Control method, device, computer equipment and storage medium

Abstract

The embodiment of the present application discloses a control method, device, computer equipment and storage medium, which belongs to the field of computer technology. The method includes: determining multiple Markov states of the edge device energy supply system; based on the target operating parameters and target changes of each edge node in each Markov state in the edge device energy supply system, respectively determining the relationship data corresponding to each edge node in each Markov state; based on the determined multiple relationship data, determining the control parameters referred to by the control identifier corresponding to each edge node in multiple Markov states, and sending the corresponding control parameter set to each edge node respectively, the control parameter set includes the control parameters of the edge node in multiple Markov states, so that the edge node controls the operation of the edge node in different Markov states based on the control parameters. This control method ensures the stability of the AC bus frequency in the edge node.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a control method, apparatus, computer equipment and storage medium. Background Art

[0002] The edge device energy supply system includes multiple edge nodes, each of which includes an energy router system, an AC bus, and an edge computing device. The energy router system is used to generate and store electrical energy, and to power the edge computing device through the AC bus to ensure the operation of the edge computing device. Figure 1 , Figure 1 Taking the edge device energy supply system including 6 edge nodes as an example, any edge node includes photovoltaic power generation equipment, traditional power generation equipment, energy storage equipment, edge computing equipment and ordinary loads, where ordinary loads refer to air conditioners, lights or other power-consuming equipment other than edge computing devices.

[0003] However, due to the imbalance between the electric energy generated or stored by the energy router system and the electric energy consumed by the edge computing device, the AC bus frequency in the edge node is unstable, which affects the operation of the edge device energy supply system. Therefore, how to control the stability of the AC bus frequency in the edge node and thus control the normal operation of the edge device energy supply system is an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide a control method, device, computer equipment and storage medium, which control edge nodes based on the acquired control parameters, thereby ensuring the stability of the AC bus frequency in the edge nodes and the normal operation of the edge device energy supply system. The technical solution is as follows:

[0005] In one aspect, a control method is provided, the method comprising:

[0006] Determine multiple Markov states of the edge device energy supply system;

[0007] Based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system, the relationship data corresponding to each edge node in each Markov state is determined respectively, the target operating parameters indicate the operating state of the edge node, the target variation includes the variation of the amount of tasks performed by the edge node, the relationship data corresponding to the edge node indicates the influence of the target variation and the control identifier on the variation of the target variation when the target operating parameters remain unchanged, and the control parameter referred to by the control identifier is a parameter used to control the edge node;

[0008] Based on the relationship data corresponding to the multiple edge nodes in the edge device energy supply system under the multiple Markov states, determine the control parameters referred to by the control identifier corresponding to each edge node under the multiple Markov states, and determine the control parameters corresponding to the same edge node under the multiple Markov states as the control parameter set corresponding to the same edge node;

[0009] A corresponding control parameter set is sent to each edge node respectively, so that the edge node controls the operation of the edge node in different Markov states based on the received control parameter set.

[0010] On the other hand, a control method is provided, the method being executed by an edge computing device in a target edge node, the target edge node being any edge computing node in an edge device energy supply system, the method comprising:

[0011] Acquire a control parameter set corresponding to the target edge node, wherein the control parameter set includes control parameters corresponding to the target edge node in different Markov states;

[0012] Based on the current operating parameters of the target edge node and multiple Markov states of the edge device energy supply system, determine the current Markov state corresponding to the current operating parameters from the multiple Markov states;

[0013] The target edge node is controlled based on the control parameters in the current Markov state.

[0014] In another aspect, a control device is provided, the device comprising:

[0015] A state determination module, used to determine multiple Markov states of the edge device energy supply system;

[0016] A relationship data determination module, for determining the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system, wherein the target operating parameters indicate the operating state of the edge node, the target variation includes the variation of the amount of tasks performed by the edge node, and the relationship data corresponding to the edge node indicates the influence of the target variation and the control identifier on the variation of the target variation when the target operating parameters remain unchanged, and the control parameter referred to by the control identifier is a parameter for controlling the edge node;

[0017] A control parameter determination module, configured to determine, based on the relationship data corresponding to the plurality of edge nodes in the edge device energy supply system under the plurality of Markov states, the control parameters referred to by the control identifier corresponding to each edge node under the plurality of Markov states, and determine the control parameters corresponding to the same edge node under the plurality of Markov states as a control parameter set corresponding to the same edge node;

[0018] The control parameter sending module is used to send a corresponding control parameter set to each edge node respectively, so that the edge node controls the operation of the edge node in different Markov states based on the received control parameter set.

[0019] In a possible implementation, the target variation is a first variation, the first variation refers to a variation of a first task amount executed in the edge node, the first task amount changes with a change in a control parameter, the target operating parameter includes a first time constant and a control coefficient, the first time constant indicates a response speed of the edge node to each first task, and the control coefficient indicates an influence of the control parameter on the first task amount;

[0020] The relationship data determination module includes:

[0021] A first relationship data determination unit is used to determine, for each edge node, first relationship data corresponding to the edge node in each Markov state based on the first time constant, the first change amount and the control coefficient of the edge node in each Markov state, wherein the first relationship data in each Markov state indicates the influence of the first change amount, the control coefficient and the control identifier on the change of the first change amount when the first time constant remains unchanged.

[0022] In another possible implementation, the target change amount is a second change amount, the second change amount refers to a change amount of a second task amount performed by the edge node, the second task amount changes with a change in an interference parameter, the target operating parameter includes a second time constant and an interference parameter, the second time constant indicates a response speed of the edge node to each second task, and the interference parameter indicates an influence of the interference parameter on the second task amount;

[0023] The relationship data determination module further includes:

[0024] A second relationship data determination unit is used to determine, for each edge node, the second relationship data corresponding to the edge node in each Markov state based on the second time constant, the second change amount and the interference parameter corresponding to the edge node in each Markov state, wherein the second relationship data indicates the influence of the second change amount and the interference parameter on the change of the second change amount when the second time constant remains unchanged.

[0025] In another possible implementation manner, the first relationship data determining unit is configured to:

[0026] The first change is a scheduling task change, which refers to a change in the amount of computing tasks or electric energy scheduled between the edge node and other edge nodes in the edge device energy supply system. Based on the first time constant, the scheduling task change, the control coefficient and the delay time of the edge node in each Markov state, the scheduling relationship data corresponding to the edge node in each Markov state are determined respectively, and the delay time refers to the time spent in scheduling the computing task or the electric energy; or

[0027] The first change is a first power change, which refers to a change in the power generation power of the traditional power generation equipment in the edge node. Based on the first time constant, the first power change and the control coefficient of the edge node in each Markov state, the first power relationship data corresponding to the edge node in each Markov state is determined respectively.

[0028] In another possible implementation manner, the second relationship data determining unit is configured to:

[0029] The second change is a load change, which refers to a change in the amount of computing tasks of the edge computing device in the edge node, and the load relationship data corresponding to the edge node in each Markov state is determined based on the second time constant, load change and interference parameter of the edge node in each Markov state; or

[0030] The second change is a second power change, which refers to the change in the power generation power of the renewable energy power generation equipment in the edge node. Based on the second time constant, the second power change and the interference parameter of the edge node in each Markov state, the second power relationship data corresponding to the edge node in each Markov state is determined respectively.

[0031] In another possible implementation, the target change amount is a third change amount, the third change amount is the change amount of the electric energy stored in the energy storage device in the edge node, the target operating parameter includes a third time constant and a first damping coefficient, the third time constant indicates the response speed of the edge node to the stored electric energy, and the relationship data determination module further includes:

[0032] A third relationship data determination unit is used to determine, for each edge node, the energy storage relationship data corresponding to the edge node in each Markov state based on the third time constant, the third change, the first damping coefficient and the AC bus frequency deviation of the edge node in each Markov state, wherein the energy storage relationship change represents the influence of the third change, the first damping coefficient and the AC bus frequency deviation on the change of the third change when the third time constant remains unchanged, and the AC bus frequency deviation indicates the value of the AC bus frequency in the edge node at at least one moment.

[0033] In another possible implementation, the target operating parameter further includes an inertia constant and a second damping coefficient, and the device further includes:

[0034] A balance relationship determination module, for each Markov state, based on the target change amount under the Markov state, the unit energy consumption of each computing task and the scheduling direction of each scheduling task, determines the power balance relationship in the edge node, wherein the power balance relationship represents the difference between the power consumed and the power generated in the edge node, the unit energy consumption represents the power consumed by the edge node to process a computing task, and the scheduling direction represents the direction of scheduling computing tasks or scheduling power between the edge node and other edge nodes in the edge device energy supply system;

[0035] A frequency deviation determination module, configured to determine frequency deviation relationship data corresponding to the edge node based on the power balance relationship, the inertia constant, the second damping coefficient and the AC bus frequency deviation in the edge node under the Markov state, wherein the frequency deviation relationship data indicates the influence of the power balance relationship, the inertia constant and the second damping coefficient on the change of the AC bus frequency deviation;

[0036] The control parameter determination module is used to determine the control parameters indicated by the control identifier corresponding to each edge node in the multiple Markov states based on the first relationship data, the second relationship data and the third relationship data corresponding to the multiple edge nodes in the edge device energy supply system under the multiple Markov states, so that the AC bus frequency deviation in the edge node indicated by the frequency deviation relationship data corresponding to each edge node is less than a preset threshold.

[0037] In another possible implementation, the control parameter determination module is used to:

[0038] Transforming the relationship data corresponding to the plurality of edge nodes under the plurality of Markov states to obtain fourth relationship data corresponding to the plurality of edge nodes under the plurality of Markov states, the fourth relationship data representing the relationship between the control identifier and the target operating parameter and the target variation;

[0039] Based on the target operating parameter corresponding to each edge node, the target change amount and the fourth relationship data, the control parameter indicated by the control identifier corresponding to each edge node under the multiple Markov states is determined.

[0040] In another possible implementation, the control parameter determination module is used to:

[0041] Using a Lyapunov functional method, the first relationship data, the second relationship data, and the third relationship data corresponding to the plurality of edge nodes under the plurality of Markov states are deformed to obtain linear matrix inequalities corresponding to the plurality of edge nodes under the plurality of Markov states, wherein the linear matrix inequality represents a satisfied relationship between the target operating parameter and the control identifier when the AC bus frequency in the plurality of edge nodes is stable;

[0042] The linear inequality is solved by using a particle swarm optimization algorithm to obtain control parameters indicated by control identifiers corresponding to each edge node under the multiple Markov states.

[0043] On the other hand, a control device is provided, which is applied to an edge computing device in a target edge node for execution, wherein the target edge node is any edge computing node in an edge device energy supply system, and the device includes:

[0044] A control parameter acquisition module, used to acquire a control parameter set corresponding to the target edge node, wherein the control parameter set includes control parameters corresponding to the target edge node under different Markov states;

[0045] A state determination module, configured to determine, based on the current operating parameters of the target edge node and the multiple Markov states of the edge device energy supply system, a current Markov state corresponding to the current operating parameters from the multiple Markov states;

[0046] A control module is used to control the target edge node based on the control parameters in the current Markov state.

[0047] In a possible implementation, the device further includes:

[0048] A state switching module, configured to determine a Markov state at a next moment based on a mode switching rate between the current Markov state and other Markov states among the multiple Markov states;

[0049] The control module is further configured to control the target edge node at the next moment based on the control parameter in the Markov state at the next moment.

[0050] On the other hand, a computer device is provided, comprising a processor and a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the control method described in the above aspects.

[0051] On the other hand, an edge computing device is provided, which includes a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the control method described in the above aspects.

[0052] On the other hand, a computer-readable storage medium is provided, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement the operations performed by the control method described in the above aspects.

[0053] On the other hand, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the operations performed by the control method described in the above aspects are implemented.

[0054] The technical solution provided by the embodiment of the present application, for each edge node in the edge device energy supply system, based on the target operating parameters and target change of each edge node in each Markov state, respectively obtains the relationship data corresponding to each edge node in each Markov state, the relationship data can simulate the change of the target change amount in the edge node under different Markov states, and determines the control parameters of each edge node in each Markov state based on the relationship data, so that the edge node can control the operation of the edge node based on the control parameters, and because the control parameters are control parameters corresponding to different Markov states, the edge node can control the edge node based on the corresponding control parameters in different Markov states. In addition, due to random external interference, the electric energy generated by the renewable energy power generation equipment in the edge node will be random, and the electric energy consumed by the edge computing equipment in the edge node to process computing tasks will also be random. In the embodiment of the present application, by controlling parameters, the electric energy generated by the traditional power generation equipment in the edge node and the electric energy consumed by the scheduling tasks performed by the edge node are controlled, which can suppress the impact of external random interference on the change of electric energy in the edge node, so that the electric energy consumed in the edge node is balanced with the electric energy generated, thereby ensuring the stability of the AC bus frequency and further ensuring the normal operation of the edge device power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 is a schematic diagram of an edge device energy supply system provided in an embodiment of the present application;

[0057] Figure 2 It is a flow chart of an implementation environment provided by an embodiment of the present application;

[0058] Figure 3 is a flow chart of a control method provided by an embodiment of the present application;

[0059] Figure 4 is a flow chart of another control method provided by an embodiment of the present application;

[0060] Figure 5 This is a flow chart of a solution based on a particle swarm optimization algorithm provided in an embodiment of the present application;

[0061] Figure 6 is a flow chart of another control method provided in an embodiment of the present application;

[0062] Figure 7 is a structural schematic diagram of a control device provided in an embodiment of the present application;

[0063] Figure 8 is a structural schematic diagram of another control device provided in an embodiment of the present application;

[0064] Fig. 9 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0065] Fig.10 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0067] It is understood that the terms "first", "second", etc. used in this application can be used in this article to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of this application, the first arrangement order can be called the second arrangement order, and the second arrangement order can be called the first arrangement order.

[0068] The terms "at least one", "a plurality of", "each", "any" and the like used in this application include one, two or more than two, a plurality of includes two or more than two, each refers to each of the corresponding plurality, and any refers to any one of the plurality. For example, the plurality of edge nodes include three edge nodes, and each edge node refers to each of the three edge nodes, and any refers to any one of the three edge nodes, which may be the first, the second, or the third.

[0069] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0070] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. Basic artificial intelligence technologies generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operating / interactive systems, mechatronics and other technologies. Artificial intelligence software technologies mainly include computer vision technology, speech processing technology, natural language processing technology, as well as machine learning / deep learning, autonomous driving, smart transportation and other major directions.

[0071] With the research and advancement of artificial intelligence technology, artificial intelligence technology has been studied and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, drones, robots, smart medical care, smart customer service, Internet of Vehicles, automatic driving, smart transportation, etc. I believe that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0072] In order to facilitate understanding of the embodiments of the present application, the key words involved in the embodiments of the present application are first explained:

[0073] Energy router system: A microgrid system with edge computing devices as loads. The energy router system includes renewable energy power generation equipment (such as photovoltaic power generation equipment), traditional power generation equipment and energy storage equipment.

[0074] AC bus frequency robust control: eliminate the impact of external interference on the AC bus frequency inside the microgrid and maintain the robust stability of the AC bus frequency inside the microgrid.

[0075] Markov chain: When the current state of a system is known, the state of the system at future moments is related to the current state, but has nothing to do with the state at historical moments. Markov chain is used to describe this random phenomenon.

[0076] Markov differential equation modeling: Simulating changes in system parameters based on Markov chain (Markov process). In the embodiment of the present application, since the edge device energy supply system is in operation, the parameters in each edge node in the edge device energy supply system (such as the power generation of the power generation equipment, the electric energy stored in the energy storage device, etc.) will change with time, and the parameters at the next moment are related to the parameters at the current moment. This change is the same as the random change described by the Markov chain. Therefore, based on the Markov chain simulation, the changes in the power generation of the renewable energy power generation equipment in each edge node in the edge device energy supply system, the changes in the power generation of the traditional power generation equipment, the changes in the electric energy stored in the energy storage device, the changes in the amount of computing tasks calculated by the edge computing device, and the changes in the amount of computing tasks or electric energy scheduled between different edge nodes are simulated.

[0077] Figure 2 is a schematic diagram of an implementation environment provided by an embodiment of the present application. Figure 2 , the implementation environment includes a computer device 201 and an edge device energy supply system 202. The computer device 201 and the edge device energy supply system 202 are connected via a wireless or wired network.

[0078] Among them, the computer device 201 is a terminal or a server. Optionally, the terminal includes but is not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle terminals, aircraft, etc. The server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The edge device energy supply system 202 includes multiple edge nodes ( Figure 2 In the example, 6 edge nodes are taken as an example), each edge node includes photovoltaic power generation equipment, traditional power generation equipment, energy storage equipment and edge computing equipment. Optionally, each edge node also includes ordinary loads, which refer to air conditioners, lights or other power-consuming equipment other than edge computing equipment.

[0079] The computer device 201 obtains the target operating parameters and target changes of each edge node in the edge device energy supply system 202 under each Markov state, and then models the edge device energy supply system 202 based on the Markov process based on the obtained target operating parameters and target changes, and determines the control parameters corresponding to each edge node under each Markov state based on the relationship data obtained by the modeling, and sends the obtained control parameters to the corresponding edge nodes in the edge device energy supply system 202, so that the edge nodes can control the operation of the edge nodes under the corresponding Markov state based on the received control parameters.

[0080] The embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving, etc.

[0081] Figure 3 is a flow chart of a control method provided by an embodiment of the present application. The execution subject of the embodiment of the present application is a computer device. Figure 3 , the method comprises the following steps:

[0082] 301. The computer device determines multiple Markov states of the edge device energy supply system.

[0083] The edge device energy supply system includes multiple edge nodes, each of which includes edge node equipment, traditional power generation equipment, renewable energy power generation equipment, and energy storage equipment. For the edge device energy supply system, the operating parameters in the edge device energy supply system will be different during different operating time periods.

[0084] Therefore, in the embodiment of the present application, in order to simulate the edge device energy supply system, a plurality of Markov states are determined, each Markov state refers to an operating state of the edge device energy supply system, and the target operating parameters of each edge node in different operating states are different, that is, different Markov states correspond to different target operating parameters. For example, during the operation of the edge device energy supply system, there is a situation in which the power generated by the power generation equipment in the edge node is greater than the power consumed by the edge computing device, and the excess power generated is stored in the energy storage device. There is also a situation in which the power generated by the power generation equipment is less than the power consumed by the edge computing device, and the energy storage device is required to power the edge computing device. These two situations can be regarded as two operating states of the two edge device energy supply systems, and these two operating states can be represented by different Markov states. And the operating state of the edge device energy supply system in different operating time periods can be the same or different, that is, each Markov state can correspond to one or more operating time periods.

[0085] 302. The computer device determines the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target change amount of each edge node in each Markov state in the edge device energy supply system.

[0086] Among them, the target operating parameter indicates the operating state of the edge node, and the target operating parameter under each Markov state indicates the operating state of the edge node in the operating time period corresponding to the Markov state; the target change includes the change in the amount of tasks performed by the edge node, and the target change under each Markov state includes the change in the amount of tasks performed by the edge node in the operating time period corresponding to the Markov state.

[0087] In the embodiment of the present application, during the operation of the edge device energy supply system, the power generation of the renewable energy power generation equipment in the edge node is affected by the renewable energy, and the renewable energy is randomly generated, for example, the generation of solar energy is related to the weather conditions; the computing tasks that the edge computing device in the edge node needs to process will change with the change of the received task processing request, and the task processing request is also beyond the control of the edge device energy supply system. The existence of these external interferences causes the electric energy generated and consumed in each edge node to change, thereby affecting the AC bus frequency inside each edge node in the edge device energy supply system. In order to keep the AC bus frequency inside each edge node stable, the electric energy generated in the edge node can be changed by controlling the power generation of the traditional power generation equipment in the edge node, or the electric energy consumed in the edge node can be changed by controlling the amount of computing tasks or electric energy scheduled between different edge nodes, so that the electric energy generated and consumed in each edge node are balanced.

[0088] Therefore, the embodiment of the present application establishes the relationship data corresponding to each edge node, and the relationship data corresponding to the edge node indicates the influence of the target change amount and the control identifier on the change of the target change amount when the target operating parameters remain unchanged, and the control identifier refers to the control parameter, which is the parameter used to control the edge node. Among them, the control parameter referred to by the control identifier is the parameter that needs to be determined to control the power generation of the traditional power generation equipment in the edge node and the computing task amount or electric energy scheduled between different edge nodes.

[0089] 303. The computer device determines the control parameters referred to by the control identifier corresponding to each edge node in the multiple Markov states based on the relationship data corresponding to multiple edge nodes in the edge device energy supply system under the multiple Markov states, and determines the control parameters corresponding to the same edge node under the multiple Markov states as a set of control parameters corresponding to the same edge node.

[0090] In the embodiment of the present application, when determining the control parameters, the computer device solves the relationship data corresponding to the multiple edge nodes under the multiple Markov states to obtain the multiple control parameters of each edge node under the multiple Markov states. For the same edge node, the control parameter set corresponding to the edge node includes the control parameters under the multiple Markov states, that is, there is a corresponding relationship between the control parameters and the Markov state.

[0091] 304. The computer device sends a corresponding control parameter set to each edge node respectively, so that the edge node controls the operation of the edge node in different Markov states based on the received control parameter set.

[0092] The purpose of the computer device determining the control parameters is to enable the edge device energy supply system to control the operation of each edge node separately based on the determined control parameters during actual operation. Therefore, the computer device needs to send a corresponding set of control parameters to each edge node.

[0093] The method provided in the embodiment of the present application, for each edge node in the edge device energy supply system, based on the target operating parameters and target change amount of each edge node in each Markov state, respectively obtains the relationship data corresponding to each edge node in each Markov state, the relationship data can simulate the change of the target change amount in the edge node under different Markov states, and determines the control parameters of each edge node in each Markov state based on the relationship data, so that the edge node can control the operation of the edge node based on the control parameters, and because the control parameters are control parameters corresponding to different Markov states, the edge node can control the edge node based on the corresponding control parameters in different Markov states. In addition, due to random external interference, the electric energy generated by the renewable energy power generation equipment in the edge node will be random, and the electric energy consumed by the edge computing equipment in the edge node to process computing tasks will also be random. In the embodiment of the present application, by controlling parameters, the electric energy generated by the traditional power generation equipment in the edge node and the electric energy consumed by the scheduling tasks performed by the edge node are controlled, which can suppress the impact of external random interference on the change of electric energy in the edge node, so that the electric energy consumed in the edge node is balanced with the electric energy generated, thereby ensuring the stability of the AC bus frequency and further ensuring the normal operation of the edge device power supply system.

[0094] Figure 4 is a flow chart of another control method provided by an embodiment of the present application. The execution subject of the embodiment of the present application is a computer device. Figure 4 , the method comprises the following steps:

[0095] 401. The computer device determines multiple Markov states of the edge device energy supply system.

[0096] In the embodiment of the present application, the edge device energy supply system includes multiple edge nodes, and at least two edge nodes among the multiple edge nodes can schedule computing tasks or dispatch electric energy to each other. Figure 1 As shown in the figure, two edge nodes connected by a dotted line can schedule computing tasks or power to each other. The edge device power supply system can be regarded as an undirected graph G(V, ζ), where V represents the edge nodes in the edge device power supply system, and ζ is the edge set of the undirected graph, which represents the scheduling line between the two edge nodes in the edge device power supply system. The edge e(l)=(i,j)=(j,i) indicates that there is a scheduling of computing tasks or power between the i-th edge node and the j-th edge node.

[0097] When the load consumption of a certain edge node is too high, the local energy of the edge node cannot make up for the consumption of the edge node. In this case, the edge node can dispatch part of the computing tasks to other edge nodes in the edge device energy supply system, or dispatch part of the electric energy from other edge nodes to the edge node to make up for the energy consumption of the edge node. For any edge device energy supply system, considering the influence of factors such as geographical location and time delay, in order to reduce time delay, there is a scheduling of computing tasks or electric energy between two edge nodes with a close geographical location, while there is no scheduling of computing tasks or electric energy between two edge nodes with a far geographical location.

[0098] The purpose of the embodiment of the present application is to reduce the impact of randomness and time delay on the stability of bus frequency by controlling the traditional power generation equipment in each edge node and the scheduling of computing tasks or electric energy between two edge nodes. In order to achieve the above purpose, the embodiment of the present application models the edge device energy supply system based on the Markov process, that is, based on the actual operating state of the edge device energy supply system, multiple Markov states are set, and each Markov state corresponds to an operating state of the edge device energy supply system.

[0099] In a possible implementation, the computer device determines multiple operating states, that is, multiple Markov states, by counting the operating parameters of each edge node in the edge device energy supply system in the historical time period and the change in the amount of tasks performed, and regards the operating states corresponding to the same operating parameters and the same change in the amount of tasks performed as the same operating state. Alternatively, the technicians preset multiple Markov states based on prior experience.

[0100] 402. The computer device determines the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system.

[0101] Among them, the target operating parameters indicate the operating status of the edge node. Different edge nodes have different target operating parameters under different Markov states, and each edge node has its own operating parameters at each moment; the target change includes the change in the amount of tasks performed by the edge node. The relationship data corresponding to the edge node indicates the influence of the target change and the control identifier on the change of the target change when the target operating parameters remain unchanged. The control parameter referred to by the control identifier is the parameter used to control the edge node. Different edge nodes are controlled by different control parameters.

[0102] In the embodiment of the present application, during the operation of the edge device energy supply system, the power generation of the renewable energy power generation equipment in the edge node is affected by the renewable energy, and the renewable energy is randomly generated, for example, the generation of solar energy is related to the weather conditions; the computing tasks that the edge computing device in the edge node needs to process will change with the change of the received task processing request, and the task processing request is also beyond the control of the edge device energy supply system. The existence of these external interferences causes the electric energy generated and consumed in each edge node to change, thereby affecting the AC bus frequency inside each edge node in the edge device energy supply system. In order to keep the AC bus frequency inside each edge node stable, the electric energy generated in the edge node can be changed by controlling the power generation of the traditional power generation equipment in the edge node, or the electric energy consumed in the edge node can be changed by controlling the amount of computing tasks or electric energy scheduled between different edge nodes, so that the electric energy generated and consumed in each edge node are balanced.

[0103] In a possible implementation, based on the above considerations, models are respectively constructed for the case where the amount of executed tasks is affected by the control parameters, the case where the amount of executed tasks is affected by the random parameters, and the case where the amount of executed tasks is not affected by the control parameters and the random parameters, to obtain different relationship data, and the obtained relationship data includes the following:

[0104] The first one:

[0105] The target variation is the first variation, which refers to the variation of the first task quantity executed in the edge node, and the first task quantity changes with the change of the control parameter, that is, the first variation can be artificially adjusted by the control parameter; the target operation parameter includes a first time constant and a control coefficient, the first time constant indicates the response speed of the edge node to each first task, and the control coefficient indicates the influence of the control parameter on the first task quantity. Among them, the first time constant and the control coefficient are known parameters, and optionally, the first time constant and the control coefficient are obtained by collecting parameters in the actual operation process of the edge device energy supply system.

[0106] For each edge node, the computer device determines the first relationship data corresponding to the edge node in each Markov state based on the first time constant, the first change amount and the control coefficient of the edge node in each Markov state. The first relationship data in each Markov state indicates the influence of the first change amount, the control coefficient and the control identifier on the change of the first change amount when the first time constant remains unchanged.

[0107] In a possible implementation, there may be scheduling of computing tasks or electric energy between different edge nodes in the edge device energy supply system. For example, there is scheduling of computing tasks between edge node A and edge node B. When the amount of computing tasks in edge node A is large and the amount of computing tasks in edge node B is small, part of the computing tasks in edge node A can be scheduled to edge node B. Therefore, the scheduling of computing tasks or energy is an important link that affects the stability of bus frequency, and it is necessary to model the scheduling process.

[0108] For each edge node, in this case, the first change is the scheduling task change, which refers to the change in the amount of computing tasks or electric energy scheduled between the edge node and other edge nodes in the edge device energy supply system. The first time constant corresponding to the scheduling task change indicates the response speed of the edge node to scheduling a computing task or unit electric energy, and the control coefficient corresponding to the scheduling task change indicates the influence of the control parameter on the scheduled computing task or electric energy. The computer device determines the scheduling relationship data corresponding to the edge node in each Markov state based on the first time constant, the scheduling task change, the control coefficient and the delay time of the edge node in each Markov state. Among them, the scheduling relationship data in each Markov state represents the influence of the scheduling task change, the control coefficient, the delay time and the control identifier on the change of the scheduling task change when the first time constant remains unchanged, and the delay time refers to the time consumed when scheduling a computing task or unit electric energy.

[0109] Optionally, for each edge node, when there is a computing task or power scheduling between the edge node and multiple other edge nodes in the edge device energy supply system, there will be multiple scheduling routes, each scheduling route connecting the edge node with any other edge node. Therefore, when determining the scheduling task relationship data, it is necessary to determine the corresponding scheduling task relationship data for each scheduling route.

[0110] First For example, in the Markov state In the Markov state, the change of the computing task volume or electric energy scheduled in the lth scheduling route is modeled to obtain the relationship data shown in the following formula (1):

[0111]

[0112] in, represents the change in the amount of change in the scheduling task in the lth scheduling route, Indicated in The first time constant corresponding to the change in the scheduling task in the lth scheduling route in the Markov state, It represents the change of the scheduling task at time t-τ in the lth scheduling route, t represents the time, τ represents the delay time, Indicated in The control coefficient corresponding to the change in the scheduling task in the lth scheduling route under the Markov state is: Indicated in The control identifier corresponding to the change in the scheduling task in the lth scheduling route under the Markov state, the subscript TS represents the scheduling task, that is, the parameters with the subscript TS are parameters related to the scheduling task. In the formula (1), is the variable to be determined, and is a known quantity.

[0113] In one possible implementation, due to the uncontrollability and strong randomness of renewable energy, the electric energy generated by the renewable energy power generation equipment in the edge node is also uncontrollable and highly random. If the edge node is powered only by renewable energy power generation equipment, it is unreliable. Therefore, the edge node is also powered by traditional power generation equipment to ensure the normal operation of the edge node. Therefore, power supply based on traditional power generation equipment is also an important link that affects the stability of bus frequency, and it is necessary to model the power generation process of traditional power generation equipment.

[0114] For each edge node, in this case, the first change is the first power change, which refers to the change in the power generation of the traditional power generation equipment in the edge node. The first time constant corresponding to the first power change indicates the response speed of the edge node to the power generation task of the traditional power generation equipment, and the control coefficient corresponding to the first power change indicates the influence of the control parameter on the change in the power generation of the traditional power generation equipment. The computer device determines the first power relationship data corresponding to the edge node in each Markov state based on the first time constant, the first power change and the control coefficient of the edge node in each Markov state. The first power relationship data in each Markov state represents the influence of the first power change, the control coefficient and the control parameter indicated by the control identifier on the change of the first power change when the first time constant remains unchanged.

[0115] First For example, for the Markov state The modeling of the change in the power generation of the traditional power generation equipment in the kth edge node under a Markov state is as follows:

[0116]

[0117] in, Indicates the change of the first power change in the kth edge node, Indicated in The first time constant corresponding to the first power change in the kth edge node in the Markov state, represents the first power change in the kth edge node, t represents the time, Indicated in The control coefficient corresponding to the first power change in the kth edge node in the Markov state is, Indicated in The control identifier corresponding to the first power change in the kth edge node in the Markov state, the subscript MT represents the power generation of the traditional power generation equipment, that is, the parameter with the subscript MT is a parameter related to the power generation of the traditional power generation equipment. In the formula (2), is the variable to be determined, and is a known quantity.

[0118] Second type:

[0119] The target change is the second change, which refers to the change in the second task quantity performed by the edge node, and the second task quantity changes with the change of the interference parameter; the target operation parameters include a second time constant and an interference parameter, the second time constant indicates the response speed of the edge node to each second task, and the interference parameter indicates the influence of the interference parameter on the second task quantity, and the interference parameter is the interference of the simulated external environment on the edge device energy supply system. Among them, the second time constant and the interference parameter are known parameters, and optionally, the second time constant and the interference parameter are obtained by collecting parameters during the actual operation of the edge device energy supply system. It should be noted that in the actual operation of the edge device energy supply system, the interference parameter is randomly generated based on external interference.

[0120] For each edge node, the computer device determines the second relationship data corresponding to the edge node in each Markov state based on the second time constant, the second change amount and the interference parameter corresponding to the edge node in each Markov state, and the second relationship data indicates the influence of the second change amount and the interference parameter on the change of the second change amount when the second time constant remains unchanged.

[0121] In one possible implementation, the edge computing device in the edge node needs to process a large number of computing tasks. In the process of processing computing tasks, the power consumed by the edge computing device is not negligible. In the embodiment of the present application, it is considered that the edge computing device may be subject to external interference, such as an increase in task requests from users, and these interferences will affect the amount of computing tasks that the edge computing device needs to process, thereby significantly changing the power consumed by the edge computing device. Therefore, the processing of computing tasks based on edge computing devices is also an important link that affects the stability of bus frequency, and it is necessary to model the computing task processing process of edge computing devices.

[0122] For each edge node, in this case, the second variation is the load variation, which refers to the variation of the computing task amount of the edge computing device in the edge node, the second time constant corresponding to the load variation indicates the response speed of the edge node to processing each computing task, and the interference parameter corresponding to the load variation indicates the influence of the interference parameter on the computing task amount processed by the edge computing device. Based on the second time constant, the load variation and the interference parameter of the edge node in each Markov state, the computer device determines the load relationship data corresponding to the edge node in each Markov state, respectively, and the load relationship data indicates the influence of the load variation and the interference parameter on the change of the load variation when the second time constant remains unchanged.

[0123] First For example, for the Markov state The modeling of the load change of the edge computing device in the kth edge node under a Markov state is as follows:

[0124]

[0125] in, Indicates the change in load variation in the kth edge node, Indicated in The second time constant corresponding to the load change in the kth edge node in the Markov state, represents the load change in the kth edge node, t represents the time, Indicated in The interference parameter corresponding to the load change in the kth edge node under the Markov state, the subscript TC represents the load of the edge computing device, that is, the parameter with the subscript TC is the parameter related to the load of the edge computing device.

[0126] In one possible implementation, in order to provide environmentally friendly and economical energy to edge nodes, renewable energy generation equipment can be used to generate electricity using renewable energy. However, renewable energy has randomness. For example, solar energy changes with weather changes, and the randomness of renewable energy significantly affects the electricity generated by the renewable energy generation equipment. Therefore, power supply based on renewable energy generation equipment is also an important link that affects the stability of bus frequency, and it is necessary to model the power generation process of renewable energy generation equipment.

[0127] For each edge node, in this case, the second variation is the second power variation, the second power variation refers to the variation of the power generation of the renewable energy power generation equipment in the edge node, the second time constant corresponding to the second power variation indicates the response speed of the edge node to the power generation task of the renewable energy power generation equipment, and the interference parameter corresponding to the second power variation indicates the influence of the interference parameter on the variation of the power generation of the renewable energy power generation equipment. The computer device determines the second power relationship data corresponding to the edge node in each Markov state based on the second time constant, the second power variation and the interference parameter of the edge node in each Markov state. The second power relationship data in each Markov state represents the influence of the second power variation and the interference parameter on the change of the second power variation when the second time constant remains unchanged.

[0128] First For example, for the Markov state The modeling of the change in the power generation capacity of the renewable energy power generation equipment in the kth edge node under a Markov state is as follows:

[0129]

[0130] in, represents the change of the second power variation in the kth edge node, Indicated in The second time constant corresponding to the second power change in the kth edge node in the Markov state, represents the second power change in the kth edge node, t represents the time, Indicated in The interference parameter corresponding to the second power change in the kth edge node under the Markov state, the subscript PV represents the power generation power of the renewable energy power generation equipment, that is, the parameter with the subscript PV is a parameter related to the power generation power of the renewable energy power generation equipment.

[0131] The third type:

[0132] In the embodiment of the present application, although the electric energy stored in the energy storage device has no direct relationship with the random parameters and the control parameters, that is, the energy storage device is not directly affected by the external environment and cannot directly control the electric energy stored in the energy storage device, the energy storage device is closely related to the electric energy currently generated and consumed in the edge node, that is, when the generated electric energy is greater than the consumed electric energy, the energy storage device will store the excess electric energy, and the electric energy stored in the storage device will increase, and when the generated electric energy is less than the consumed electric energy, the energy storage device will supply power to the edge computing device, and the electric energy stored in the storage device will decrease. Therefore, the storage of electric energy by the energy storage device is also an important link affecting the stability of the bus frequency, and it is necessary to model the storage of electric energy by the energy storage device.

[0133] The target change is the third change, which is the change of the electric energy stored in the energy storage device in the edge node. The target operation parameters include the third time constant and the first damping coefficient, and the third time constant indicates the response speed of the edge node to the stored electric energy. The third time constant and the first damping coefficient are known parameters. Optionally, the third time constant and the first damping coefficient are obtained by collecting parameters during the actual operation of the edge device energy supply system.

[0134] For each edge node, the computer device determines the energy storage relationship data corresponding to the edge node in each Markov state based on the third time constant, the third change, the first damping coefficient and the AC bus frequency deviation of the edge node in each Markov state. The energy storage relationship change indicates the influence of the third change, the first damping coefficient and the AC bus frequency deviation on the change of the third change when the third time constant remains unchanged, and the AC bus frequency deviation indicates the value of the AC bus frequency in the edge node at at least one moment.

[0135] First For example, for the Markov state The modeling of the change in the amount of stored electric energy in the energy storage device of the kth edge node under a Markov state is as follows:

[0136]

[0137] in, Indicates the change of the third change amount in the kth edge node, Indicated in The third time constant corresponding to the third change in the kth edge node in the Markov state, represents the third change in the kth edge node, t represents the time, Indicated in The first damping coefficient corresponding to the third change in the kth edge node in the Markov state, Δf k (t) indicates the The AC bus frequency deviation in the kth edge node under a Markov state, the subscript BES represents the electric energy stored in the energy storage device, that is, the parameters with the subscript BES are parameters related to the electric energy stored in the energy storage device.

[0138] 403. For each Markov state in each edge node, the computer device determines the power balance relationship in the edge node based on the target change in the Markov state, the unit energy consumption of each computing task, and the scheduling direction of each scheduling task, and determines the frequency deviation relationship data corresponding to the edge node based on the power balance relationship in the Markov state, the inertia constant, the second damping coefficient, and the AC bus frequency deviation in the edge node.

[0139] Among them, the power balance relationship represents the difference between the power consumed and the power generated in the edge node, the unit energy consumption represents the power consumed by the edge node to process a computing task, and the scheduling direction represents the direction of scheduling computing tasks or scheduling power between the edge node and other edge nodes in the edge device power supply system.

[0140] First For example, for the Markov state The modeling of the power balance relationship in the kth edge node under a Markov state is as follows:

[0141]

[0142] Among them, ΔP k Represents the electrical energy balance relationship, represents the load change, E represents the unit energy consumption, represents the second power variation, represents the first power change, represents the third variation (the rate of change of the electric energy stored in the energy storage device), represents the change in the scheduling task, f(k, l) represents the direction of the lth scheduling route for the kth edge node, L represents the number of total scheduling routes in the edge device energy supply system, and the value of f(k, l) is 1 or -1. When the value of f(k, l) is 1, it means that the kth edge node sends computing tasks to other edge nodes through the lth scheduling route, and when the value of f(k, l) is -1, it means that the kth edge node receives computing tasks sent by other edge nodes through the lth scheduling route. Formula (6) takes the scheduling of computing tasks as an example. In another embodiment, electric energy can also be scheduled.

[0143] In an embodiment of the present application, the edge device power supply system is modeled based on the Markov chain to determine the control parameters that keep the AC bus frequency deviation in each edge node in the edge device power supply system stable. In the above implementation process, the computer device has established the first relationship data, the second relationship data, the third relationship data and the power balance relationship, and it is also necessary to model the AC bus frequency deviation.

[0144] The computer device determines the frequency deviation relationship data corresponding to the edge node based on the power balance relationship, inertia constant, second damping coefficient and AC bus frequency deviation in the edge node under the Markov state, and the frequency deviation relationship data indicates the influence of the power balance relationship, inertia constant and second damping coefficient on the change of AC bus frequency deviation. Among them, the inertia constant and the second damping coefficient are parameters included in the target operating parameters, and the inertia constant and the second damping coefficient are known parameters. Optionally, the inertia constant and the second damping coefficient are obtained by collecting parameters during the actual operation of the edge device energy supply system.

[0145] First For example, for the Markov state The modeling of the AC bus frequency deviation in the kth edge node under a Markov state is as follows:

[0146]

[0147] Where dΔf k (t) represents the change of AC bus frequency deviation in the kth edge node, Indicated in The inertia constant in the kth edge node in the Markov state, Δf k (t) represents the AC bus frequency deviation in the kth edge node, t represents the time, Indicated in The second damping coefficient in the kth edge node in the Markov state.

[0148] 404. The computer device determines the control parameters indicated by the control identifier corresponding to each edge node in the multiple Markov states based on the relationship data corresponding to the multiple edge nodes in the edge device energy supply system under the multiple Markov states, so that the AC bus frequency deviation in the edge node indicated by the frequency deviation relationship data corresponding to each edge node is less than a preset threshold.

[0149] Among them, the preset threshold is any value. If the AC bus frequency deviation is less than the preset threshold, it means that the AC bus frequency changes little at different times, which can ensure that the AC bus frequency in the edge node in the edge device energy supply system is in a stable state.

[0150] In one possible implementation, a computer device uses a Lyapunov functional method to transform first relationship data, second relationship data, and third relationship data corresponding to multiple edge nodes under multiple Markov states, and obtains linear matrix inequalities corresponding to multiple edge nodes under multiple Markov states, wherein the linear matrix inequality represents a satisfied relationship between target operating parameters and control identifiers when the AC bus frequency in multiple edge nodes is stable; then a particle swarm optimization algorithm is used to solve the linear inequality to obtain control parameters referred to by the control identifier corresponding to each edge node under multiple Markov states.

[0151] Optionally, before using the Lyapunov functional method, the computer device first associates the above formulas (1)-(5) to obtain association relationship data (8):

[0152]

[0153] Among them, A(r t ) represents a matrix composed of the second time constants corresponding to the load changes of multiple edge nodes under multiple Markov states, A d (r t ) represents the matrix composed of the first time constant and control coefficient corresponding to the change of the scheduling task of multiple edge nodes under various Markov states, B(r t ) represents a matrix composed of the second time constants corresponding to the second power changes of multiple edge nodes under multiple Markov states, C(r t ) represents a matrix composed of the first time constants and control coefficients corresponding to the first power changes of multiple edge nodes under multiple Markov states, D(r t ) represents a matrix consisting of a third time constant and a first damping coefficient corresponding to changes in stored electric energy of multiple edge nodes under multiple Markov states, x represents a system state matrix consisting of changes in loads, scheduling tasks, second power changes, first power changes, changes in stored electric energy and AC bus frequency deviations of multiple edge nodes under multiple Markov states, u represents a control parameter matrix consisting of control parameters corresponding to changes in scheduling tasks of multiple edge nodes under multiple Markov states and control parameters corresponding to first power changes, v represents an interference parameter matrix consisting of interference parameters corresponding to load changes of multiple edge nodes under multiple Markov states and interference parameters corresponding to second power changes, dx represents the total change of each change, z represents an output matrix, which includes the AC bus frequency deviations of each edge node under multiple Markov states.

[0154] Before using the Lyapunov functional method, computer equipment also needs to determine the probability of transitions between multiple Markov states. The state space of the Markov chain is defined as S = 1, 2, 3 ..., o, where each parameter in the state space represents a Markov state, and the space transfer matrix is ​​Π = [π i，j ], i, j = 1, 2, 3 ..., o, the spatial transfer matrix includes the mode switching rate between any two Markov states, the mode switching rate indicates the possibility of jumping from one Markov state to another Markov state, and the Markov chain satisfies the following formula (9):

[0155]

[0156] Among them, P r {r(t+dt)=j|r(t)=i} represents the probability of jumping from the i-th Markov state to the j-th Markov state, r(t+dt) represents the j-th Markov state, r(t) represents the i-th Markov state, t represents the current time, t+dt represents the time after dt time has passed from the current time t, that is, the current time t is in the i-th Markov state, and the next time t+dt is in the j-th Markov state, π i，j represents the mode switching rate from the i-th Markov state to the j-th Markov state, π i，j ≥0, It means that π i Defined as π i，i ,and and, o represents a total of o Markov states in the state space.

[0157] The jump between different Markov states in the above formula (9) represents the transition between different operating states in the edge device power supply system, that is, the jump from one Markov state to another Markov state. In the edge device power supply system, it is a transition from one operating state to another operating state. For example, the operating state in which the electric energy generated by the edge node is greater than the electric energy consumed is converted to the operating state in which the electric energy generated by the edge node is less than the electric energy consumed.

[0158] For the above-mentioned association data (8), it is ultimately necessary to solve multiple control parameters, which need to meet the following conditions: each AC bus deviation included in the output matrix is ​​less than a preset threshold, that is, to ensure that each AC bus frequency deviation remains stable. In order to achieve this goal, the Lyapunov functional method is used to transform the association data (8) to obtain the following linear matrix inequality (10):

[0159]

[0160] Among them, Ω h for:

[0161]

[0162] Ξ h for:

[0163]

[0164] Γ h for:

[0165] Γ h =diag[X h , ..., X h-1 , X h+1 , ..., X o , R]

[0166] The subscript h refers to (r t ). I is the unit matrix, γ, R, X h and Y h is the parameter to be determined, u=K h x, A dh ′、X h ′、D h ′、C h ′ and Ξ h A dh , X h , D h , C h and h The transposed matrix of , diag[] represents the diagonal matrix, represents the mode switching rate between the hth Markov state and the first Markov state, and the same is true for the others.

[0167] Among them, γ represents the influence of the interference parameter on the control parameter. Optionally, in order to improve the suppression of the interference parameter, that is, to improve the anti-interference ability of the control parameter, and because the interference parameter always exists, that is, the influence of the interference parameter on the control parameter always exists, it is necessary to make γ take the minimum value as much as possible when it is not less than 0, that is, to optimize the above formula (10) to the following formula (11):

[0168]

[0169] Wherein, ω represents the preset weight.

[0170] Then, the computer device uses a particle swarm optimization algorithm to solve the above formula (11) to obtain the control parameters corresponding to each edge node in each Markov state.

[0171] The solution process of the particle swarm optimization algorithm is shown in Figure 5 , the computer device first initializes the particles, that is, initializes the particle group (speed and position), inertia factor, acceleration constant, maximum number of iterations and the minimum allowable error for algorithm termination; then determines the fitness value of each particle, and when the fitness value of each particle is the initial fitness value, the initial fitness value is used as the local optimal value and global optimal value of the current particle, and the position corresponding to the initial fitness value is used as the position of the local optimal value of the current particle and the global optimal value of the particle group. When the fitness value of each particle is not the initial fitness value, the current fitness value is compared with the historical fitness value, and then the local optimal value of the current particle and the global optimal value of the particle group are determined; then the current speed and current position of each particle are updated. Then determine whether the current number of iterations has reached the maximum number of times. If the maximum number of iterations has been reached, the global optimal value of the particle group and its corresponding position and the local optimal value of each particle and its corresponding position are output; if the maximum number of iterations has not been reached, the number of iterations is increased by 1, and the process of determining the fitness value of each particle is performed again.

[0172] In the embodiment of the present application, the computer device calculates the γ, R, and X to be solved. h and Y h Consider γ, R, and X as a particle respectively. h and Y h The whole is regarded as a particle swarm, and then the particle swarm optimization algorithm is used in the given search space to search for γ, R, X h and Y h The search space contains multiple values.

[0173] It should be noted that, through the above formula (10) or formula (11), it is necessary to determine a set of γ, R, and X corresponding to each edge node in each Markov state. h and Y h , based on determining each group of γ, R, X h and Y h , determine the control parameters corresponding to each edge node in each Markov state.

[0174] In another possible implementation, the computer device transforms the relationship data corresponding to multiple edge nodes under multiple Markov states to obtain fourth relationship data corresponding to multiple edge nodes under multiple Markov states, and the fourth relationship data represents the relationship between the control identifier and the target operating parameter and the target change amount; based on the target operating parameter, target change amount and fourth relationship data corresponding to each edge node, the control parameter referred to by the control identifier corresponding to each edge node under multiple Markov states is determined. Wherein, when the fourth relationship data and the target operating parameters and target change amounts corresponding to multiple edge nodes under multiple Markov states are determined, the target operating parameters and target change amounts are substituted into the fourth relationship data, and then solved, and the control parameters corresponding to each edge node under multiple Markov states can also be obtained.

[0175] Of course, in another embodiment, other methods can be used to determine the control parameters corresponding to each edge node under multiple Markov states based on the determined relationship data. The embodiment of the present application does not limit the specific algorithm for solving the control parameters.

[0176] 405. The computer device sends a corresponding control parameter set to each edge node respectively, so that the edge node controls the operation of the edge node in different Markov states based on the received control parameter set.

[0177] The purpose of the computer device determining the control parameters is to enable the edge device energy supply system to control the operation of each edge node based on the determined control parameters during the actual operation. Therefore, the computer device needs to send a corresponding set of control parameters to each edge node. The implementation method of the edge node controlling the operation of the edge node based on the control parameters is as follows Figure 6 The embodiments shown will not be described in detail here.

[0178] The method provided in the embodiment of the present application, for each edge node in the edge device energy supply system, based on the target operating parameters and target change amount of each edge node in each Markov state, respectively obtains the relationship data corresponding to each edge node in each Markov state, the relationship data can simulate the change of the target change amount in the edge node under different Markov states, and determines the control parameters of each edge node in each Markov state based on the relationship data, so that the edge node can control the operation of the edge node based on the control parameters, and because the control parameters are control parameters corresponding to different Markov states, the edge node can control the edge node based on the corresponding control parameters in different Markov states. In addition, due to random external interference, the electric energy generated by the renewable energy power generation equipment in the edge node will be random, and the electric energy consumed by the edge computing equipment in the edge node to process computing tasks will also be random. In the embodiment of the present application, by controlling parameters, the electric energy generated by the traditional power generation equipment in the edge node and the electric energy consumed by the scheduling tasks performed by the edge node are controlled, which can suppress the impact of external random interference on the change of electric energy in the edge node, so that the electric energy consumed in the edge node is balanced with the electric energy generated, thereby ensuring the stability of the AC bus frequency and further ensuring the normal operation of the edge device power supply system.

[0179] Figure 6 is a flow chart of another control method provided by an embodiment of the present application. The execution subject of the embodiment of the present application is an edge computing device in a target edge node, and the target edge node is any edge node in an edge device energy supply system. Figure 6 , the method comprises the following steps:

[0180] 601. The edge computing device obtains a control parameter set corresponding to a target edge node, where the control parameter set includes control parameters corresponding to the target edge node under different Markov states.

[0181] Among them, the control parameter set is composed of the above Figure 5 The embodiment shown is determined.

[0182] 602. The edge computing device determines a current Markov state corresponding to the current operating parameters from a plurality of Markov states based on the current operating parameters of the target edge node and a plurality of Markov states of the energy supply system of the edge device.

[0183] Since the operating parameters of the edge node do not remain unchanged during operation, but change with external interference, the working state of the edge node, etc., that is, as the operating state of the edge node changes, the operating parameters will also change. Based on this situation, the Markov state corresponding to each operating state can be determined, that is, the Markov state corresponding to the operating parameters under each operating state can be determined.

[0184] In one possible implementation, the edge computing device calls the Markov model to process the current operating parameters of the target edge node to obtain the Markov state corresponding to the current operating parameters. Currently, the edge computing device can also use other methods to determine the current Markov state of the target edge node, and the embodiment of the present application does not limit the method of determining the Markov state.

[0185] 603. The edge computing device controls the target edge node based on the control parameters in the current Markov state.

[0186] After determining the current Markov state, the edge computing device obtains the control parameters under the current Markov state from the control parameter set, and then controls the target edge node based on the control parameters.

[0187] Among them, controlling the target edge node includes: controlling the scheduling of computing tasks or the scheduling of electric energy between the target edge node and other edge nodes in the edge device energy supply system, and controlling the power generation power of traditional power generation equipment in the target edge node.

[0188] In one possible implementation, the edge computing device can determine the Markov state at the next moment based on the modal switching rate between the current Markov state and other Markov states among the multiple Markov states; at the next moment, the target edge node is controlled based on the control parameters in the Markov state at the next moment. The modal switching rate indicates the possibility of jumping from one Markov state to another Markov state, and the modal switching rate is pre-set.

[0189] It should be noted that the embodiments of the present application are only described by taking the target edge node as an example. For the edge device power supply system, each edge node in the edge device power supply system can be controlled using the above implementation.

[0190] The method provided in the embodiment of the present application is that during the operation of the target edge node, the target edge node can be controlled based on the control parameters corresponding to the current Markov state by determining the current Markov state of the target edge node. Due to external random interference, the electric energy generated by the renewable energy power generation equipment in the target edge node is random, and the electric energy consumed by the edge computing device in the target edge node to process the computing tasks is also random. In the embodiment of the present application, the electric energy generated by the traditional power generation equipment in the target edge node and the electric energy consumed by the scheduling tasks performed by the target edge node are controlled by controlling the parameters, which can suppress the influence of external random interference on the change of electric energy in the target edge node, so that the electric energy consumed in the target edge node is balanced with the electric energy generated, thereby ensuring the stability of the AC bus frequency.

[0191] Figure 7 is a schematic diagram of the structure of a control device provided in an embodiment of the present application. Figure 7 , the device comprises:

[0192] A state determination module 701 is used to determine multiple Markov states of the edge device energy supply system;

[0193] The relationship data determination module 702 is used to determine the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system, wherein the target operating parameters indicate the operating state of the edge node, the target variation includes the variation of the amount of tasks performed by the edge node, and the relationship data corresponding to the edge node indicates the influence of the target variation and the control identifier on the variation of the target variation when the target operating parameters remain unchanged, and the control parameter indicated by the control identifier is a parameter used to control the edge node;

[0194] A control parameter determination module 703 is used to determine the control parameters referred to by the control identifiers corresponding to each edge node under multiple Markov states based on the relationship data corresponding to multiple edge nodes in the edge device energy supply system under multiple Markov states, and determine the control parameters corresponding to the same edge node under multiple Markov states as a control parameter set corresponding to the same edge node;

[0195] The control parameter sending module 704 is used to send a corresponding control parameter set to each edge node respectively, so that the edge node controls the operation of the edge node in different Markov states based on the received control parameter set.

[0196] The apparatus provided in the embodiment of the present application obtains, for each edge node in the edge device energy supply system, relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target change amount of each edge node in each Markov state, respectively. The relationship data can simulate the change of the target change amount in the edge node under different Markov states, and the control parameters of each edge node in each Markov state are determined based on the relationship data, so that the edge node can control the operation of the edge node based on the control parameters, and since the control parameters are control parameters corresponding to different Markov states, the edge node can control the edge node based on the corresponding control parameters under different Markov states. In addition, due to random external interference, the electric energy generated by the renewable energy power generation equipment in the edge node will be random, and the electric energy consumed by the edge computing equipment in the edge node to process computing tasks will also be random. In the embodiment of the present application, by controlling parameters, the electric energy generated by the traditional power generation equipment in the edge node and the electric energy consumed by the scheduling tasks performed by the edge node are controlled, which can suppress the impact of external random interference on the change of electric energy in the edge node, so that the electric energy consumed in the edge node is balanced with the electric energy generated, thereby ensuring the stability of the AC bus frequency and further ensuring the normal operation of the edge device power supply system.

[0197] In a possible implementation, the target change amount is a first change amount, the first change amount refers to a change amount of a first task amount executed in the edge node, the first task amount changes with a change in a control parameter, the target operation parameter includes a first time constant and a control coefficient, the first time constant indicates a response speed of the edge node to each first task, and the control coefficient indicates an influence of the control parameter on the first task amount;

[0198] The relationship data determination module 702 includes:

[0199] The first relationship data determination unit is used to determine, for each edge node, the first relationship data corresponding to the edge node in each Markov state based on the first time constant, the first change amount and the control coefficient of the edge node in each Markov state, wherein the first relationship data in each Markov state indicates the influence of the first change amount, the control coefficient and the control parameter indicated by the control identifier on the change of the first change amount when the first time constant remains unchanged.

[0200] In another possible implementation, the target change amount is a second change amount, the second change amount refers to a change amount of a second task amount performed by the edge node, the second task amount changes with a change in an interference parameter, the target operation parameter includes a second time constant and an interference parameter, the second time constant indicates a response speed of the edge node to each second task, and the interference parameter indicates an influence of the interference parameter on the second task amount;

[0201] The relationship data determination module 702 further includes:

[0202] A second relationship data determination unit is used to determine, for each edge node, second relationship data corresponding to the edge node in each Markov state based on a second time constant, a second change amount and an interference parameter corresponding to the edge node in each Markov state, wherein the second relationship data indicates the influence of the second change amount and the interference parameter on the change of the second change amount when the second time constant remains unchanged.

[0203] In another possible implementation manner, the first relationship data determining unit is configured to:

[0204] The first change is the scheduling task change, which refers to the change in the amount of computing tasks or electric energy scheduled between the edge node and other edge nodes in the edge device energy supply system. Based on the first time constant, the scheduling task change, the control coefficient and the delay time of the edge node in each Markov state, the scheduling relationship data corresponding to the edge node in each Markov state are determined respectively. The delay time refers to the time spent in scheduling the computing task or electric energy; or

[0205] The first change is the first power change, which refers to the change in the power generation power of the traditional power generation equipment in the edge node. Based on the first time constant, the first power change and the control coefficient of the edge node in each Markov state, the first power relationship data corresponding to the edge node in each Markov state are determined respectively.

[0206] In another possible implementation manner, the second relationship data determining unit is configured to:

[0207] The second change is a load change, which refers to a change in the amount of computing tasks of the edge computing device in the edge node. Based on the second time constant, load change, and interference parameter of the edge node in each Markov state, the load relationship data corresponding to the edge node in each Markov state is determined respectively; or,

[0208] The second change is the second power change, which refers to the change in the power generation power of the renewable energy power generation equipment in the edge node. Based on the second time constant, the second power change and the interference parameter of the edge node in each Markov state, the second power relationship data corresponding to the edge node in each Markov state is determined respectively.

[0209] In another possible implementation, the target change amount is a third change amount, the third change amount is a change amount of electric energy stored in the energy storage device in the edge node, the target operating parameter includes a third time constant and a first damping coefficient, the third time constant indicates a response speed of the edge node to the stored electric energy, and the relationship data determination module 702 further includes:

[0210] The third relationship data determination unit is used to determine, for each edge node, the energy storage relationship data corresponding to the edge node in each Markov state based on the third time constant, the third change, the first damping coefficient and the AC bus frequency deviation of the edge node in each Markov state, wherein the energy storage relationship change indicates the influence of the third change, the first damping coefficient and the AC bus frequency deviation on the change of the third change when the third time constant remains unchanged, and the AC bus frequency deviation indicates the value of the AC bus frequency in the edge node at at least one moment.

[0211] In another possible implementation, the target operating parameter further includes an inertia constant and a second damping coefficient, and the device further includes:

[0212] A balance relationship determination module is used to determine the power balance relationship in the edge node for each Markov state based on the target change amount in the Markov state, the unit energy consumption of each computing task, and the scheduling direction of each scheduling task, wherein the power balance relationship represents the difference between the power consumed and the power generated in the edge node, the unit energy consumption represents the power consumed by the edge node to process a computing task, and the scheduling direction represents the direction of scheduling computing tasks or scheduling power between the edge node and other edge nodes in the edge device energy supply system;

[0213] A frequency deviation determination module is used to determine frequency deviation relationship data corresponding to the edge node based on the power balance relationship, inertia constant, second damping coefficient and AC bus frequency deviation in the edge node under the Markov state, wherein the frequency deviation relationship data indicates the influence of the power balance relationship, inertia constant and second damping coefficient on the change of AC bus frequency deviation;

[0214] The control parameter determination module 703 is used to determine the control parameters indicated by the control identifier corresponding to each edge node under multiple Markov states based on the first relationship data, the second relationship data and the third relationship data corresponding to multiple edge nodes in the edge device energy supply system under multiple Markov states, so that the AC bus frequency deviation in the edge node indicated by the frequency deviation relationship data corresponding to each edge node is less than a preset threshold.

[0215] In another possible implementation, the control parameter determination module 703 is used to:

[0216] Transforming the relationship data corresponding to the plurality of edge nodes under the plurality of Markov states to obtain fourth relationship data corresponding to the plurality of edge nodes under the plurality of Markov states, the fourth relationship data representing the relationship between the control identifier and the target operating parameter and the target variation;

[0217] Based on the target operating parameters, the target variation and the fourth relationship data corresponding to each edge node, the control parameters indicated by the control identifiers corresponding to each edge node under the multiple Markov states are determined.

[0218] In another possible implementation, the control parameter determination module 703 is used to:

[0219] By adopting the Lyapunov functional method, the first relation data, the second relation data and the third relation data corresponding to the multiple edge nodes under the multiple Markov states are deformed to obtain the linear matrix inequality corresponding to the multiple edge nodes under the multiple Markov states. The linear matrix inequality represents the satisfied relationship between the target operating parameters and the control identifiers when the AC bus frequency is stable in the multiple edge nodes.

[0220] The particle swarm optimization algorithm is used to solve the linear inequality and obtain the control parameters referred to by the control identifier corresponding to each edge node under various Markov states.

[0221] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0222] It should be noted that: the control device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the control device provided in the above embodiment and the control method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0223] Figure 8 This is a schematic diagram of the structure of another control device provided in an embodiment of the present application. The device is applied to an edge computing device in a target edge node for execution. The target edge node is any edge computing node in an edge device energy supply system. Figure 8 , the device comprises:

[0224] A control parameter acquisition module 801 is used to acquire a control parameter set corresponding to a target edge node, where the control parameter set includes control parameters corresponding to the target edge node under different Markov states;

[0225] A state determination module 802, configured to determine a current Markov state corresponding to the current operating parameters from a plurality of Markov states based on the current operating parameters of the target edge node and a plurality of Markov states of the energy supply system of the edge device;

[0226] The control module 803 is used to control the target edge node based on the control parameters in the current Markov state.

[0227] The device provided in the embodiment of the present application can control the target edge node during operation by determining the current Markov state of the target edge node and based on the control parameters corresponding to the current Markov state. Due to external random interference, the electric energy generated by the renewable energy power generation equipment in the target edge node will be random, and the electric energy consumed by the edge computing device in the target edge node to process the computing tasks will also be random. In the embodiment of the present application, the electric energy generated by the traditional power generation equipment in the target edge node and the electric energy consumed by the scheduling tasks performed by the target edge node are controlled by controlling the parameters, which can suppress the influence of external random interference on the change of electric energy in the target edge node, so that the electric energy consumed in the target edge node is balanced with the electric energy generated, thereby ensuring the stability of the AC bus frequency.

[0228] In a possible implementation, the device further includes:

[0229] A state switching module, used for determining a Markov state at a next moment based on a mode switching rate between a current Markov state and other Markov states among a plurality of Markov states;

[0230] The control module 803 is further configured to control the target edge node at the next moment based on the control parameters in the Markov state at the next moment.

[0231] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0232] It should be noted that the control device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the edge computing device is divided into different functional modules to complete all or part of the functions described above. In addition, the control device and the control method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0233] An embodiment of the present application further provides a computer device, which includes a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the control method of the above embodiment.

[0234] An embodiment of the present application also provides an edge computing device, which includes a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the control method of the above embodiment.

[0235] Optionally, the computer device or edge computing device is provided as a terminal. Fig. 9 It is a structural diagram of a terminal 900 provided in an embodiment of the present application.

[0236] The processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 901 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 901 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0237] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is used to store at least one computer program, which is used to be executed by the processor 901 to implement the control method provided in the method embodiment of the present application.

[0238] In some embodiments, the terminal 900 may further optionally include: a peripheral device interface 903 and at least one peripheral device. The processor 901, the memory 902 and the peripheral device interface 903 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 903 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 904, a display screen 905, a camera assembly 906, an audio circuit 907, a positioning assembly 908 and a power supply 909.

[0239] The peripheral device interface 903 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, the memory 902, and the peripheral device interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902, and the peripheral device interface 903 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0240] The radio frequency circuit 904 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 904 communicates with communication networks and other communication devices through electromagnetic signals. The radio frequency circuit 904 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 904 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 904 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 904 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0241] The display screen 905 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 905 is a touch display screen, the display screen 905 also has the ability to collect touch signals on the surface or above the surface of the display screen 905. The touch signal can be input to the processor 901 as a control signal for processing. At this time, the display screen 905 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 905 can be one, set on the front panel of the terminal 900; in other embodiments, the display screen 905 can be at least two, respectively set on different surfaces of the terminal 900 or in a folding design; in other embodiments, the display screen 905 can be a flexible display screen, set on the curved surface or folding surface of the terminal 900. Even, the display screen 905 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 905 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0242] The camera assembly 906 is used to capture images or videos. Optionally, the camera assembly 906 includes a front camera and a rear camera. The front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 906 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0243] The audio circuit 907 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 901 for processing, or input them into the radio frequency circuit 904 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 900. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 907 may also include a headphone jack.

[0244] The positioning component 908 is used to locate the current geographical location of the terminal 900 to implement navigation or LBS (Location Based Service).

[0245] The power supply 909 is used to power various components in the terminal 900. The power supply 909 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 909 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0246] In some embodiments, the terminal 900 further includes one or more sensors 910 . The one or more sensors 910 include, but are not limited to: an acceleration sensor 911 , a gyroscope sensor 912 , a pressure sensor 913 , an optical sensor 914 , and a proximity sensor 915 .

[0247] The acceleration sensor 911 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 900. For example, the acceleration sensor 911 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 901 can control the display screen 905 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 911. The acceleration sensor 911 can also be used to collect motion data of games or users.

[0248] The gyro sensor 912 can detect the body direction and rotation angle of the terminal 900, and the gyro sensor 912 can cooperate with the acceleration sensor 911 to collect the user's 3D actions on the terminal 900. The processor 901 can implement the following functions based on the data collected by the gyro sensor 912: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0249] The pressure sensor 913 can be set on the side frame of the terminal 900 and / or the lower layer of the display screen 905. When the pressure sensor 913 is set on the side frame of the terminal 900, it can detect the user's holding signal of the terminal 900, and the processor 901 performs left and right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 913. When the pressure sensor 913 is set on the lower layer of the display screen 905, the processor 901 controls the operability controls on the UI interface according to the user's pressure operation on the display screen 905. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0250] The optical sensor 914 is used to collect the ambient light intensity. In one embodiment, the processor 901 can control the display brightness of the display screen 905 according to the ambient light intensity collected by the optical sensor 914. Specifically, when the ambient light intensity is high, the display brightness of the display screen 905 is increased; when the ambient light intensity is low, the display brightness of the display screen 905 is reduced. In another embodiment, the processor 901 can also dynamically adjust the shooting parameters of the camera assembly 906 according to the ambient light intensity collected by the optical sensor 914.

[0251] The proximity sensor 915, also called a distance sensor, is disposed on the front panel of the terminal 900. The proximity sensor 915 is used to collect the distance between the user and the front of the terminal 900. In one embodiment, when the proximity sensor 915 detects that the distance between the user and the front of the terminal 900 is gradually decreasing, the processor 901 controls the display screen 905 to switch from the screen-on state to the screen-off state; when the proximity sensor 915 detects that the distance between the user and the front of the terminal 900 is gradually increasing, the processor 901 controls the display screen 905 to switch from the screen-off state to the screen-on state.

[0252] Those skilled in the art will understand that Fig. 9 The structure shown in the figure does not constitute a limitation on the terminal 900, and the terminal 900 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0253] Optionally, the computer device or edge computing device is provided as a server. Fig.10This is a schematic diagram of the structure of a server provided in an embodiment of the present application. The server 1000 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 1001 and one or more memories 1002, wherein the memory 1002 stores at least one computer program, and the at least one computer program is loaded and executed by the processor 1001 to implement the methods provided in the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the server may also include other components for implementing device functions, which will not be described in detail here.

[0254] An embodiment of the present application further provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is loaded and executed by a processor to implement the operations performed by the control method of the above embodiment.

[0255] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the operations performed by the control method of the above embodiment are implemented.

[0256] In some embodiments, the computer program involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.

[0257] It is understandable that in the specific implementation of this application, related data such as user information is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0258] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0259] The above are only optional embodiments of the embodiments of the present application and are not intended to limit the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A control method, characterized in that: The method comprises: Determine multiple Markov states of the edge device energy supply system; Based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system, the relationship data corresponding to each edge node in each Markov state is determined respectively, the target operating parameters indicate the operating state of the edge node, the target variation includes the variation of the amount of tasks performed by the edge node, the relationship data corresponding to the edge node indicates the influence of the target variation and the control identifier on the variation of the target variation when the target operating parameters remain unchanged, and the control parameter referred to by the control identifier is a parameter used to control the edge node; Based on the relationship data corresponding to the multiple edge nodes in the edge device energy supply system under the multiple Markov states, determine the control parameters referred to by the control identifier corresponding to each edge node under the multiple Markov states, and determine the control parameters corresponding to the same edge node under the multiple Markov states as the control parameter set corresponding to the same edge node; Sending a corresponding control parameter set to each edge node respectively, so that the edge node controls the operation of the edge node under different Markov states based on the received control parameter set; The target variation is a first variation, which refers to a variation of a first task amount executed in the edge node, and the first task amount changes with a change in a control parameter. The target operating parameter includes a first time constant and a control coefficient, and the first time constant indicates a response speed of the edge node to each first task, and the control coefficient indicates an influence of the control parameter on the first task amount. The determining of the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system includes: For each edge node, based on the first time constant, the first change amount and the control coefficient of the edge node in each Markov state, the first relationship data corresponding to the edge node in each Markov state is determined respectively, and the first relationship data in each Markov state indicates the influence of the first change amount, the control coefficient and the control identifier on the change of the first change amount when the first time constant remains unchanged.

2. The method according to claim 1, characterized in that The target variation is a second variation, the second variation refers to a variation of a second task amount performed by the edge node, the second task amount changes with a change in an interference parameter, the target operation parameter includes a second time constant and an interference parameter, the second time constant indicates a response speed of the edge node to each second task, and the interference parameter indicates an influence of the interference parameter on the second task amount; The step of determining the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system further includes: For each edge node, based on the second time constant, second change amount and interference parameter corresponding to the edge node under each Markov state, the second relationship data corresponding to the edge node under each Markov state is determined respectively, and the second relationship data indicates the influence of the second change amount and the interference parameter on the change of the second change amount when the second time constant remains unchanged.

3. The method according to claim 1, characterized in that The determining, based on the first time constant, the first change amount, and the control coefficient of the edge node in each Markov state, respectively corresponding to the first relationship data of the edge node in each Markov state includes: The first change is a scheduling task change, which refers to a change in the amount of computing tasks or electricity scheduled between the edge node and other edge nodes in the edge device energy supply system. Based on the first time constant, scheduling task change, control coefficient and delay duration of the edge node in each Markov state, the scheduling relationship data corresponding to the edge node in each Markov state are determined respectively, and the delay duration refers to the duration consumed in scheduling a computing task or unit of electric energy; or The first change is the first power change, which refers to the change in the power generation power of the traditional power generation equipment in the edge node. Based on the first time constant, the first power change and the control coefficient of the edge node in each Markov state, the first power relationship data corresponding to the edge node in each Markov state is determined respectively.

4. The method according to claim 2, characterized in that: The determining, based on the second time constant, the second variation, and the interference parameter corresponding to the edge node in each Markov state, the second relationship data corresponding to the edge node in each Markov state respectively includes: The second change is a load change, which refers to a change in the amount of computing tasks of the edge computing device in the edge node. Based on the second time constant, load change and interference parameter of the edge node in each Markov state, the load relationship data corresponding to the edge node in each Markov state are determined respectively; or The second change is the second power change, which refers to the change in the power generation power of the renewable energy power generation equipment in the edge node. Based on the second time constant, the second power change and the interference parameter of the edge node in each Markov state, the second power relationship data corresponding to the edge node in each Markov state is determined respectively.

5. The method according to claim 1, characterized in that The target variation is a third variation, the third variation is a variation of electric energy stored in the energy storage device in the edge node, the target operating parameter includes a third time constant and a first damping coefficient, the third time constant indicates a response speed of the edge node to the stored electric energy; The step of determining the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system further includes: For each edge node, based on the third time constant, the third change, the first damping coefficient and the AC bus frequency deviation of the edge node in each Markov state, the energy storage relationship data corresponding to the edge node in each Markov state is determined respectively, the energy storage relationship data represents the influence of the third change, the first damping coefficient and the AC bus frequency deviation on the change of the third change when the third time constant remains unchanged, and the AC bus frequency deviation indicates the value of the AC bus frequency in the edge node at at least one moment.

6. The method according to claim 5, characterized in that The target operating parameter further includes an inertia constant and a second damping coefficient, and the method further includes: For each Markov state in each edge node: Based on the target change amount under the Markov state, the unit energy consumption of each computing task, and the scheduling direction of each scheduling task, determine the power balance relationship in the edge node, the power balance relationship represents the difference between the power consumed and the power generated in the edge node, the unit energy consumption represents the power consumed by the edge node to process a computing task, and the scheduling direction represents the direction of scheduling computing tasks or scheduling power between the edge node and other edge nodes in the edge device energy supply system; Based on the power balance relationship, the inertia constant, the second damping coefficient and the AC bus frequency deviation in the edge node in the Markov state, determine the frequency deviation relationship data corresponding to the edge node, the frequency deviation relationship data indicating the influence of the power balance relationship, the inertia constant and the second damping coefficient on the change of the AC bus frequency deviation; The determining, based on the relationship data corresponding to the plurality of edge nodes in the edge device energy supply system under the plurality of Markov states, the control parameter referred to by the control identifier corresponding to each edge node under the plurality of Markov states comprises: Based on the first relationship data, the second relationship data and the third relationship data corresponding to the multiple edge nodes in the edge device energy supply system under the multiple Markov states, the control parameters indicated by the control identifier corresponding to each edge node under the multiple Markov states are determined so that the AC bus frequency deviation in the edge node indicated by the frequency deviation relationship data corresponding to each edge node is less than a preset threshold.

7. The method according to claim 1, characterized in that The determining, based on the relationship data corresponding to the plurality of edge nodes in the edge device energy supply system under the plurality of Markov states, the control parameter referred to by the control identifier corresponding to each edge node under the plurality of Markov states comprises: Transforming the relationship data corresponding to the plurality of edge nodes under the plurality of Markov states to obtain fourth relationship data corresponding to the plurality of edge nodes under the plurality of Markov states, the fourth relationship data representing the relationship between the control identifier and the target operating parameter and the target variation; Based on the target operating parameter corresponding to each edge node, the target change amount and the fourth relationship data, the control parameter indicated by the control identifier corresponding to each edge node under the multiple Markov states is determined.

8. The method according to claim 5, characterized in that The determining, based on the relationship data corresponding to the plurality of edge nodes in the edge device energy supply system under the plurality of Markov states, the control parameter referred to by the control identifier corresponding to each edge node under the plurality of Markov states comprises: Using a Lyapunov functional method, the first relationship data, the second relationship data, and the third relationship data corresponding to the plurality of edge nodes under the plurality of Markov states are deformed to obtain linear matrix inequalities corresponding to the plurality of edge nodes under the plurality of Markov states, wherein the linear matrix inequality represents a satisfied relationship between the target operating parameter and the control identifier when the AC bus frequency in the plurality of edge nodes is stable; The linear inequality is solved by using a particle swarm optimization algorithm to obtain control parameters indicated by control identifiers corresponding to each edge node under the multiple Markov states.

9. A control method, characterized in that: The method is performed by an edge computing device in a target edge node, and the target edge node is any edge computing node in an edge device energy supply system. The method includes: Acquire a control parameter set corresponding to the target edge node, wherein the control parameter set includes control parameters corresponding to the target edge node in different Markov states; Based on the current operating parameters of the target edge node and multiple Markov states of the edge device energy supply system, determine the current Markov state corresponding to the current operating parameters from the multiple Markov states; Based on the control parameters in the current Markov state, controlling the target edge node; Wherein, the control parameter set is obtained by any one of the control methods in claims 1 to 8.

10. The method according to claim 9, characterized in that The method further comprises: Determining a Markov state at a next moment based on a mode switching rate between the current Markov state and other Markov states among the multiple Markov states; At the next moment, the target edge node is controlled based on the control parameter in the Markov state at the next moment.

11. A control device, characterized in that: The device comprises: A state determination module, used to determine multiple Markov states of the edge device energy supply system; A relationship data determination module, for determining the relationship data corresponding to each edge node in each Markov state based on the target operating parameters and target variation of each edge node in each Markov state in the edge device energy supply system, wherein the target operating parameters indicate the operating state of the edge node, the target variation includes the variation of the amount of tasks performed by the edge node, and the relationship data corresponding to the edge node indicates the influence of the target variation and the control identifier on the variation of the target variation when the target operating parameters remain unchanged, and the control parameter referred to by the control identifier is a parameter for controlling the edge node; A control parameter determination module, configured to determine, based on the relationship data corresponding to the plurality of edge nodes in the edge device energy supply system under the plurality of Markov states, the control parameters referred to by the control identifier corresponding to each edge node under the plurality of Markov states, and determine the control parameters corresponding to the same edge node under the plurality of Markov states as a control parameter set corresponding to the same edge node; A control parameter sending module, used to send a corresponding control parameter set to each edge node respectively, so that the edge node controls the operation of the edge node under different Markov states based on the received control parameter set; Among them, the target change amount is the first change amount, the first change amount refers to the change amount of the first task amount executed in the edge node, the first task amount changes with the change of the control parameter, the target operating parameters include a first time constant and a control coefficient, the first time constant indicates the response speed of the edge node to each first task, the control coefficient indicates the influence of the control parameter on the first task amount, and the relationship data determination module is used to: for each edge node, based on the first time constant, the first change amount and the control coefficient of the edge node in each Markov state, respectively determine the first relationship data corresponding to the edge node in each Markov state, the first relationship data in each Markov state indicates the influence of the first change amount, the control coefficient and the control identifier on the change of the first change amount when the first time constant remains unchanged.

12. A control device, characterized in that: The device is applied to an edge computing device in a target edge node for execution, and the target edge node is any edge computing node in an edge device energy supply system, and the device includes: A control parameter acquisition module, used to acquire a control parameter set corresponding to the target edge node, wherein the control parameter set includes control parameters corresponding to the target edge node under different Markov states, wherein the control parameter set is acquired by the control device according to claim 11; A state determination module, configured to determine, based on the current operating parameters of the target edge node and the multiple Markov states of the edge device energy supply system, a current Markov state corresponding to the current operating parameters from the multiple Markov states; A control module is used to control the target edge node based on the control parameters in the current Markov state.

13. A computer device, characterized in that: The computer device includes a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the control method according to any one of claims 1 to 8.

14. An edge computing device, characterized in that: The edge computing device includes a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the operations performed by the control method according to any one of claims 9 to 10.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor to implement the operations performed by the control method as claimed in any one of claims 1 to 8, or to implement the operations performed by the control method as claimed in any one of claims 9 to 10.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the operations performed by the control method described in any one of claims 1 to 8, or implements the operations performed by the control method described in any one of claims 9 to 10.

Images