CN115834466B - Method, device, equipment, system and storage medium for analyzing path of computing power network - Google Patents

Abstract

The present application provides a computing power network path analysis method, device, equipment, system and storage medium, the method comprising: for the resource occupancy rate of the link between each server node and each target routing node at the current moment, the following steps are performed: according to the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment, the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is determined, and according to the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate, weight and threshold value of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the current moment is determined. The method provided by the present application can solve the problem of ultra-low latency requirements while ensuring that computing power resources are fully utilized.

Description

Computing power network path analysis method, device, equipment, system and storage medium

Technical Field

The embodiments of the present application relate to the field of data processing technology, and in particular to a computing power network path analysis method, device, equipment, system and storage medium.

Background technique

With the continuous development of artificial intelligence and mobile Internet technologies, a large number of new business applications have emerged. These new business applications usually consume huge computing resources, storage resources and energy. The computing power of current smart terminal devices is still relatively limited, and the battery capacity is also relatively low, which cannot meet the processing requirements of these new business applications. Therefore, cloud computing is proposed. Cloud computing uses virtualization technology to establish a large-capacity computing resource pool so that various applications can obtain the required computing resources, storage resources, and software and platform services. Although the emergence of cloud computing meets the needs of computing-intensive business processing, some applications are also sensitive to latency. In many cases, the transmission latency from the terminal to the cloud cannot meet the ultra-low latency requirements of this type of application. For this reason, edge computing technology can be used.

However, the large-scale deployment of edge computing devices and smart terminal devices, although solving the problem of long latency caused by uploading massive data in the network to the cloud computing center, also makes computing resources show a trend of ubiquitous deployment. On the one hand, the edge computing nodes do not perform effective collaborative processing tasks, and the computing resources of a single node cannot meet the computing resource requirements of ultra-large computing-intensive tasks such as image rendering, and still cannot solve the ultra-low latency requirements of new businesses that are both computing-intensive and latency-sensitive. On the other hand, although some edge computing nodes are overloaded and cannot effectively process computing tasks, due to the imbalance of network load, some computing nodes are bound to remain idle, resulting in the inability to fully utilize the computing resources of the edge network.

Therefore, existing technologies cannot effectively analyze the paths of computing power networks, and thus cannot solve the problem of ultra-low latency requirements while ensuring that computing power resources are fully utilized.

Summary of the invention

The present application provides a computing power network path analysis method, device, equipment, system and storage medium, which can solve the problem of ultra-low latency demand while ensuring that computing power resources are fully utilized.

In a first aspect, the present application provides a computing power network path analysis method, which is applied to a computing power network system, including:

Obtaining resource occupancy rates of links between each server node and each target routing node at the current moment, resource occupancy rates of links between each server node and each target routing node at the previous moment, and weights of links between each server node and each target routing node at the previous moment, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes; wherein one server node corresponds to one target routing node;

For the resource occupancy rate of the link between each server node and each target routing node at the current moment, the following steps are performed: according to the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment, the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is determined;

Determine the weight of the link between each server node and each target routing node at the current moment according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value;

Among them, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path in the computing power network.

In a possible design, the threshold value includes a first threshold value and a second threshold value, and the first threshold value is less than the second threshold value; determining the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment according to the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment and the threshold value, includes:

If the resource occupancy rate of the link between the server and the corresponding target routing node is less than the first threshold value, determining that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource light load;

If the resource occupancy rate of the link between the server node and the corresponding target routing node is greater than or equal to the first threshold value and less than the second threshold value, it is determined that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource medium load;

If the resource occupancy rate of the link between the server node and the corresponding target routing node is greater than or equal to the second threshold value and less than 1, it is determined that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource overload.

In a possible design, the weight of the link between each server node and each target routing node at the current moment is determined according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value, including:

For each of the servers, determine a weight calculation model according to the resource load scenario type, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and a threshold value;

According to the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment, the weight calculation model is used to obtain the weight of the link between each server node and each target routing node at the current moment.

In a possible design, determining a weight calculation model according to the resource load scenario type, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and a threshold value includes:

According to the resource load scenario type, by comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment with the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment with a threshold value, a weight calculation model and a multiple of the weight coefficient used in the weight calculation model to calculate the link between the server node and the corresponding target routing node at the current moment are determined.

In one possible design, the method further includes:

The weight of the link between the server node and the corresponding target routing node at the current moment is updated to the network topology structure of the computing power network system.

In one possible design, the method further includes:

Obtaining a weight of a link between two routing nodes on the same link among the multiple routing nodes;

The shortest path of the computing power network is determined according to the weight of the link between the two routing nodes on the same link and the weight of the link between each server node and the corresponding target router.

In a second aspect, the present application provides a computing power network path analysis device, which is applied to a computing power network system, wherein the computing power network system includes multiple server nodes and multiple routing nodes, and the device includes:

An acquisition module, used to acquire resource occupancy rates of links between each server node and each target routing node at the current moment, resource occupancy rates of links between each server node and each target routing node at the previous moment, and weights of links between each server node and each target routing node at the previous moment, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes; wherein one server node corresponds to one target routing node;

The determination module is used to perform the following steps for the resource occupancy rate of the link between each server node and each target routing node at the current moment: determine the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment according to the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment;

A path analysis module, used to determine the weight of the link between each server node and each target routing node at the current moment according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value;

Among them, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path in the computing power network.

In a third aspect, the present application provides an electronic device, comprising: at least one processor and a memory;

The memory stores computer-executable instructions;

The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the computing power network path analysis method described in the first aspect and the possible design of the first aspect.

In a fourth aspect, the present application provides a computing power network system, comprising: the electronic device as described in the third aspect, multiple server nodes and multiple routing nodes.

In a fifth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the computing power network path analysis method described in the first aspect and the possible design of the first aspect is implemented.

The computing power network path analysis method, device, equipment, system and storage medium provided in this embodiment are applied to a computing power network system, wherein the computing power network system includes multiple server nodes and multiple routing nodes; firstly, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment and the weight of the link between each server node and each target routing node at the previous moment are obtained, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes; wherein one server node corresponds to one target routing node; then, the following steps are performed for the resource occupancy rate of the link between each server node and each target routing node at the current moment. : According to the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment, determine the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment; according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value, determine the weight of the link between each server node and each target routing node at the current moment; wherein, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path of the computing power network. Therefore, the present application obtains the resource occupancy rates corresponding to the previous moment and the current moment respectively, and then determines the weights of the server node and the target routing node at the current moment in combination with the weights of the server node and the target routing node at the previous moment and the gate value, comprehensively analyzes the weights of the server node and the target routing node at the current moment, and realizes dynamic update of weights based on resource occupancy, and then determines a shortest path resource selected for the business based on the updated weight, thereby realizing rational use of resources and solving the problem of ultra-low latency requirements based on the shortest path.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

FIG1 is a schematic diagram of a scenario of a computing power network path analysis method provided in an embodiment of the present application;

FIG2 is a schematic diagram of a flow chart of a computing power network path analysis method provided in an embodiment of the present application;

FIG3 is a flow chart of a computing power network path analysis method provided in yet another embodiment of the present application;

FIG4 is a schematic diagram of the structure of a computing power network path analysis device provided in an embodiment of the present application;

FIG5 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

At present, the large-scale deployment of edge computing devices and smart terminal devices has solved the problem of long latency caused by uploading massive data in the network to the cloud computing center, but it has also led to a trend of ubiquitous deployment of computing resources. On the one hand, the edge computing nodes do not perform effective collaborative processing tasks, and the computing resources of a single node cannot meet the computing resource requirements of ultra-large computing-intensive tasks such as image rendering, and still cannot solve the ultra-low latency requirements of new services that are both computing-intensive and latency-sensitive. On the other hand, although some edge computing nodes are overloaded and cannot effectively process computing tasks, due to the imbalance of network load, some computing nodes are bound to remain idle, resulting in the inability to fully utilize the computing resources of the edge network. Therefore, the existing technology cannot effectively analyze the path of the computing network, and thus cannot solve the problem of ultra-low latency requirements while ensuring that computing resources are fully utilized.

In order to solve the above problems, the technical concept of the present application is: by obtaining the resource occupancy rates corresponding to the previous moment and the current moment respectively, and then combining the weights of the server node and the target routing node at the previous moment and the gate value, the weights of the server node and the target routing node at the current moment are determined, and the weights of the server node and the target routing node at the current moment are comprehensively analyzed to realize dynamic update of the weights based on the resource occupancy, and then determine a shortest path resource selected for the business based on the updated weight, thereby realizing the rational use of resources and solving the ultra-low latency requirement problem based on the shortest path.

Explanation of terms:

W _{RR_ij} : the weight value between routing node i and routing node j;

W _{RN_ij_t} : the weight value between routing node i and computing server node (i.e. server node) j at time t (which can be used as the current time);

W _{RN_ij_t-1} : the weight value between routing node i and computing server node j at time t-1 (can be used as the previous time);

R _{RN_ij_t} : resource occupancy rate between routing node i and computing server node j at time t;

R _{RN_ij_t-1} : resource occupancy rate between routing node i and computing server node j at time t-1;

Th1: first threshold value;

Th2: second threshold value;

α: weight coefficient.

Refer to Figure 1, which is a scenario diagram of the computing power network path analysis method provided in an embodiment of the present application. Figure 1 shows a computing power network system, including multiple server nodes (such as server node 1, namely N1, server node 2, namely N2) and multiple routing nodes (such as routing node 1, namely R1, routing node 2, namely R2, routing node 3, namely R3, routing node 4, namely R4, routing node 5, namely R5, routing node 6, namely R6). Among them, the routing node is used for network signal transmission, that is, the business information initiated by the terminal device is transmitted through the link between the routing nodes; the server node is used to provide corresponding business services according to the business information initiated by the received terminal device.

By considering the usage of server resources, the routing weights (taking time t as an example, the routing weights here are W _{RN_31_t} , W _{RN_52_t} ) between the server (here refers to the server nodes, such as N1, N2) and the router (here refers to the routing nodes, such as R3, R5) are dynamically perceived, and network path calculation is performed, thereby greatly improving the utilization of network resources. Among them, the weights of the links between routing nodes (such as W _{RR_12} , W _{RR_13} , W _{RR_23} , W _{RR_24} , W _{RR_25} , W _{RR_35} , W _{RR_45} , W _{RR_46} , W _{RR_56} ) are determined based on the characteristics of the length of network signal lines such as optical fibers. Therefore, by obtaining the resource occupancy rates corresponding to the previous moment and the current moment, and then combining the weights of the server node and the target routing node at the previous moment and the gate value to determine the weights of the server node and the target routing node at the current moment, the weights of the server node and the target routing node at the current moment are comprehensively analyzed to achieve dynamic update of weights based on resource occupancy, and then determine the shortest path resource selected for the business based on the updated weight, thereby achieving reasonable utilization of resources and solving the problem of ultra-low latency requirements based on the shortest path.

The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

See Figure 2, which is a flow chart of the computing power network path analysis method provided in an embodiment of the present application.

Referring to FIG. 2 , the computing power network path analysis method is applied to a computing power network system, wherein the computing power network system includes a plurality of server nodes and a plurality of routing nodes; the method includes:

S201. Obtain the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes.

Among them, one server node corresponds to one target routing node, that is, one server node is directly connected to one target routing node.

In this embodiment, in order to dynamically update the weight of the link between the server and the router, the weight and resource occupancy at the previous moment and the resource occupancy corresponding to the current moment may be obtained, and the weight at the current moment may be recalculated.

S202. For the resource occupancy rate of the link between each server node and each target routing node at the current moment, the following steps are performed: based on the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment, the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is determined.

In this embodiment, for each server, due to the different resource occupancy rates on the link between the server node and the corresponding target routing node, the resource load scenario types corresponding to the link between the server node and the corresponding target routing node at the current moment are different. Specifically, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment is compared with the threshold value, and the resource load scenario type on the link at the current moment is determined according to the comparison result.

S203. Determine the weight of the link between each server node and each target routing node at the current moment according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value.

Among them, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path in the computing power network.

The weight of the link between each server node and each target routing node at the current moment is the weight corresponding to the resource occupancy rate of the link between each server node and each target routing node at the current moment. The tighter the resources, the greater the weight, and the path is bypassed as much as possible. Therefore, based on the weight, the shortest path that can make reasonable use of resources can be calculated.

In this embodiment, according to the determined resource load scenario type, the scenario to which the weight calculation method belongs is then determined; in the scenario to which the calculation method belongs, based on the resource occupancy rate of the link between each server and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value, the weight calculation method is determined to obtain the weight of the link between each server node and each target routing node at the current moment. Then, according to the weight of the link between each server node and each target routing node at the current moment, combined with the weight of the link between the routing nodes, a shortest path is selected as the resource path provided for the service initiated by the terminal device, and the server node on the path is the resource allocated to the service.

The computing network path analysis method provided in this embodiment is applied to a computing network system, wherein the computing network system includes multiple server nodes and multiple routing nodes; firstly, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment are obtained, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes; wherein one server node corresponds to one target routing node; then, for the resource occupancy rate of the link between each server node and each target routing node at the current moment, the following steps are performed: according to the resource occupancy rate of the link at the current moment The resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node determine the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment; according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value, determine the weight of the link between each server node and each target routing node at the current moment; wherein, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path of the computing power network. Therefore, the present application obtains the resource occupancy rate corresponding to the previous moment and the current moment respectively, and then determines the weight of the server node and the target routing node at the current moment in combination with the weight of the server node and the target routing node at the previous moment and the value under the gate, comprehensively analyzes the weight of the server node and the target routing node at the current moment, realizes the dynamic update of the weight based on the resource occupancy situation, and then determines the shortest path resource selected for the business based on the updated weight, realizes the rational use of resources, and solves the problem of ultra-low latency demand based on the shortest path.

In a possible design, this embodiment, based on the above embodiment, provides a detailed description of how to determine the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment. The threshold value includes a first threshold value and a second threshold value, and the first threshold value is less than the second threshold value; the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is determined based on the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment, which can be achieved by the following steps:

Step a1: if the resource occupancy rate of the link between the server and the corresponding target routing node is less than a first threshold value, determining that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource light load;

Step a2: if the resource occupancy rate of the link between the server node and the corresponding target routing node is greater than or equal to the first threshold value and less than the second threshold value, then determine that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource medium load;

Step a3: If the resource occupancy rate of the link between the server node and the corresponding target routing node is greater than or equal to the second threshold value and less than 1, determine that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource overload.

In this embodiment, when 0≤R _{RN_ij_t} <Th1, it indicates that the resource is lightly loaded and the server Nj should be selected preferentially, that is, the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at time t is lightly loaded.

When Th1≤R _{RN_ij_t} ＜Th2, it indicates that the resource is lightly loaded and there is no preference for selecting the server Nj, that is, the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at time t (which can be regarded as the current time here) is medium resource load.

When Th2≤R _{RN_ij_t} <1, it indicates resource overload and the server Nj should be avoided. That is, the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at time t (which can be regarded as the current time) is resource overload.

In a possible design, this embodiment provides a detailed description of S203 based on the above embodiment. According to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value, the weight of the link between each server node and each target routing node at the current moment is determined, which can be achieved by the following steps:

Step b1: for each server, determine the weight calculation model according to the resource load scenario type, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and the threshold value.

In a possible design, a weight calculation model is determined according to the resource load scenario type, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and a threshold value, which can be implemented by the following steps:

According to the resource load scenario type, by comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment with the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment with a threshold value, a weight calculation model and a multiple of the weight coefficient used in the weight calculation model to calculate the link between the server node and the corresponding target routing node at the current moment are determined.

In this embodiment: if the resource load scenario type is resource light load, that is, 0≤R _{RN_ij_t} <Th1, the following two situations can be analyzed, the situation at the current moment is selected, and then the weight calculation model is determined.

Case 11: If R _{RN_ij_t} -R _{RN_ij_t-1} ≤ 0

1) When Th1≤R _{RN_ij_t-1} ＜Th2, k is set to an odd number, and the weight calculation model is:

W _{RN — ij — t = W RN — ij — t-1} *[1+2α*(-1) ^k (|R _RN — ij _{— t -R RN — ij — t-1} |/R _RN — ij — t )];

Here, the multiple of the weight coefficient is 2. Since the resource occupancy rate corresponding to the current moment is not greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the previous moment is between two threshold values, it means that the weight of the link between the server node and the corresponding target routing node at the current moment is lower than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an odd number, and the multiple of α is greater than 1, such as 2.

2) When Th2≤R _{RN_ij_t-1} ＜1, k is set to an odd number, and the weight calculation model is:

W _{RN_ij_t} = W _{RN_ij_t-1} *[1+3α(-1) ^k (|R _{RN_ij_t} -R _{RN_ij_t-1} |/R _{RN_ij_t} )];

The multiple of the weight coefficient is 3. Since the resource occupancy rate corresponding to the current moment is not greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the previous moment is greater than the second threshold value (the large threshold value), it means that the weight of the link between the server node and the corresponding target routing node at the current moment is lower than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an odd number, and it is larger than the multiple of α described in (1) in Case 21, such as 2.

Case 12: If R _{RN_ij_t} -R _{RN_ij_t-1} > 0, set k to an even number, and the weight calculation model is:

W _{RN_ij_t} = W _{RN_ij_t-1} *[1+α*(-1) ^k (|R _{RN_ij_t} -R _{RN_ij_t-1} |/R _{RN_ij_t} )];

The multiple of the weight coefficient is 1. Since the resource occupancy rate corresponding to the current moment is greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the current moment is not greater than the first threshold value, it means that the weight of the link between the server node and the corresponding target routing node at the current moment is higher than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an even number, and the multiple of α can be 1.

If the resource load scenario type is medium resource load, that is, Th1≤R _{RN_ij_t} ＜Th2, the following two situations can be analyzed, and the situation at the current moment can be selected to determine the weight calculation model.

Case 21: If R _{RN_ij_t} -R _{RN_ij_t-1} ≤ 0

1) When Th1≤R _{RN_ij_t-1} ＜Th2, k is set to an odd number, and the weight calculation model is:

W _{RN_ij_t} = W _{RN_ij_t-1} *[1+α*(-1) ^k (|R _{RN_ij_t} -R _{RN_ij_t-1} |/R _{RN_ij_t} )];

The multiple of the weight coefficient is 1. Since the resource occupancy rate corresponding to the current moment is not greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the previous moment is between two threshold values, it means that the weight of the link between the server node and the corresponding target routing node at the current moment is lower than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an odd number, and the multiple of α can be 1.

2) When Th2≤R _{RN_ij_t-1} ＜1, k is set to an odd number, and the weight calculation model is:

W _{RN_ij_t} = W _{RN_ij_t-1} *[1+2α(-1) ^k (|R _{RN_ij_t} -R _{RN_ij_t-1} |/R _{RN_ij_t} )];

The multiple of the weight coefficient is 2. Since the resource occupancy rate corresponding to the current moment is not greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the previous moment is greater than the second threshold value (the large threshold value), it means that the weight of the link between the server node and the corresponding target routing node at the current moment is lower than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an odd number, and it is larger than the multiple of α described in (1) in Case 21, such as 2.

Case 22: If R _{RN_ij_t} -R _{RN_ij_t-1} ＞0

1) When 0≤R _{RN_ij_t-1} ＜Th1, k is set to an even number, and the weight calculation model is:

W _{RN — ij — t = W RN — ij — t-1} *[1+2α*(-1) ^k (|R _RN — ij _{— t -R RN — ij — t-1} |/R _RN — ij — t )];

Here, the multiple of the weight coefficient is 2. Since the resource occupancy rate corresponding to the current moment is greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the current moment is less than the first threshold value, it means that the weight of the link between the server node and the corresponding target routing node at the current moment is higher than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an even number, and the multiple of α can be 2.

2) When Th1≤R _{RN — ij — t-1} <Th2, W _{RN — ij — t} =W _{RN — ij — t} -1.

If the resource load scenario type is resource overload, that is, Th2≤R _{RN_ij_t} ＜1, the following two situations can be analyzed, and the situation at the current moment can be selected to determine the weight calculation model.

Case 31: If R _RN — ij — t −R _{RN — ij —} t −1≤0, then W _{RN — ij — t} =W _{RN — ij — t−1} .

Case 32: If R _{RN_ij_t} -R _{RN_ij_t-1} ＞0

1) When 0≤R _{RN_ij_t-1} ＜Th1, k is set to an even number, and the weight calculation model is:

W _{RN — ij — t = W RN — ij — t-1} *[1+2α*(-1) ^k (|R _RN — ij _{— t -R RN — ij — t-1} |/R _RN — ij — t )];

Here, the multiple of the weight coefficient is 2. Since the resource occupancy rate corresponding to the current moment is greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the current moment is less than the first threshold value, it means that the weight of the link between the server node and the corresponding target routing node at the current moment is higher than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned to an even number, and the multiple of α can be 2.

2) When Th1≤R _{RN_ij_t-1} ＜Th2, k is set to an even number, and the weight calculation model is:

W _{RN — ij — t = W RN — ij — t-1} *[1+3α*(-1) ^k (|R _RN — ij _{— t -R RN — ij — t-1} |/R _RN — ij — t )];

Here, the multiple of the weight coefficient is 3. Since the resource occupancy rate corresponding to the current moment is greater than the resource occupancy rate corresponding to the previous moment, and the resource occupancy rate corresponding to the previous moment is between two threshold values, it means that the weight of the link between the server node and the corresponding target routing node at the current moment is higher than the weight of the link between the server node and the corresponding target routing node at the previous moment. At this time, k is assigned an even number, and it is a large multiple of α described in (1) in case 32, such as 3.

Step b2: according to the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment, the weight calculation model is used to obtain the weight of the link between each server node and each target routing node at the current moment.

In this embodiment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment are input into the weight calculation model to obtain the weight of the link between each server node and each target routing node at the current moment.

In a possible design, based on the above embodiment, the method of this embodiment can also be implemented by the following steps:

The weight of the link between the server node and the corresponding target routing node at the current moment is updated to the network topology structure of the computing power network system.

In this embodiment, after the network topology weight is set, the weight is dynamically updated. Then, based on the updated weight, resources are allocated and the shortest path is selected. The tighter the resources, the greater the weight, and the path is bypassed as much as possible. Therefore, based on the weight, the shortest path that can make reasonable use of resources can be calculated.

In a possible design, the method can also be implemented by the following steps:

Obtaining a weight of a link between two routing nodes on the same link among the multiple routing nodes;

The shortest path of the computing power network is determined according to the weight of the link between the two routing nodes on the same link and the weight of the link between each server node and the corresponding target router.

In this embodiment, the server resources to be allocated are determined by combining the weights of the links between two routing nodes on the same link among the multiple routing nodes and the weights of the links between each of the server nodes and the corresponding target routers, and then the shortest path is determined from all the links from the terminal device to the selected server node. The shortest path calculation is performed using the Dijkstra algorithm, which is not specifically limited here.

Specifically, as shown in FIG3, FIG3 is a flow chart of a computing power network path analysis method provided by another embodiment of the present application. By obtaining the resource occupancy rates corresponding to the previous moment and the current moment, and then combining the weights of the server node and the target routing node at the previous moment and the gate value, the weights of the server node and the target routing node at the current moment are determined, and the weights of the server node and the target routing node at the current moment are comprehensively analyzed. Based on the weights of the links between the two routing nodes on the same link and the weights of the links between each server node and the corresponding target router, the shortest path of the computing power network is determined. The dynamic update of weights based on resource occupancy is realized, and then the shortest path resource selected for the business is determined based on the updated weights, which realizes the rational use of resources and solves the problem of ultra-low latency requirements based on the shortest path.

In order to implement the computing power network path analysis method, this embodiment provides a computing power network path analysis device. Referring to FIG. 4 , FIG. 4 is a schematic diagram of the structure of the computing power network path analysis device provided in the embodiment of the present application; the computing power network path analysis device 40 is applied to a computing power network system, and the computing power network system includes multiple server nodes and multiple routing nodes, and the device includes:

The acquisition module 401 is used to acquire the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes; wherein one server node corresponds to one target routing node;

The determination module 402 is used to perform the following steps for the resource occupancy rate of the link between each server node and each target routing node at the current moment: determine the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment according to the resource occupancy rate and threshold value of the link between the server node and the corresponding target routing node at the current moment;

The path analysis module 403 is used to determine the weight of the link between each server node and each target routing node at the current moment according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value;

Among them, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path in the computing power network.

In this embodiment, an acquisition module 401, a determination module 402, and a path analysis module 403 are set to acquire the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment, wherein the target routing node is a routing node directly connected to each server node among the multiple routing nodes; wherein one server node corresponds to one target routing node; and then the following steps are performed for the resource occupancy rate of the link between each server node and each target routing node at the current moment: according to the resource occupancy rate of the link between the server node and the corresponding routing node at the current moment, The resource occupancy rate and threshold value of the link between the corresponding target routing nodes determine the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment; according to the resource load scenario type, the resource occupancy rate of the link between each server node and each target routing node at the current moment, the resource occupancy rate of the link between each server node and each target routing node at the previous moment, the weight of the link between each server node and each target routing node at the previous moment, and the threshold value, determine the weight of the link between each server node and each target routing node at the current moment; wherein, the weight of the link between each server node and each target routing node at the current moment is used to determine the shortest path of the computing power network. Therefore, the present application obtains the resource occupancy rate corresponding to the previous moment and the current moment respectively, and then determines the weight of the server node and the target routing node at the current moment in combination with the weight of the server node and the target routing node at the previous moment and the value under the gate, comprehensively analyzes the weight of the server node and the target routing node at the current moment, realizes the dynamic update of the weight based on the resource occupancy situation, and then determines a shortest path resource selected for the business based on the updated weight, realizes the rational use of resources, and solves the problem of ultra-low latency demand based on the shortest path.

The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

In a possible design, the threshold value includes a first threshold value and a second threshold value, and the first threshold value is less than the second threshold value; and the determining module is specifically configured to:

When the resource occupancy rate of the link between the server and the corresponding target routing node is less than the first threshold value, determining that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource light load;

When the resource occupancy rate of the link between the server node and the corresponding target routing node is greater than or equal to the first threshold value and less than the second threshold value, determining that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource medium load;

When the resource occupancy rate of the link between the server node and the corresponding target routing node is greater than or equal to the second threshold value and less than 1, it is determined that the resource load scenario type corresponding to the link between the server node and the corresponding target routing node at the current moment is resource overload.

In a possible design, the path analysis module includes: a weight calculation model determination unit and a weight determination unit;

A weight calculation model determination unit, configured to determine a weight calculation model for each of the servers according to the resource load scenario type, the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and a threshold value;

The weight determination unit is used to obtain the weight of the link between each server node and each target routing node at the current moment through the weight calculation model according to the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and the weight of the link between each server node and each target routing node at the previous moment.

In a possible design, the weight calculation model determination unit is specifically used to:

According to the resource load scenario type, by comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment with the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment, and comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment with a threshold value, a weight calculation model and a multiple of the weight coefficient used in the weight calculation model to calculate the link between the server node and the corresponding target routing node at the current moment are determined.

In one possible design, the apparatus further includes: a weight updating module; and a weight updating module configured to:

The weight of the link between the server node and the corresponding target routing node at the current moment is updated to the network topology structure of the computing power network system.

In a possible design, the path analysis module is further used to:

Obtaining a weight of a link between two routing nodes on the same link among the multiple routing nodes;

The shortest path of the computing power network is determined according to the weight of the link between the two routing nodes on the same link and the weight of the link between each server node and the corresponding target router.

In order to implement the computing power network path analysis method, the present embodiment provides an electronic device. Figure 5 is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. As shown in Figure 5, the electronic device 50 of the present embodiment includes: at least one processor 501 and a memory 502; wherein the memory 502 is used to store computer-executable instructions; at least one processor 501 is used to execute the computer-executable instructions stored in the memory to implement the various steps performed in the above embodiments. For details, please refer to the relevant description in the aforementioned method embodiment.

An embodiment of the present application also provides a computing power network system, including: the electronic device as described above, multiple server nodes and multiple routing nodes.

An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the computing power network path analysis method as described above is implemented.

In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. In addition, each functional module in each embodiment of the present application can be integrated into a processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. It should be understood that the above-mentioned processor can be a central processing unit (English: Central Processing Unit, referred to as: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, referred to as: DSP), application-specific integrated circuits (English: Application Specific Integrated Circuit, referred to as: ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the invention can be directly embodied as a hardware processor to be executed, or the hardware and software modules in the processor can be combined and executed.

The memory may include high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk, etc. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus. The above-mentioned storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a disk or an optical disk. The storage medium may be any available medium that can be accessed by a general or special-purpose computer.

An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc., various media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims (10)

1. The power calculation network path analysis method is characterized by being applied to a power calculation network system, wherein the power calculation network system comprises a plurality of server nodes and a plurality of routing nodes; the method comprises the following steps:

acquiring the resource occupancy rate of links between each server node and each target routing node at the current moment, the resource occupancy rate of links between each server node and each target routing node at the previous moment and the weight of links between each server node and each target routing node at the previous moment, wherein the target routing node is a routing node which is directly connected with each server node in the plurality of routing nodes; wherein one server node corresponds to one target routing node;

the method comprises the following steps of: determining the corresponding resource load scene type of the link between the server node and the corresponding target routing node at the current moment according to the resource occupancy rate and the threshold value of the link between the server node and the corresponding target routing node at the current moment;

determining the weight of the links between each server node and each target routing node at the current moment according to the resource load scene type, the resource occupancy rate of the links between each server node and each target routing node at the current moment, the resource occupancy rate of the links between each server node and each target routing node at the previous moment, the weight of the links between each server node and each target routing node at the previous moment and the threshold value;

And the weight of the links between each server node and each target routing node at the current moment is used for determining the shortest path of the computing power network.

2. The method of claim 1, wherein the threshold value comprises a first threshold value and a second threshold value, the first threshold value being less than the second threshold value; the determining the resource load scene type corresponding to the link between the server node and the corresponding target routing node at the current moment according to the resource occupancy rate and the threshold value of the link between the server node and the corresponding target routing node at the current moment comprises the following steps:

if the resource occupancy rate of the link between the server and the corresponding target route is smaller than a first threshold value, determining that the resource load scene type corresponding to the link between the server node and the corresponding target route node at the current moment is a resource light load;

if the resource occupancy rate of the link between the server node and the corresponding target route is larger than or equal to a first threshold value and smaller than a second threshold value, determining that the resource load scene type corresponding to the link between the server node and the corresponding target route node at the current moment is the resource medium load;

And if the resource occupancy rate of the link between the server node and the corresponding target route is greater than or equal to a second threshold value and less than 1, determining that the resource load scene type corresponding to the link between the server node and the corresponding target route node at the current moment is resource reload.

3. The method according to claim 2, wherein determining the weight of the links between each server node and each target routing node at the current time according to the resource load scenario type, the resource occupancy of the links between each server node and each target routing node at the current time, the resource occupancy of the links between each server node and each target routing node at the previous time, the weight of the links between each server node and each target routing node at the previous time, and the threshold value comprises:

determining a weight calculation model according to the resource load scene type, the resource occupancy rate of a link between the server node and a corresponding target routing node at the current moment, the resource occupancy rate of a link between the server node and a corresponding target routing node at the previous moment and a threshold value for each server;

And obtaining the weight of the links between each server node and each target routing node at the current moment through the weight calculation model according to the resource occupancy rate of the links between the server node and the corresponding target routing nodes at the current moment, the resource occupancy rate of the links between the server node and the corresponding target routing nodes at the previous moment and the weight of the links between each server node and each target routing node at the previous moment.

4. A method according to claim 3, wherein said determining a weight calculation model according to the resource load scenario type, the resource occupancy of the link between the server node and the corresponding target routing node at the current time, the resource occupancy of the link between the server node and the corresponding target routing node at the previous time, and the threshold value comprises:

according to the resource load scene type, the weight calculation model and the multiple of the weight coefficient used for calculating the link between the server node and the corresponding target routing node at the current moment are determined by comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the current moment with the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment and comparing the resource occupancy rate of the link between the server node and the corresponding target routing node at the previous moment with a threshold value.

5. The method according to any one of claims 1-4, further comprising:

and updating the weight of the link between the server node and the corresponding target routing node at the current moment into the network topology structure of the computing power network system.

6. The method according to any one of claims 1-4, further comprising:

acquiring the weight of a link between two routing nodes on the same link in the plurality of routing nodes;

and determining the shortest path of the computing power network according to the weight of the links between the two routing nodes on the same link and the weight of the links between the server nodes and the corresponding target routers.

7. A computing power network path analysis apparatus for use in a computing power network system comprising a plurality of server nodes and a plurality of routing nodes, the apparatus comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring the resource occupancy rate of links between each server node and each target routing node at the current moment, the resource occupancy rate of links between each server node and each target routing node at the last moment and the weight of links between each server node and each target routing node at the last moment, and the target routing node is a routing node which is directly connected with each server node in the plurality of routing nodes; wherein one server node corresponds to one target routing node;

The determining module is used for executing the following steps aiming at the resource occupancy rate of links between each server node and each target routing node at the current moment: determining the corresponding resource load scene type of the link between the server node and the corresponding target routing node at the current moment according to the resource occupancy rate and the threshold value of the link between the server node and the corresponding target routing node at the current moment;

the path analysis module is used for determining the weight of the links between each server node and each target routing node at the current moment according to the resource load scene type, the resource occupancy rate of the links between each server node and each target routing node at the current moment, the resource occupancy rate of the links between each server node and each target routing node at the previous moment, the weight and the threshold value of the links between each server node and each target routing node at the previous moment;

and the weight of the links between each server node and each target routing node at the current moment is used for determining the shortest path of the computing power network.

8. An electronic device, comprising: at least one processor and memory;

The memory stores computer-executable instructions;

the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the method of computational power network path analysis of any one of claims 1-6.

9. A computing power network system, comprising: the electronic device, as set forth in claim 8, a plurality of server nodes, and a plurality of routing nodes.

10. A computer readable storage medium having stored therein computer executable instructions which, when executed by a processor, implement the method of computational power network path analysis of any one of claims 1-6.