, for example, in the accessible address http://123.123.223.1:80/apps/foo, http://123.123.223.1 is a public network address of the edge node for processing the application task foo, 80 is a standard port corresponding to the edge node, apps/foo is identification information of the application task, and http://123.123.223.1:80 is address information of the edge node. In other words, the address information of the edge node includes the public network address and the port information of the edge node, and the accessible address of the application task includes the address information of the edge node for processing the application task and the identification information of the application task.

Correspondingly, if the identification information of the target application task is apps/foo, the client can screen out the accessible address with the accessible address of numbers 1-4 corresponding to the target application task according to the accessible address list. Further, a processing request for the target application task may be generated according to the accessible address corresponding to the target application task, so that the processing request may include address information of a target edge node for processing the target application task: http://123.123.223.1:80, http://123.123.223.2:80, http://123.123.223.1:443, http://123.123.223.2:443, and identification information of the target application task: apps/foo.

For example, referring to fig. 1, the edge machine room includes N edge nodes: edge node 1, edge node 2. http://123.123.223.1, and default ports (80, 443), the address information of edge node 2 is the public network IP address of edge node 1: http://123.123.223.2, and default ports (80, 443). Accordingly, the client 30 can determine the target edge node for processing the target application task apps/foo as the edge node 1 and the edge node 2, and finally, transmit the generated processing request to the edge node 1 and the edge node 2 according to the address information of the edge node 1 and the edge node 2.

Step 202, determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the pre-stored identification information of the application task and the private network address of the application container.

In this step, after receiving a processing request for a target application task sent by a client, a target edge node may determine a private network address of a target application container corresponding to the identification information of the target application task according to the identification information for processing the target application task included in the processing request and a correspondence between the pre-stored identification information of the application task and the private network address of the application container.

Table 2 may be a correspondence between the identification information of the application task and the private network address of the application container stored in advance in the edge node 1, corresponding to fig. 1, where the edge node 1 may include two application containers, and the corresponding private network addresses are respectively private network IP addresses: 192.168.0.1 and 192.168.0.3; table 3 may be a correspondence between the identification information of the application task and the private network address of the application container stored in advance in the edge node 2, corresponding to fig. 1, where the edge node 2 may include two application containers, and the corresponding private network addresses are respectively private network IP addresses: 192.168.0.2 and 192.168.0.4.

In the embodiment of the present invention, the edge node 1 and the edge node 2 are target edge nodes for processing target application tasks apps/foos, and both the edge node 1 and the edge node 2 may receive a processing request of a target application task sent by a client, where the processing request includes identification information of the target application task as follows: apps/foo.

Further, after receiving the processing request of the target application task, the edge node 1 may determine, according to the corresponding relationship shown in the table 2 stored in advance, that the private network address of the target application container used for processing the target application task in the edge node 1 is 192.168.0.1; after receiving the processing request of the target application task, the edge node 2 may determine, according to the correspondence shown in the table 3 stored in advance, that the private network address of the target application container used for processing the target application task in the edge node 2 is 192.168.0.2.

Identification information of application task	Private network address of application container
		apps/foo	192.168.0.1
apps/soo	192.168.0.3

TABLE 2

Identification information of application task	Private network address of application container
		apps/foo	192.168.0.2
apps/soo	192.168.0.4

TABLE 3 Table 3

And 203, calling at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the at least one target application container, processing the processing request to obtain a processing result, and feeding back the processing result to the client.

In this step, after receiving a processing request of a target application task and determining a private network address of at least one target application container for processing the target application task in the target edge node, the target edge node may call the at least one target application container in the target edge node according to address information of the target edge node and the private network address of the target application container, so as to process the processing request by using the at least one target application container, obtain a processing result of the target application task, and further feed back the processing result to the client, thereby implementing the application task.

It should be noted that, the client may interact with the edge node through an accessible address of the application task, and the application container in the edge node may interact with the edge node through a private network. The application container in the edge node cannot directly interact with the client, the client can only send a processing request aiming at the target application task to the target edge node, and the target edge node calls the target application container to execute the target application task.

For example, if the edge machine room is used to process the target application task: apps/foo is application container 1 in edge node 1, corresponding private network address 192.168.0.1, and application container 3 in edge node 2, corresponding private network address 192.168.0.3. If the user triggers a processing instruction for a target application task based on an accessible address of the target application task through the client, the client can generate a processing request for the target application task according to the accessible address of the target application task, send the processing request to an edge node 1 for processing the target application task, and the edge node 1 calls an application container 1 according to a private network address 192.168.0.1, so that the processing request is processed by the application container 1. Similarly, the edge node 2 can call the application container 3 according to the private network address of 192.168.0.3, so that the application container 3 is utilized to process the processing request, and finally, the processing of the target application task is completed, and the processing result of the target application task is obtained.

Referring to fig. 4, a flowchart of specific steps of another implementation method of an application task based on edge computing according to an embodiment of the present invention is shown.

The implementation method of the application task based on the edge calculation is applied to a target edge node, wherein the target edge node comprises at least one application container and a proxy server.

Step 301, receiving an application task configuration request sent by a central control server, where the application task configuration request includes identification information of an application task, address information of an edge node for processing the application task, and a private network address of an application container for processing the application task in the edge node.

In this step, the target edge node may receive an application task configuration request sent by the central control server.

The application task configuration request may include identification information of an application task, address information of an edge node processing the application task, and a private network address of an application container processing the application task in the edge node.

For example, referring to table 4, if there are two application tasks, the identification information of the corresponding application task is apps/foo and apps/soo, the application task apps/foo is the application container 1 in the edge node 1 and the application container 2 in the edge node 2, the application task apps/soo is the application container 3 in the edge node 1 and the application container 4 in the edge node 2, the central control server may obtain in advance the identification information of the two application tasks listed in table 4, the address information of the edge node corresponding to each application task, and the private network address of the application container in the edge node for each application task, and generate an application task configuration request according to these information and send to each edge node.

TABLE 4 Table 4

Step 302, obtaining the address information of the target edge node, and inquiring the identification information of the application task matched with the target edge node and the private network address of the application container from the application task configuration request according to the address information of the target edge node.

In this step, after receiving the application task configuration request sent by the central control server, the target edge node may query, from the application task configuration request, identification information of an application task matching the target edge node and a private network address of the application container according to address information of the target edge node.

For example, if the target edge node is edge node 1, the application task identification information that matches the target edge node, which is determined from the task configuration request including the information shown in table 4, is: apps/foo, the private network address of the corresponding application container is 192.168.0.1, and the application task identification information is: apps/soo, the private network address of the corresponding application container is 192.168.0.3; if the target edge node is edge node 2, the application task identification information matched with the target edge node determined from the task configuration request including the information shown in table 4 is: apps/foo, the private network address of the corresponding application container is 192.168.0.2, and the application task identification information is: apps/soo, the private network address of the corresponding application container is 192.168.0.4.

And step 303, correspondingly storing the identification information of the application task and the private network address of the application container according to the identification information of the application task matched with the target edge node and the private network address of the application container.

In this step, after determining, from the application task configuration request, the identification information of the application task and the private network address of the application container, which are matched with the target edge node, according to the address information of the target edge node, the target edge node may generate and store a correspondence between the identification information of the application task and the private network address of the application container according to the obtained identification information of the application task and the private network address of the application container.

For example, if the target edge node is edge node 1, the corresponding relationship shown in table 2 may be generated according to the application task identification information and the private network address of the application container, which are determined from the task configuration request including the information shown in table 4 and are matched with the target edge node; if the target edge node is edge node 2, the corresponding relationship shown in table 3 may be generated according to the application task identification information and the private network address of the application container, which are determined from the task configuration request including the information shown in table 4 and are matched with the target edge node.

In the embodiment of the present invention, the steps 301 to 303 may be performed by a proxy server set in an edge node, that is, the proxy server in each edge node receives an application task configuration request sent by a central control server, and determines, according to address information of an edge node where a current proxy server is located, identification information of an application task matched with the edge node and a private network address of an application container from the application task configuration request, so as to generate a correspondence between the identification information of the application task and the private network address of the application container, that is, generate a local rule for the edge node. The proxy server in the edge node and the application container realize communication and control through a docker network bridge.

Specifically, the local rule generated by the edge node 1 may be:

-Host:*

-Path:/app/foo

-Target:192.168.0.1

and:

-Host:*

-Path:/app/soo

-Target:192.168.0.2

that is, for application foo, all hosts can be matched, the forwarding path is/app/foo, and the private network address of the corresponding deployed container is 192.168.0.1. For application soo, all hosts can be matched, the forwarding path is/app/soo, and the private network address of the corresponding deployed container is 192.168.0.3.

The local rules generated by the edge node 2 may be:

-Host:*

-Path:/app/foo

-Target:192.168.0.2

And:

-Host:*

-Path:/app/soo

-Target:192.168.0.4

that is, for application foo, all hosts can be matched, the forwarding path is/app/foo, and the private network address of the corresponding deployed container is 192.168.0.2. For application soo, all hosts can be matched, forwarding path is/app/soo, and private network address of the corresponding deployed container is 192.168.0.4.

Step 304, a processing request for a target application task sent by a client is received.

The processing request is generated by the client according to at least one accessible address of the target application task acquired from a central control server, the at least one accessible address is generated by the central server according to identification information of the target application task and address information of at least one target edge node for processing the target application task, each accessible address corresponds to address information of one target edge node, and the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task.

This step is specifically referred to as step 201.

It should be noted that, the processing request sent by the client for the target application task may include, for example, an HTTP request, a hypertext transfer security protocol (Hyper Text Transfer Protocol over SecureSocket Layer, HTTPs) request, a transmission control protocol (Transmission Control Protocol, TCP) request, a TCP-based full duplex communication protocol (Websocket) request, a file transfer protocol (File Transfer Protocol, FTP) request, a simple mail transfer protocol (Simple Mail Transfer Protocol, SMTP) request, a user datagram protocol (User Datagram Protocol, UDP) request, and the like.

The HTTPS request supports the service domain name certificate, so that the security in the network transmission process is ensured.

Step 305, determining the private network address of at least one target application container for processing the target application task according to the corresponding relation between the pre-stored identification information of the application task and the private network address of the application container.

This step may refer to step 202 specifically, and will not be described herein.

And step 306, calling a target application container matched with the subtask in the target edge node according to the address information of the target edge node and the private network address of the target application container, so that the called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

This step is specifically referred to as step 203.

For example, the application task may be a computing task in an application program, and when the computing task is implemented based on edge computing, a target edge node for processing the computing task may be set in at least one edge node in advance, a target application container for processing the computing task is disposed in the target edge node, and a correspondence between identification information of the computing task and a private network IP address of the target application container is stored in the target edge node. When the client initiates the calculation task, the processing request of the calculation task can be generated and sent to the target edge node, and the processing request carries the identification information of the calculation task, so that after the target edge node receives the processing request of the calculation task, the private network IP address of the target application container for processing the calculation task is determined, the target application container is called according to the private network IP address of the target application container to process the calculation task, and a calculation result is obtained and returned to the client.

Correspondingly, the application task may be an information uploading task in a certain application program, when the information uploading task is implemented based on edge calculation, a target edge node for processing the information uploading task may be set in at least one edge node in advance, a target application container for processing the information uploading task is disposed in the target edge node, and a correspondence between identification information of the information uploading task and a private network IP address of the target application container is stored in the target edge node. When the client initiates the information uploading task, a processing request of the information uploading task can be generated and sent to the target edge node, the processing request carries identification information of the information uploading task, after the target edge node receives the processing request of the information uploading task, a private network IP address of a target application container for processing the information uploading task is determined, and accordingly the target application container is called according to the private network IP address of the target application container to receive and finish storage of the uploaded information, and a processing result which is successfully uploaded is generated and returned to the client.

Optionally, a target application task may include at least one subtask, and correspondingly, the processing request of the target application task may further include identification information of the subtask, and step 306 may specifically include:

Sub-step 3061, determining the private network address of the target application container for processing each sub-task according to the corresponding relation between the pre-stored sub-task identification information and the private network address of the application container.

In this step, if the target application task is a relevant task such as calculation or information uploading for the application foo, and the target application task includes two subtasks: the identification information of the corresponding subtasks is respectively as follows: apps/foo-1 and apps/foo-2. The corresponding relation between the identification information of the subtasks and the private network address of the application container can be stored in the target edge node in advance, so that the private network address of the target application container for processing each subtask can be determined according to the identification information of the subtasks contained in the target application task and the corresponding relation.

TABLE 5

For example, if the target edge node for processing the target application task apps/foo is the edge node 1, table 5 may be a correspondence between the identification information of the subtasks stored in the edge node 1 in advance and the private network address of the application container, so that it can be known that there are two target application containers for processing the target application task in the edge node 1: the target application container with the private network address of 192.168.0.1 is used for executing the subtask 1 with the identification information of apps/foo-1 in the target application task, and the target application container with the private network address of 192.168.0.3 is used for executing the subtask 2 with the identification information of apps/foo-2 in the target application task.

And sub-step 3062, calling a target application container in the target edge node according to the address information of the target edge node and the private network address of the target application container, and respectively processing each subtask to obtain the processing result.

In the step, after the private network address of the target application container for processing each subtask in the target application task is determined in the target edge node, the target application container in the target edge node can be called according to the private network address of the target application container, each subtask is processed respectively, the target application task is completed, and the target processing result of the target application task is obtained, so that a single application task is realized by using the distributed deployed application containers, and the processing efficiency of the application task is improved.

For example, if the target edge node for processing the target application task apps/foo is edge node 1, there are two target application containers for processing the target application task in edge node 1: the target application container with the private network address of 192.168.0.1 is used for executing the subtask 1 with the app s/foo-1 as the identification information in the target application task, the target application container with the private network address of 192.168.0.3 is used for executing the subtask 2 with the app s/foo-2 as the identification information in the target application task, then the target application container with the private network address of 192.168.0.1 can be called to execute the subtask 1 with the app s/foo-1 as the identification information in the target application task, and the target application container with the private network address of 192.168.0.3 is called to execute the subtask 2 with the app s/foo-2 as the identification information in the target application task, thereby completing the whole target application task and obtaining the processing result of the target application task.

In addition, the subtasks in a single application task can be realized by using the distributed deployed application containers, so that each subtask in the single application task can be processed in parallel by a plurality of application containers, and the processing efficiency of the application task is improved.

Referring to fig. 5, a flowchart of steps in a method for implementing an application task based on edge computation according to an embodiment of the present invention is shown.

The implementation method of the application task based on the edge calculation is applied to the client.

Step 401, receiving at least one accessible address corresponding to a target application task sent by a central control server.

Step 402, generating a processing request for the target application task according to the at least one accessible address, wherein the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task.

Step 403, sending the processing request to the at least one target edge node according to the address information of the at least one target edge node.

Step 404, receiving the processing result fed back by the at least one target edge node.

Referring to fig. 6, a flowchart of steps in another implementation method of an application task based on edge computing according to an embodiment of the present invention is shown.

The implementation method of the application task based on the edge calculation is applied to the central control server.

Step 501, obtaining identification information of a target application task, and determining address information of at least one target edge node for processing the target application task by combining a corresponding relation between the prestored identification information of the application task and address information of the edge node for processing the application task.

For example, if the identification information of the target application task acquired by the central control server is: the correspondence between the prestored identification information of the application task and the address information of the edge node for processing the application task is the information listed in table 4, and then it can be determined that the address information of at least one target edge node for processing the target application task apps/foo is: address information of edge node 1: http://123.123.223.1, address information of edge node 2: http://123.123.223.2.

Step 502, generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task.

In this step, after determining address information of at least one target edge node that processes the target application task, the central control server may generate an accessible address of the target application task according to the address information of the target edge node and identification information corresponding to the target application task.

Step 503, the at least one accessible address is sent to the client.

In this step, after generating the accessible address of the target application task, the central control server may send the accessible address to the client, so that the client may generate a processing request for the target application task according to the accessible address, and send the processing request to the target edge node according to the address information of the target edge node, so that the target edge node determines, according to the identification information of the target application task, a private network address of at least one target application container for processing the target application task, and may further call the target application container to process the processing request, thereby obtaining a processing result.

Referring to fig. 7, a flowchart of specific steps in a method for implementing an application task based on edge computation according to an embodiment of the present invention is shown.

In step 601, an application container deployment request is generated, where the application container deployment request includes address information of an edge node and configuration information of an application container included in the edge node.

In this step, the central control server may configure the edge nodes in the edge room in advance, and the application containers contained in the edge nodes.

Specifically, the central control server may generate an application container deployment request, where the application container deployment request may include address information of the edge node and configuration information of an application container included in the edge node.

Optionally, the configuration information of the application containers includes the number of application containers contained in the edge node, usage resource information of each application container, and a mirror address.

Step 602, determining the edge node according to the address information of the edge node, creating the application container in the edge node according to the configuration information of the application container, and generating a private network address of the corresponding application container for the application container.

In this step, after generating the application container deployment request, the central control server may determine an edge node according to address information of the edge node in the application container deployment request, further, may create an application container in the edge node according to configuration information of the application container in the application container deployment request, and generate a private network address of the corresponding application container for the application container, thereby implementing distributed deployment of the application container.

Since the configuration information of the application container may include the number of application containers included in the edge node, the usage resource information of each application container, and the mirror address, when a plurality of application containers corresponding to the number of application containers are created in the edge node, a server (may also be referred to as a node) where a plurality of available resources correspond to the application container usage resource information may be selected according to the application container usage resource information, and a corresponding container is created on the selected server according to the mirror address of the application container.

In the embodiment of the invention, when the application container is created in the edge node and the private network address of the corresponding application container is generated for the application container, a docker single network can be used, and networks such as Flannel, calico can also be used. Wherein, the docker single-machine network can only realize the communication between different application containers in the same host, while the network Flannel, calico and the like can realize the communication across the host application containers.

Step 603, generating an application task configuration request, where the application task configuration request includes identification information of the application task, address information of an edge node for processing the application task, and a private network address of an application container for processing the application task in the edge node.

In this step, the central control server may generate an application task configuration request, so that the application configuration request may be sent to each edge node, so that the edge node generates a correspondence between identification information of the application task and a private network address of the application container.

Step 604, sending the application task configuration request to each edge node, so that the edge node generates a corresponding relationship between the identification information of the application task and the private network address of the application container according to the application task configuration request.

In this step, the central control server may further transmit the generated application task configuration request to each edge node after generating the application task configuration request.

Step 605, obtaining identification information of a target application task, and determining address information of at least one target edge node for processing the target application task by combining a corresponding relation between the prestored identification information of the application task and address information of the edge node for processing the application task.

This step may refer to step 501 specifically, and will not be described herein.

Step 606, generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task.

This step may refer to step 502 specifically, and will not be described herein.

Step 607, the at least one accessible address is sent to the client.

This step may refer to step 503 specifically, and will not be described herein.

In addition, as the application containers in the edge nodes can be deployed in advance, the application containers in distributed deployment are obtained, and therefore when a single application task is realized by using the application containers in distributed deployment, each subtask in the single application task is processed in parallel through a plurality of application containers, and the processing efficiency of the application task can be improved.

Referring to FIG. 1, a schematic diagram of an edge computing system according to an embodiment of the present invention is shown, the edge computing system includes: at least one edge node, a central control server and a client, each edge node comprises at least one application container and a proxy server.

The central control server is used for acquiring the identification information of the target application task, and determining the address information of at least one target edge node for processing the target application task by combining the prestored corresponding relation between the identification information of the application task and the address information of the edge node for processing the application task; generating at least one accessible address of the target application task according to the address information of the at least one target edge node and the identification information corresponding to the target application task, wherein each accessible address corresponds to the address information of one target edge node; the at least one accessible address is sent to the client.

The client is used for receiving the at least one accessible address sent by the central control server and generating a processing request aiming at the target application task according to the at least one accessible address, wherein the processing request comprises address information of at least one target edge node for processing the target application task and identification information of the target application task; and sending the processing request to the at least one target edge node according to the address information of the at least one target edge node.

On the basis of the embodiment, the embodiment of the invention also provides a device for realizing the application task based on the edge calculation.

Referring to fig. 8, a block diagram of a target edge node 700 according to an embodiment of the present invention is shown, where the target edge node includes at least one application container and a proxy server, where the application container is configured to process an application task and obtain a processing result, and the proxy server is configured to receive a processing request for the target application task sent by a client, where the processing request includes address information of at least one target edge node that processes the target application task and identification information of the target application task; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and calling at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the target application container, so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

Referring to fig. 9, a block diagram of an implementation apparatus 800 of an application task based on edge computing according to an embodiment of the present invention is shown, which is applied to a client, and may specifically include the following modules:

an accessible address receiving module 801, configured to receive at least one accessible address corresponding to a target application task sent by a central control server, where each accessible address corresponds to address information of a target edge node;

a processing request generating module 802, configured to generate, according to the at least one accessible address, a processing request for the target application task, where the processing request includes address information of at least one target edge node that processes the target application task, and identification information of the target application task;

a processing request sending module 803, configured to send, according to address information of the at least one target edge node, a processing request for the target application task to the at least one target edge node, so that the at least one target edge node determines, according to identification information of the target application task, a private network address of at least one target application container for processing the target application task, and invokes the at least one target application container to process the processing request, thereby obtaining a processing result;

A processing result receiving module 804, configured to receive the processing result fed back by the at least one target edge node.

Referring to fig. 10, a block diagram of still another implementation apparatus 900 of an application task based on edge computing according to an embodiment of the present invention is shown, which is applied to a central control server, and may specifically include the following modules:

the edge node determining module 901 is configured to obtain identification information of a target application task, and determine address information of at least one target edge node for processing the target application task by combining a corresponding relationship between the prestored identification information of the application task and address information of an edge node for processing the application task;

an accessible address generating module 902, configured to generate at least one accessible address of the target application task according to address information of the at least one target edge node and identification information corresponding to the target application task, where each accessible address corresponds to address information of one target edge node;

an accessible address sending module 903, configured to send the at least one accessible address to a client.

For the above-described device embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, with reference to the description of the method embodiments in part.

The embodiment of the present invention also provides an electronic device, as shown in fig. 11, including a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004, where the processor 1001, the communication interface 1002, and the memory 1003 complete communication with each other through the communication bus 1004,

a memory 1003 for storing a computer program;

the processor 1001 is configured to execute a program stored in the memory 1003, and implement the following steps:

a method for implementing an application task based on edge computation, applied to a target edge node, the target edge node including at least one application container and one proxy server, the method comprising:

An implementation method of an application task based on edge calculation is applied to a client, and the method comprises the following steps:

An implementation method of an application task based on edge calculation is applied to a central control server, and the method comprises the following steps:

the at least one accessible address is sent to the client.

The communication bus mentioned by the above terminal may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the terminal and other devices.

The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In yet another embodiment of the present invention, a computer readable storage medium is provided, where instructions are stored, which when executed on a computer, cause the computer to perform the method for implementing the edge computing based application task according to any of the above embodiments.

In yet another embodiment of the present invention, a computer program product comprising instructions that, when executed on a computer, cause the computer to perform the method for implementing the edge-computing-based application task of any of the above embodiments is also provided.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for implementing an application task based on edge computing, the method being applied to an edge computing system, the edge computing system including at least one edge node, a central control server and a client, each edge node including at least one application container and one proxy server, the method comprising:

2. A method for implementing an application task based on edge computing, applied to a target edge node, the target edge node including at least one application container and a proxy server, the method comprising:

3. The method of claim 2, wherein prior to the step of receiving a processing request for a target application task sent by the client, the method further comprises:

Receiving an application task configuration request sent by a central control server, wherein the application task configuration request comprises identification information of an application task, address information of an edge node for processing the application task and a private network address of an application container for processing the application task in the edge node;

acquiring address information of the target edge node, and inquiring identification information of an application task matched with the target edge node and a private network address of an application container from the application task configuration request according to the address information of the target edge node;

and correspondingly storing the identification information of the application task and the private network address of the application container according to the identification information of the application task matched with the target edge node and the private network address of the application container.

4. The method according to claim 2, wherein the target application task comprises at least one subtask, and the processing request further comprises identification information of the subtask;

the step of calling at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the at least one target application container so that the at least one called target application container processes the processing request to obtain a processing result comprises the following steps:

Determining a private network address of a target application container for processing the subtasks according to a corresponding relation between the prestored identification information of the subtasks and the private network address of the application container;

and calling a target application container matched with the subtask in the target edge node according to the address information of the target edge node and the private network address of the target application container, so that the called target application container processes the subtask to obtain a processing result.

5. The method for realizing the application task based on the edge calculation is characterized by being applied to a client, and comprises the following steps:

6. The method of claim 5, wherein the address information of the target edge node includes public network address and port information corresponding to the target edge node.

7. A method for implementing an application task based on edge computation, which is applied to a central control server, the method comprising:

and sending the at least one accessible address to a client so that the client generates a processing request for the target application task according to the accessible address, and sending the processing request to the target edge node according to the address information of the target edge node, so that the target edge node determines a private network address of at least one target application container for processing the target application task according to the identification information of the target application task, and calls the target application container to process the processing request to obtain a processing result.

8. The method according to claim 7, wherein prior to the step of obtaining identification information of the target application task, the method comprises:

generating an application task configuration request, wherein the application task configuration request comprises identification information of the application task, address information of an edge node for processing the application task and a private network address of an application container for processing the application task in the edge node;

and sending the application task configuration request to each edge node so that the edge node can generate a corresponding relation between the identification information of the application task and the private network address of the application container according to the application task configuration request.

9. The method of claim 8, wherein prior to the step of generating an application task configuration request, the method further comprises:

generating an application container deployment request, wherein the application container deployment request comprises address information of an edge node and configuration information of an application container contained in the edge node;

and determining the edge node according to the address information of the edge node, creating the application container in the edge node according to the configuration information of the application container, and generating a private network address of the corresponding application container for the application container.

10. The method of claim 9, wherein the configuration information of the application containers includes the number of application containers contained in the edge node, usage resource information of each of the application containers, and a mirror address.

11. An edge computing system, the edge computing system comprising: at least one edge node, a central control server and a client, wherein each edge node comprises at least one application container and one proxy server;

12. The target edge node is characterized in that the target edge calculation comprises at least one application container and a proxy server, wherein the application container is used for processing application tasks and obtaining processing results, and the proxy server is used for receiving a processing request for the target application tasks, which is sent by a client, wherein the processing request comprises address information of at least one target edge node for processing the target application tasks and identification information of the target application tasks; determining a private network address of at least one target application container for processing the target application task according to a corresponding relation between the prestored identification information of the application task and the private network address of the application container; and calling at least one target application container in the target edge nodes according to the address information of the target edge nodes and the private network address of the at least one target application container so that the at least one called target application container processes the processing request to obtain a processing result, and feeding back the processing result to the client.

13. An apparatus for implementing an application task based on edge computation, applied to a client, the apparatus comprising:

14. An apparatus for implementing an application task based on edge computation, applied to a central control server, the apparatus comprising:

the accessible address sending module is used for sending the at least one accessible address to the client so that the client can generate a processing request aiming at the target application task according to the accessible address, and sending the processing request to the target edge node according to the address information of the target edge node, so that the target edge node can determine a private network address of at least one target application container for processing the target application task according to the identification information of the target application task, and the target application container is called to process the processing request to obtain a processing result.

15. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus;

the memory is used for storing a computer program;

the processor is configured to implement the method steps of any one of claims 1-10 when executing a program stored on the memory.

16. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1-10.