CN113655764A - Cloud edge cooperative control system and control method - Google Patents
Cloud edge cooperative control system and control method Download PDFInfo
- Publication number
- CN113655764A CN113655764A CN202110938618.2A CN202110938618A CN113655764A CN 113655764 A CN113655764 A CN 113655764A CN 202110938618 A CN202110938618 A CN 202110938618A CN 113655764 A CN113655764 A CN 113655764A
- Authority
- CN
- China
- Prior art keywords
- data
- layer
- control
- edge
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000013598 vector Substances 0.000 claims abstract description 87
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims description 26
- 230000005540 biological transmission Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 45
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4185—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the network communication
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/33—Director till display
- G05B2219/33273—DCS distributed, decentralised controlsystem, multiprocessor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a cloud-edge cooperative control system and a control method. Wherein cloud limit cooperative control system includes: the edge control layer is connected with the terminal equipment layer, controls equipment of the terminal equipment layer, acquires data of the terminal equipment layer, processes the data into a data characteristic vector by combining the data of the edge control layer and transmits the data characteristic vector to the central cloud layer; and the central cloud layer analyzes the data characteristic vector to obtain a control relation, an equipment relation and point location data of the equipment between the edge control layer and the terminal equipment layer, monitors the point location data of the equipment based on a preset algorithm, and generates a new data characteristic vector based on the control relation and the equipment relation and transmits the new data characteristic vector to the edge control layer when the deviation rate of the point location data of the equipment is greater than a threshold value, so that the dynamic update of the control logic of the terminal equipment layer is realized. The invention realizes the dynamic update of the control logic of the equipment, so that the control scene corresponding to the equipment can realize automatic control and deviation correction.
Description
Technical Field
The invention relates to an intelligent control technology, in particular to a cloud-side cooperative control system and a control method.
Background
In recent years, with the development of science and technology and the gradual soundness of building control technology, people have higher and higher requirements on building control, in the integration process of the existing building field device system, the control logics needed to be adopted under different scenes often have differences, and the scene change needs to be manually replaced and configured every time, so that the workload is large, and the maintenance cost is increased.
The prior art with application number 202010449276.3 provides a distributed control method for a network controller, which realizes the point location data acquisition and control mechanism and configuration logic of each subsystem by the controller, but increases the maintenance cost by means of configuration issuing logic, and is only the control logic of a single scene. In addition, the configuration logic in the prior art is a fixed logic which needs to be written by a technician, and once the configuration logic needs to be adjusted, the technician needs to write the corresponding logic again, so that the configuration logic is very inconvenient to use.
Therefore, it is an urgent technical problem in the art to provide a control system capable of dynamically updating the control logic of the device.
Disclosure of Invention
The invention provides a cloud-edge cooperative control system and a control method, aiming at solving the technical problems that control logic is relatively fixed and cannot be automatically updated in the prior art.
The invention provides a cloud edge cooperative control system, which comprises:
the edge control layer is connected with the terminal equipment layer, controls equipment of the terminal equipment layer, acquires data of the terminal equipment layer, processes the data into a data characteristic vector by combining the data of the edge control layer and transmits the data characteristic vector to the central cloud layer;
and the central cloud layer analyzes the data characteristic vector to obtain a control relation, an equipment relation and point location data of the equipment between the edge control layer and the terminal equipment layer, monitors the point location data of the equipment based on a preset algorithm, and generates a new data characteristic vector based on the control relation and the equipment relation and transmits the new data characteristic vector to the edge control layer when the deviation rate of the point location data of the equipment is greater than a threshold value, so that the dynamic update of the control logic of the terminal equipment layer is realized.
Further, the terminal device layer includes at least one group of devices, and each group of devices constitutes a control scene.
Further, the edge control layer includes edge controllers arranged in one-to-one correspondence with the respective groups of devices.
Further, the edge controller includes:
the first transmission module is in remote communication with the central cloud layer;
the shallow learning network module reconstructs data of a corresponding group of equipment and data of the edge controller into data characteristic vectors according to a communication protocol, transmits the data characteristic vectors to the central cloud layer through the first transmission module, receives new data characteristic vectors sent by the central cloud layer and analyzes new control logic from the new data characteristic vectors;
and the logic module immediately adopts the latest control logic to control the corresponding group of equipment.
Further, an initial control logic is preset in the logic module, and before the control logic analyzed by the shallow learning network module is not received, the initial control logic is adopted to control a group of corresponding devices.
Further, the shallow learning network module comprises:
the data reconstruction unit is used for realizing the mutual conversion of the data of the corresponding group of equipment and the data of the edge controller and the data characteristic vector according to the communication protocol;
the data conversion unit is used for converting the data of the equipment and/or the data of the edge controller obtained from the data characteristic vector acquired from the central cloud layer into a new logic language of the control logic;
and the logic control unit is used for installing the logic language obtained by the data conversion unit to a logic layer of the edge controller.
Further, the central cloud layer includes:
the second transmission module is communicated with the edge control layer;
the message analysis module is used for analyzing the data characteristic vector to obtain data of a terminal equipment layer and data of an edge control layer;
the relationship analysis module is used for analyzing the data of the terminal equipment layer and the data of the edge control layer to obtain the control relationship between the edge control layer and the terminal equipment layer, the equipment relationship and the point position data of the equipment;
the data processing module learns the point location data of the equipment of each control scene according to a preset learning algorithm to obtain change information of the point location data, judges whether the point location data deviate or not by adopting a preset difference analysis algorithm based on the change information, calculates to obtain new point location data if the deviation rate of the point location data is greater than a threshold value, and generates a new data feature vector based on the new point location data.
Further, the preset learning algorithm is a deep neural network learning algorithm.
Further, the preset difference analysis algorithm comprises a positive and negative balance method and a sample deviation analysis method.
Further, the change information of the point location data includes trend data of the point location data or amplitude data of the point location data.
Further, the data of the terminal device layer includes: information data of each device in the terminal device layer and point location data of each device; the information data of the device includes an ID capable of uniquely identifying the device and a corresponding message body, and the point location data of the device includes an ID capable of uniquely identifying the point location and a corresponding message body.
Further, the data of the edge control layer includes: information data of each edge controller in the edge control layer; the information data of the edge controller includes an ID that can uniquely identify the edge controller and a corresponding message body.
Further, the data feature vector includes an ID that can uniquely identify an edge controller corresponding to the data feature vector, an ID of a device corresponding to the data feature vector, an ID of a point location corresponding to the data feature vector, and a corresponding message body.
Further, the set of devices in the terminal device layer includes an execution device, or includes a detection device and an execution device.
The control method of the cloud-edge cooperative control system provided by the technical scheme of the invention comprises the following steps:
step 1, the edge control layer takes an initial control logic as a current control logic to control the terminal equipment layer;
step 2, the edge control layer acquires the data of the terminal equipment layer, processes the data into a data characteristic vector by combining the data of the edge control layer and transmits the data characteristic vector to the central cloud layer;
step 3, the central cloud layer analyzes the data characteristic vector to obtain the control relationship, the equipment relationship and the point position data of the edge control layer and the terminal equipment layer;
step 4, the central cloud layer monitors point location data of the equipment based on a preset algorithm, and when the deviation ratio of the point location data is larger than a threshold value, a new data feature vector is generated based on the control relation and the equipment relation and is transmitted to an edge control layer;
and 5, the edge control layer analyzes the data characteristic vector, acquires a new control logic from the data characteristic vector, takes the new control logic as the current control logic of the corresponding equipment and returns to the step 2.
Further, in step 3, the central cloud layer generates each virtual control scene model for copying the terminal device layer according to the control relationship, the device relationship, and the point location data, and learns the point location data of the control scene model based on a preset learning algorithm in step 4 to obtain change information of the point location data.
The invention adopts the cloud edge cooperative control system to control the equipment, realizes the dynamic update of the control logic of the equipment, and realizes the dynamic update of the scene control logic when the equipment is applied and controls the scene. Meanwhile, the control logic is not directly generated on the cloud platform, only the data is learned, the deviation rate is analyzed, if the deviation rate is higher than the threshold value, a new data feature vector is generated based on the new point location data, the edge control layer regenerates a corresponding logic language to realize the updating of the control logic, and the computing overhead and the intermediate data transmission of the cloud platform are reduced.
Drawings
The invention is described in detail below with reference to examples and figures, in which:
FIG. 1 is a system architecture diagram of the present invention.
FIG. 2 is a block diagram of the shallow learning network module of the present invention.
FIG. 3 is a processing architecture diagram of the center cloud layer of the present invention.
FIG. 4 is a data structure diagram of a data feature vector of the present invention.
Fig. 5 is a data upstream flow chart of the present invention.
Fig. 6 is a flow chart of the data thresholding at the cloud according to the present invention.
FIG. 7 is a flow chart of the data processing at the edge control layer according to the present invention.
FIG. 8 is a data downstream flow diagram of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Thus, a feature indicated in this specification will serve to explain one of the features of one embodiment of the invention, and does not imply that every embodiment of the invention must have the stated feature. Further, it should be noted that this specification describes many features. Although some features may be combined to show a possible system design, these features may also be used in other combinations not explicitly described. Thus, the combinations illustrated are not intended to be limiting unless otherwise specified.
The principles of the present invention will be described in detail below with reference to the accompanying drawings and embodiments.
The technical basis for realizing the method is a cloud-edge coordination technology, which needs coordination between the edge side and the central cloud to realize centralized control of the equipment, but if the number of the edge equipment is huge, the data information amount is increased rapidly, and the load of the cloud platform is caused by only directly controlling the equipment through the cloud platform, so that the use and the efficiency of the system are influenced. Therefore, the invention is correspondingly improved on the basis of cloud-side cooperative control, so that the load of the cloud platform is minimum, and the dynamic update of the control logic of the equipment can be realized.
As shown in fig. 1, the cloud edge coordination system proposed by the present invention includes an edge control layer and a central cloud layer.
The edge control layer is connected with the terminal equipment layer to obtain data of the terminal equipment layer, and the data is processed into a data characteristic vector by combining the data of the edge control layer and is transmitted to the central cloud layer.
The edge control layer is a collection of edge controllers, the number of which is based on the number of control scenarios, each of which has a corresponding set of devices. Namely, the terminal device layer comprises at least one group of devices, each group of devices forms a control scene, and each control scene is controlled by an edge controller. There are multiple control scenarios in fig. 1, and thus edge controllers with the same data.
The devices (i.e. referred to as a group of devices) in each control scenario may all be execution devices, or may be a combination of a detection device and an execution device, where the detection device refers to a sensor or other device with a detection function, and the execution device is a device that is to perform a corresponding action according to the control logic based on a detection result of the detection device. The devices within each control scenario cooperate to implement control logic within the control scenario.
The data of the terminal device layer refers to a set of data of the device, and the data of the edge control layer refers to a set of data of the edge controller. The edge controller processes the data of the equipment in the control scene corresponding to the receiver by combining the data of the edge controller, and obtains a data characteristic vector which is transmitted to the central cloud layer. The edge controller thus includes a first transmission module, a shallow learning network module, and a logic module.
The first transmission module is in remote communication with the central cloud layer.
The shallow learning network module reconstructs data of a group of corresponding equipment and data of the edge controller into a data characteristic vector according to a communication protocol, wherein the data of the equipment corresponds to information data of each equipment corresponding to the edge controller and point location data of each equipment. The information data of the device includes an ID that can uniquely identify the device and a corresponding message body, for example, the content of the message body includes, but is not limited to, the version and type of the device (e.g., 485 module, IO module, two-bus module, etc.). The point location data of a device includes an ID that uniquely identifies the point location and a corresponding message body. The data of the edge controller refers to information data of the edge controller, and the information data of the edge controller includes an ID that can uniquely identify the edge controller and a corresponding message body, for example, the content of the message body includes, but is not limited to, a program version, a running log, and a logic change record of the edge controller. The data characteristic vector formed by the shallow learning network module is transmitted to the central cloud layer through the first transmission module, and if a new data characteristic vector is sent from the side of the central cloud layer, the shallow learning network module also needs to analyze a new control logic from the new data characteristic vector.
When the shallow learning network module analyzes a new control logic, the logic module immediately adopts the latest control logic to control a group of corresponding equipment, thereby realizing the real-time update of the control logic of the equipment without manual modification and update or shutdown update, and having very convenient operation. The logic module may be preset with an initial control logic, and before the control logic analyzed by the shallow learning network module is not received, the initial control logic is adopted to control a corresponding group of devices.
As shown in fig. 2, the shallow learning network module can be further divided into three units, namely a data reconstruction unit, a data conversion unit and a logic control unit. And the data reconstruction unit reconstructs the data of the corresponding group of equipment and the data of the edge controller into a data characteristic vector according to the communication protocol. The data feature vectors obtained from the central cloud layer may also be converted into data for the device and data for the edge controllers. The logic control unit is used for converting the data of the equipment and/or the data of the edge controller obtained from the data characteristic vector obtained from the central cloud layer into a new logic language of the control logic, and the logic control unit is used for installing the logic language obtained by the data conversion unit into the logic layer of the edge controller.
As shown in fig. 3, the central cloud layer analyzes the data feature vector to obtain a control relationship between the edge control layer and the terminal device layer, a device relationship and point location data of the device, monitors the point location data of the device based on a preset algorithm, and generates a new data feature vector based on the control relationship and the device relationship and transmits the new data feature vector to the edge control layer when the deviation ratio of the point location data of the device is greater than a threshold value, so as to dynamically update the control logic of the terminal device layer. For example, a certain edge controller is connected with 64 expansion modules, each expansion module is connected with 1000 sensors, the sensors are detection devices, each expansion module is equivalent to one detection device, each detection device has 1000 point locations, namely 64 point locations are total, 1000 point locations are total, and corresponding point location data is the ID of the point location, the state (on or off) of the point location, and running data stored in the point location.
The central cloud layer analyzes the data feature vector based on the communication protocol in the protocol analysis pool, and obtains the information data of the edge controller, the information data of the device, and the point location data of the device shown in fig. 3. Then, the data in the central cloud layer obtains corresponding message bodies (namely, message bodies), and then the message bodies are subjected to message buffering, and if the current thread is not enough to process, the central cloud layer also performs resource scheduling through a scheduler so as to process the data reasonably as soon as possible. The central cloud layer can obtain the control relationship between the edge control layer and the terminal equipment layer, the equipment relationship and the point location data of the equipment based on the information data of the edge controller, the information data of the equipment and the message body in the point location data of the equipment, and can build corresponding virtual control scene models based on the control relationship between the edge control layer and the terminal equipment layer, the equipment relationship and the point location data of the equipment, the virtual control scene models are copies of the terminal equipment layer and the edge control layer, the number and the architecture of the controller models are the same as those of the edge controllers in the edge control layer, the number and the architecture of the equipment of the terminal equipment model and the terminal equipment layer are the same, and corresponding point location mapping is carried out, so that the equipment has a corresponding equipment point location model. Of course, the representation form of the model may not be adopted, and other forms may also be adopted to represent the control relationship between the edge control layer and the terminal device layer, the device relationship, and the point location data of the device.
In the central cloud layer, the running logs of each independent control scene can be inquired in real time through a visual interface according to personal authority, namely, all groups of equipment are independent. Meanwhile, the visual module can be accessed at the side end, and a corresponding control scene running log can be inquired after a specified password is input to obtain the inquiry authority, wherein the inquiry content comprises but is not limited to the following inquiry contents: basic information, a scene model, cloud control data (threshold values and the like), a difference deviation rate curve change diagram, a system scene update log and the like.
The central cloud layer may include four modules, which are a second transmission module, a message analysis module, a relationship analysis module, and a data processing module, respectively.
The second transmission module is communicated with the edge control layer and is a module which is directly and newly communicated with each first transmission module.
And the message analysis module analyzes the data characteristic vector to obtain data of a terminal equipment layer and data of an edge control layer.
The relationship analysis module analyzes the data of the terminal equipment layer and the data of the edge control layer to obtain the control relationship between the edge control layer and the terminal equipment layer, the equipment relationship and the point position data of the equipment;
the data processing module learns the point location data of the equipment of each control scene according to a preset learning algorithm to obtain change information of the point location data, judges whether the point location data deviate or not by adopting a preset difference analysis algorithm based on the change information, calculates to obtain new point location data if the deviation rate of the point location data is greater than a threshold value, and generates a new data feature vector based on the new point location data. The predetermined learning algorithm referred to herein includes, but is not limited to, a deep neural network learning algorithm. The preset difference analysis algorithm includes, but is not limited to, a positive and negative balance method and a sample deviation analysis method, and the sample deviation analysis method adopts an existing known deviation analysis method, and specifically, the deviation analysis method is selected according to the deviation direction to be analyzed.
When the point location data in the existing control scene is learned by adopting a deep neural network learning algorithm, normal change information of the point location data can be obtained, wherein the change information of the point location data comprises trend data of the point location data or amplitude data of the point location data, when the difference between the latest uploaded actual point location data and the previous point location data is compared with the change information obtained through the learning algorithm, if the deviation rate of the point location data is greater than a threshold value, the control logic of corresponding equipment needs to be adjusted correspondingly, so that a central cloud layer needs to generate a corresponding data feature vector according to the new point location data and then obtains a specific logic language from a corresponding edge controller to realize dynamic update of the control logic. The threshold referred to herein is not a uniform value, and each point of data has its corresponding threshold of deviation ratio.
As shown in fig. 4, the edge controller needs to reconstruct the information data of the edge controller, the information data of the device, and the point location data of the device into a data feature vector, and if new point location data is obtained by the central cloud layer, a new data feature vector needs to be generated. The shallow learning network module reconstructs the information data of the edge controller, the information data of the equipment and the point location data of the equipment into a form of controller ID, equipment ID, point location ID and a corresponding message body, and then sends the information data, the equipment ID, the point location ID and the corresponding message body to the central cloud layer. The central cloud layer also wants the same structure when generating a new data feature vector, so that the corresponding edge controller, the corresponding device and the corresponding point location can be updated correspondingly.
As shown in fig. 5 to 8, the control method of the cloud-edge cooperative control system provided by the present invention mainly includes the following steps:
step 1, the edge control layer takes the initial control logic as the current control logic to control the terminal equipment layer;
step 2, the edge control layer acquires data of the terminal equipment layer, processes the data into a data characteristic vector by combining the data of the edge control layer and transmits the data characteristic vector to the central cloud layer;
step 3, the central cloud layer analyzes the data characteristic vector to obtain a control relation, an equipment relation and point position data of the edge control layer and the terminal equipment layer;
step 4, the central cloud layer monitors the point location data of the equipment based on a preset algorithm, and when the deviation ratio of the point location data is larger than a threshold value, a new data feature vector is generated based on the control relation and the equipment relation and is transmitted to the edge control layer;
and 5, the edge control layer analyzes the data characteristic vector, acquires a new control logic from the data characteristic vector, takes the new control logic as the current control logic of the corresponding equipment and returns to the step 2.
In the step 3, the central cloud layer generates each virtual control scene model for copying the terminal equipment layer according to the control relationship, the equipment relationship and the point location data, and learns the point location data of the control scene model based on a preset learning algorithm in the step 4 to obtain the change information of the point location data.
As shown in fig. 5, when data is transmitted in an uplink manner, the edge controller acquires point location data of the device, and transmits the information data of the edge controller, the information data of the device, and the point location data of the device to the shallow learning network module, the shallow learning network module reconstructs the acquired data into data feature vectors, and then transmits the data feature vectors to the first transmission module, and the first transmission module uploads the data to the central cloud layer for analysis processing.
As shown in fig. 6, after receiving data, the central cloud layer performs parsing, and then generates virtual control scene modules based on the parsing result, where the control scene models have the same structure as the terminal device layer and the edge control layer, and the point locations are also in a one-to-one mapping relationship. And if the deviation rate of the point location data of the central cloud computing equipment is greater than the corresponding threshold value, generating a new data feature vector.
As shown in fig. 7, the central cloud layer receives the data feature vector, generates a virtual control scene module, performs point location mapping, and performs difference comparison analysis by a positive and negative balance method and a sample deviation analysis method, so as to generate a deviation rate of a corresponding point location, and if the deviation rate is higher than a threshold, generates a latest data feature vector according to a current control scene model, and transmits the data feature vector to the edge control layer through the second transmission module for analysis processing.
As shown in fig. 8, during data downlink transmission, the shallow learning network module analyzes the data feature vector transmitted by the central cloud layer to obtain corresponding data, that is, data with a message body, then changes the data with the message body into a logic voice capable of implementing control logic, and installs the logic voice to the logic module of the edge controller by using the logic control unit, thereby implementing a new control scenario.
The data of the terminal equipment layer and the data of the edge control layer are periodically processed from edge to cloud, the central cloud layer stores and learns all the uplink data, if the deviation rate of the point location data is lower than a threshold value, the central cloud layer only stores and is used for subsequent analysis, the latest data feature vector is not generated to send the data, and the current scene control logic is not updated. Example (c): the cloud end sets a threshold value to be 10%, the current scene control logic cannot be updated if the deviation rate obtained in certain calculation is 5%, the latest scene control logic is generated if the deviation rate obtained in certain calculation is 15%, the latest scene control logic is transmitted to the edge control layer in a data characteristic vector mode, the edge control layer converts the corresponding message body into a logic language, and the logic language is installed in a logic module of the edge controller.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (16)
1. A cloud-edge cooperative control system, comprising:
the edge control layer is connected with the terminal equipment layer, controls equipment of the terminal equipment layer, acquires data of the terminal equipment layer, processes the data into a data characteristic vector by combining the data of the edge control layer and transmits the data characteristic vector to the central cloud layer;
and the central cloud layer analyzes the data characteristic vector to obtain a control relation, an equipment relation and point location data of the equipment between the edge control layer and the terminal equipment layer, monitors the point location data of the equipment based on a preset algorithm, and generates a new data characteristic vector based on the control relation and the equipment relation and transmits the new data characteristic vector to the edge control layer when the deviation rate of the point location data of the equipment is greater than a threshold value, so that the dynamic update of the control logic of the terminal equipment layer is realized.
2. The cloud-edge cooperative control system according to claim 1, wherein the terminal device layer includes at least one group of devices, and each group of devices constitutes one control scenario.
3. The cloud-edge cooperative control system according to claim 2, wherein the edge control layer includes edge controllers provided in one-to-one correspondence with the respective groups of devices.
4. The cloud-edge cooperative control system according to claim 3, wherein the edge controller comprises:
the first transmission module is in remote communication with the central cloud layer;
the shallow learning network module reconstructs data of a corresponding group of equipment and data of the edge controller into data characteristic vectors according to a communication protocol, transmits the data characteristic vectors to the central cloud layer through the first transmission module, receives new data characteristic vectors sent by the central cloud layer and analyzes new control logic from the new data characteristic vectors;
and the logic module immediately adopts the latest control logic to control the corresponding group of equipment.
5. The cloud-edge cooperative control system according to claim 4, wherein an initial control logic is preset in the logic module, and before the control logic analyzed by the shallow learning network module is not received, the initial control logic is adopted to control a corresponding set of devices.
6. The cloud-edge collaborative control system of claim 4, wherein the shallow learning network module comprises:
the data reconstruction unit is used for realizing the mutual conversion of the data of the corresponding group of equipment and the data of the edge controller and the data characteristic vector according to the communication protocol;
the data conversion unit is used for converting the data of the equipment and/or the data of the edge controller obtained from the data characteristic vector acquired from the central cloud layer into a new logic language of the control logic;
and the logic control unit is used for installing the logic language obtained by the data conversion unit to a logic layer of the edge controller.
7. The cloud-edge cooperative control system according to claim 2, wherein the central cloud layer comprises:
the second transmission module is communicated with the edge control layer;
the message analysis module is used for analyzing the data characteristic vector to obtain data of a terminal equipment layer and data of an edge control layer;
the relationship analysis module is used for analyzing the data of the terminal equipment layer and the data of the edge control layer to obtain the control relationship between the edge control layer and the terminal equipment layer, the equipment relationship and the point position data of the equipment;
the data processing module learns the point location data of the equipment of each control scene according to a preset learning algorithm to obtain change information of the point location data, judges whether the point location data deviate or not by adopting a preset difference analysis algorithm based on the change information, calculates to obtain new point location data if the deviation rate of the point location data is greater than a threshold value, and generates a new data feature vector based on the new point location data.
8. The cloud-edge cooperative control system according to claim 7, wherein the preset learning algorithm is a deep neural network learning algorithm.
9. The cloud-edge cooperative control system according to claim 7, wherein the preset variance analysis algorithm comprises a positive and negative balance method and a sample deviation analysis method.
10. The cloud-edge cooperative control system according to claim 7, wherein the change information of the point location data includes trend data of the point location data or magnitude data of the point location data.
11. The cloud-edge cooperative control system according to claim 1, wherein the data of the terminal device layer includes: information data of each device in the terminal device layer and point location data of each device; the information data of the device includes an ID capable of uniquely identifying the device and a corresponding message body, and the point location data of the device includes an ID capable of uniquely identifying the point location and a corresponding message body.
12. The cloud-edge cooperative control system according to claim 11, wherein the data of the edge control layer includes: information data of each edge controller in the edge control layer; the information data of the edge controller includes an ID that can uniquely identify the edge controller and a corresponding message body.
13. The cloud-edge cooperative control system according to claim 12, wherein the data feature vector includes an ID uniquely identifying an edge controller corresponding to the data feature vector, an ID of a device corresponding to the data feature vector, an ID of a point corresponding to the data feature vector, and a corresponding message body.
14. The cloud-edge cooperative control system according to claim 2, wherein a group of devices of the terminal device layer includes an execution device, or includes a detection device and an execution device.
15. A control method of the cloud-edge cooperative control system according to any one of claims 1 to 14, comprising:
step 1, the edge control layer takes an initial control logic as a current control logic to control the terminal equipment layer;
step 2, the edge control layer acquires the data of the terminal equipment layer, processes the data into a data characteristic vector by combining the data of the edge control layer and transmits the data characteristic vector to the central cloud layer;
step 3, the central cloud layer analyzes the data characteristic vector to obtain the control relationship, the equipment relationship and the point position data of the edge control layer and the terminal equipment layer;
step 4, the central cloud layer monitors point location data of the equipment based on a preset algorithm, and when the deviation ratio of the point location data is larger than a threshold value, a new data feature vector is generated based on the control relation and the equipment relation and is transmitted to an edge control layer;
and 5, the edge control layer analyzes the data characteristic vector, acquires a new control logic from the data characteristic vector, takes the new control logic as the current control logic of the corresponding equipment and returns to the step 2.
16. The method for controlling the cloud-edge cooperative control system according to claim 15, wherein in the step 3, the central cloud layer generates each virtual control scene model for copying the terminal device layer according to the control relationship, the device relationship, and the point location data, and learns the point location data of the control scene model based on a preset learning algorithm in the step 4 to obtain change information of the point location data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938618.2A CN113655764A (en) | 2021-08-16 | 2021-08-16 | Cloud edge cooperative control system and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110938618.2A CN113655764A (en) | 2021-08-16 | 2021-08-16 | Cloud edge cooperative control system and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113655764A true CN113655764A (en) | 2021-11-16 |
Family
ID=78491171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110938618.2A Pending CN113655764A (en) | 2021-08-16 | 2021-08-16 | Cloud edge cooperative control system and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113655764A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115842823A (en) * | 2023-02-20 | 2023-03-24 | 广州机智云物联网科技有限公司 | Cloud edge cooperative management method based on cloud originality |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110343541A (en) * | 2019-06-18 | 2019-10-18 | 广东石油化工学院 | A kind of cracking furnace pipe intelligence coking monitoring side cloud collaborative platform and its working method |
| CN111421554A (en) * | 2020-05-22 | 2020-07-17 | 中国科学院自动化研究所 | Robotic arm intelligent control system, method and device based on edge computing |
| CN111464627A (en) * | 2020-03-31 | 2020-07-28 | 中国科学院自动化研究所 | Data processing method, edge server, central server and processing system |
| US20200241482A1 (en) * | 2019-01-28 | 2020-07-30 | Johnson Controls Technology Company | Building management system with hybrid edge-cloud processing |
| CN111596629A (en) * | 2020-06-02 | 2020-08-28 | 曲阜师范大学 | A cloud-side collaborative industrial data fusion method and security controller |
| CN112217860A (en) * | 2020-09-01 | 2021-01-12 | 武汉魅客科技有限公司 | Intelligent energy management system based on edge computing technology |
| CN112286691A (en) * | 2020-11-12 | 2021-01-29 | 济南浪潮高新科技投资发展有限公司 | Cloud edge-side cooperation method based on heterogeneous decision model generation technology |
-
2021
- 2021-08-16 CN CN202110938618.2A patent/CN113655764A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200241482A1 (en) * | 2019-01-28 | 2020-07-30 | Johnson Controls Technology Company | Building management system with hybrid edge-cloud processing |
| CN110343541A (en) * | 2019-06-18 | 2019-10-18 | 广东石油化工学院 | A kind of cracking furnace pipe intelligence coking monitoring side cloud collaborative platform and its working method |
| CN111464627A (en) * | 2020-03-31 | 2020-07-28 | 中国科学院自动化研究所 | Data processing method, edge server, central server and processing system |
| CN111421554A (en) * | 2020-05-22 | 2020-07-17 | 中国科学院自动化研究所 | Robotic arm intelligent control system, method and device based on edge computing |
| CN111596629A (en) * | 2020-06-02 | 2020-08-28 | 曲阜师范大学 | A cloud-side collaborative industrial data fusion method and security controller |
| CN112217860A (en) * | 2020-09-01 | 2021-01-12 | 武汉魅客科技有限公司 | Intelligent energy management system based on edge computing technology |
| CN112286691A (en) * | 2020-11-12 | 2021-01-29 | 济南浪潮高新科技投资发展有限公司 | Cloud edge-side cooperation method based on heterogeneous decision model generation technology |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115842823A (en) * | 2023-02-20 | 2023-03-24 | 广州机智云物联网科技有限公司 | Cloud edge cooperative management method based on cloud originality |
| CN115842823B (en) * | 2023-02-20 | 2023-04-28 | 广州机智云物联网科技有限公司 | Cloud edge collaborative management method based on cloud primordia |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110430219B (en) | Method and system for self-adapting of multi-protocol Internet of things equipment | |
| CN113176948B (en) | Edge gateway, edge computing system and configuration method thereof | |
| CN110780914A (en) | Service publishing method and device | |
| JP2019513246A (en) | Training method of random forest model, electronic device and storage medium | |
| CN102523103B (en) | Industrial monitoring network data collection node | |
| CN105610944A (en) | IOT-oriented fog computing architecture | |
| CN108306804A (en) | A kind of Ethercat main station controllers and its communication means and system | |
| WO2016165242A1 (en) | Method of adjusting number of nodes in system and device utilizing same | |
| CN113031452B (en) | Method and system for batch processing of intelligent household equipment control instructions | |
| CN113179190A (en) | Edge controller, edge computing system and configuration method thereof | |
| CN113655764A (en) | Cloud edge cooperative control system and control method | |
| CN110703616A (en) | Intelligent interaction method, cloud server, intelligent interaction system and storage medium | |
| CN111324460B (en) | Power monitoring control system and method based on cloud computing platform | |
| CN111104289B (en) | System and method for checking efficiency of GPU (graphics processing Unit) cluster | |
| CN110740169B (en) | Data communication system and method for Matlab power simulation model and Internet of things equipment | |
| CN110925936A (en) | Air conditioner control method and device, computer equipment and storage medium | |
| CN112214303A (en) | Kubernetes cluster autoscaling system | |
| CN112327655A (en) | Intelligent household system based on resource sharing technology | |
| CN110611599A (en) | Network control system and control method thereof | |
| CN115145549A (en) | Video or image AI analysis equipment and system based on edge gateway equipment | |
| WO2023050930A1 (en) | Auxiliary control method and system for wind turbine generator set, and wind turbine generator set | |
| CN111143050B (en) | Method and equipment for dispatching container clusters | |
| CN110266818B (en) | Management method based on Internet of things terminal group | |
| CN203191786U (en) | Multi-sensor dynamic data fusion control system | |
| KR102121030B1 (en) | Ubiquitous sensor network simulation system based on distributed parallel computing and simulation method using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211116 |