Electric energy scheduling method, device and system, storage medium and program product

Abstract

The invention provides an electric energy dispatching method, device and system, a storage medium and a program product, and relates to the technical field of electric power system dispatching. The method is applied to intelligent agents, the intelligent agents are independently deployed on all electric power nodes in an electric power system, and the electric energy dispatching method comprises the steps that power flow between the intelligent agents and direct connection intelligent agents is monitored, and if the power flow does not meet the electric energy flow intensity requirement, the direct connection intelligent agents corresponding to the power flow are determined as target intelligent agents; based on an ant colony algorithm, determining whether the target agent is an agent to be subjected to an electric energy adjustment strategy; if the target agent is the agent to execute the electric energy adjustment strategy, the target agent is triggered to execute the electric energy adjustment strategy, and the electric energy adjustment strategy comprises the step of controlling a target electric power node corresponding to the target agent to output first electric power according to current operation parameters of the target agent and operation parameters of adjacent agents, the effects of improving the electric energy dispatching efficiency, precision and flexibility are achieved, and the increasing electric power requirements and complex scenes are met.

Description

Technical Field

[0001] The present application relates to the technical field of power system dispatching, and in particular to an electric energy dispatching method, device, system, storage medium and program product. Background Art

[0002] In traditional power systems, power dispatching usually adopts a centralized management mode, with the central control system responsible for power monitoring and dispatching of the power grid. This approach often lacks flexibility and real-time response capabilities when faced with power load fluctuations and diverse user needs, leading to power quality problems such as voltage instability and frequency fluctuations. In addition, the centralized management model fails to fully utilize the potential of distributed energy and renewable energy, limiting the adaptability and efficiency of the power system.

[0003] Therefore, there is an urgent need for an effective power dispatching solution to improve the efficiency, accuracy and flexibility of dispatching to meet the growing electricity demand and complex scenarios. Summary of the invention

[0004] The present application provides an electric energy scheduling method, device, system, storage medium and program product to achieve the effect of improving scheduling efficiency, accuracy and flexibility.

[0005] In a first aspect, the present application provides an electric energy dispatching method, which is applied to an intelligent agent, and the intelligent agent is independently deployed on each power node in the power system. The electric energy dispatching method includes:

[0006] Monitor the power flow between directly connected agents. The power flow is used to reflect the intensity of the electric energy flow between agents.

[0007] If the power flow does not meet the requirements of the power flow intensity, the directly connected agent corresponding to the power flow is determined as the target agent;

[0008] Based on the ant colony algorithm, determine whether the target intelligent agent is an intelligent agent for which the power adjustment strategy is to be executed;

[0009] If the target intelligent agent is an intelligent agent to execute the power adjustment strategy, the target intelligent agent is triggered to execute the power adjustment strategy, and the power adjustment strategy includes controlling the target power node corresponding to the target intelligent agent to output the first power according to the current operating parameters of the target intelligent agent and the operating parameters of the adjacent intelligent agents.

[0010] In a possible implementation, based on the ant colony algorithm, determining whether the target agent is the target agent for the power adjustment strategy to be executed includes:

[0011] Based on the ant colony algorithm, determine whether the path to the target agent is the path with the highest selection probability;

[0012] If the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability, the target intelligent agent is determined as the target intelligent agent for executing the power adjustment strategy.

[0013] In a possible implementation, the electric energy scheduling method further includes:

[0014] If the agent is the target agent, the current operating parameters of the target agent and the operating parameters of the adjacent agents are weighted summed to obtain the updated operating parameters corresponding to the target agent;

[0015] Based on the mapping relationship between the operating parameters and the power, determining the first power corresponding to the updated operating parameters;

[0016] The target power node is controlled to output the first power.

[0017] In a possible implementation, the electric energy scheduling method further includes:

[0018] After controlling the target power node to output the first power, determining a power quality indicator of the target power node according to the first power, where the power quality indicator is used to measure the power output quality of the power node;

[0019] Sending a power quality indicator to an edge computing device, where the edge computing device is used to feedback a power dispatch instruction based on the power quality indicator, where the power dispatch instruction carries the power distribution amount to be adjusted;

[0020] receiving an electric energy dispatching instruction, and determining a second electric power corresponding to the electric power distribution amount to be adjusted based on a mapping relationship between the electric power distribution amount and the electric power;

[0021] The target power node is controlled to output the second power.

[0022] In one possible implementation, agents communicate with each other based on a message passing protocol;

[0023] And / or, each power node and edge computing device in the power system are deployed in the blockchain network.

[0024] In a second aspect, the present application provides an electric energy scheduling method, which is applied to an edge computing device. The electric energy scheduling method includes:

[0025] receiving a power quality indicator sent by an intelligent agent, the intelligent agent being independently deployed on a power node in the power system, the power quality indicator being determined according to a first power output by the power node, and the power quality indicator being used to measure the power output quality of the power node;

[0026] Determine the power distribution amount to be adjusted according to the power quality index and the preset power quality index;

[0027] According to the power distribution amount to be adjusted, an electric energy dispatching instruction is sent to the intelligent agent, the electric energy dispatching instruction carries the power distribution amount to be adjusted, and the intelligent agent is used to control the power node to output the second power according to the power distribution amount to be adjusted.

[0028] In a possible implementation manner, determining the power distribution amount to be adjusted according to the power quality indicator and the preset power quality indicator includes:

[0029] Based on the feedback control mechanism, a difference between the power quality indicator and the preset power quality indicator is integrated in the time domain, and multiplied by the integral gain to obtain a first intermediate value;

[0030] Differentiate the difference in time domain and multiply it by the differential gain to obtain a second intermediate value;

[0031] Multiply the difference by the proportional gain to obtain a third intermediate value;

[0032] The power distribution amount to be adjusted is determined according to the sum of the first intermediate value, the second intermediate value and the third intermediate value.

[0033] In one possible implementation, each power node and edge computing device in the power system are deployed in a blockchain network.

[0034] In a third aspect, the present application provides an electric energy dispatching device, which is applied to an intelligent agent, and the intelligent agent is independently deployed on each power node in the power system. The electric energy dispatching device includes:

[0035] A monitoring module is used to monitor the power flow between the directly connected intelligent agents. The power flow is used to reflect the intensity of the electric energy flow between the intelligent agents.

[0036] A first determination module is used to determine the directly connected intelligent agent corresponding to the power flow as the target intelligent agent when the power flow does not meet the power flow intensity requirement;

[0037] A second determination module is used to determine whether the target intelligent agent is an intelligent agent for which the power adjustment strategy is to be executed based on an ant colony algorithm;

[0038] The trigger module is used to trigger the target intelligent body to execute the power adjustment strategy when the target intelligent body is the intelligent body to execute the power adjustment strategy. The power adjustment strategy includes controlling the target power node corresponding to the target intelligent body to output the first power according to the current operating parameters of the target intelligent body and the operating parameters of the adjacent intelligent bodies.

[0039] In a possible implementation, the second determination module is specifically used to: determine whether the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability based on the ant colony algorithm; if the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability, determine the target intelligent agent as the target intelligent agent for the power adjustment strategy to be executed.

[0040] In one possible implementation, the second determination module is also used for: if the intelligent agent is a target intelligent agent, performing a weighted summation on the current operating parameters of the target intelligent agent and the operating parameters of the adjacent intelligent agents to obtain updated operating parameters corresponding to the target intelligent agent; based on the mapping relationship between the operating parameters and the power, determining the first power corresponding to the updated operating parameters; and controlling the target power node to output the first power.

[0041] In one possible implementation, the second determination module is also used to: after controlling the target power node to output the first power, determine the power quality index of the target power node based on the first power, the power quality index is used to measure the power output quality of the power node; send the power quality index to the edge computing device, the edge computing device is used to feedback the power scheduling instruction based on the power quality indicator, the power scheduling instruction carries the power distribution amount to be adjusted; receive the power scheduling instruction, and based on the mapping relationship between the power distribution amount and the power, determine the second power corresponding to the power distribution amount to be adjusted; control the target power node to output the second power.

[0042] In one possible implementation, intelligent agents communicate with each other based on a message passing protocol; and / or, each power node and edge computing device in the power system are deployed in a blockchain network.

[0043] In a fourth aspect, the present application provides an electric energy dispatching device, which is applied to an edge computing device. The electric energy dispatching device includes:

[0044] A receiving module, used for receiving a power quality index sent by an intelligent agent, the intelligent agent is independently deployed on a power node in the power system, the power quality index is determined according to the first power output by the power node, and the power quality index is used to measure the power output quality of the power node;

[0045] A determination module, used to determine the power distribution amount to be adjusted according to the power quality index and the preset power quality index;

[0046] The sending module is used to send an electric energy dispatching instruction to the intelligent body according to the electric energy distribution amount to be adjusted, the electric energy dispatching instruction carries the electric energy distribution amount to be adjusted, and the intelligent body is used to control the power node to output the second power according to the electric energy distribution amount to be adjusted.

[0047] In one possible implementation, the determination module is specifically used to: based on the feedback control mechanism, perform time domain integration on the difference between the power quality index and the preset power quality index, and multiply it by the integral gain to obtain a first intermediate value; perform time domain differentiation on the difference, and multiply it by the differential gain to obtain a second intermediate value; multiply the difference by the proportional gain to obtain a third intermediate value; and determine the power distribution amount to be adjusted based on the sum of the first intermediate value, the second intermediate value and the third intermediate value.

[0048] In one possible implementation, each power node and edge computing device in the power system are deployed in a blockchain network.

[0049] In a fifth aspect, the present application provides an intelligent agent, characterized in that it includes: a processor, and a memory communicatively connected to the processor;

[0050] Memory stores computer-executable instructions;

[0051] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0052] In a sixth aspect, the present application provides an edge computing device, comprising: a processor, and a memory communicatively connected to the processor;

[0053] Memory stores computer-executable instructions;

[0054] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above second aspect and / or various possible implementations of the second aspect.

[0055] In a seventh aspect, the present application provides an electric energy dispatching system, comprising:

[0056] The intelligent agent as described in the fifth aspect is deployed on each power node in the power system;

[0057] An edge computing device as described in the sixth aspect.

[0058] In an eighth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed, they are used to implement the first aspect and / or various possible implementation methods of the first aspect as described above, and / or, when the computer execution instructions are executed, they are used to implement the second aspect and / or various possible implementation methods of the second aspect as described above.

[0059] In a ninth aspect, the present application provides a computer program product, comprising a computer program, which, when executed, implements the first aspect above and / or various possible implementations of the first aspect, and / or, when executed, is used to implement the second aspect above and / or various possible implementations of the second aspect.

[0060] The electric energy dispatching method, device, system, storage medium and program product provided by the present application monitor the power flow between directly connected intelligent entities, determine the directly connected intelligent entity corresponding to the power flow that does not meet the requirements of the intensity of the electric energy flow as the target intelligent entity, and determine whether the target intelligent entity is an intelligent entity for which an electric energy adjustment strategy is to be executed based on the ant colony algorithm. When the target intelligent entity is an intelligent entity for which an electric energy adjustment strategy is to be executed, the target intelligent entity is triggered to execute the electric energy adjustment strategy, and the electric energy adjustment strategy includes controlling the target power node corresponding to the target intelligent entity to output the first power according to the current operating parameters of the target intelligent entity and the operating parameters of the adjacent intelligent entities. The present application accurately reflects the power transmission characteristics of the power nodes in the power grid by monitoring the power flow between directly connected intelligent entities, and facilitates the timely identification of the target intelligent entity that does not meet the requirements of power transmission. Further, based on the ant colony algorithm, the intelligent entity for which the electric energy adjustment strategy is to be executed is determined from the target intelligent entity, thereby improving the accuracy of the selection of the electric energy dispatching path, providing important support for effectively guiding the electric energy dispatching of various parts of the power grid, and making the dispatching more accurate and efficient. On this basis, intelligent agents share information and work together, so that the power output adjustment of power nodes depends on the operating parameters of the intelligent agent itself and the operating parameters of adjacent intelligent agents, ensuring the power balance between multiple power nodes. To a certain extent, it realizes the global optimization of power dispatch and improves the stability of power quality. In addition, distributed dispatch control based on intelligent agents not only improves the dispatch accuracy, but also provides flexibility and real-time response capabilities for the dynamic dispatch of power systems, better meeting the growing power demand and complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0062] Figure 1 A schematic diagram of a scenario of an electric energy dispatching method provided in an embodiment of the present application;

[0063] Figure 2 Schematic diagram of the process of the power dispatching method provided in the embodiment of the present application Figure 1 ;

[0064] Figure 3 Schematic diagram of the process of the power dispatching method provided in the embodiment of the present application Figure 2 ;

[0065] Figure 4 Schematic diagram of the process of the power dispatching method provided in the embodiment of the present application Figure 3 ;

[0066] Figure 5 A schematic diagram of the structure of the electric energy dispatching device provided in the embodiment of the present application Figure 1 ;

[0067] Figure 6 A schematic diagram of the structure of the electric energy dispatching device provided in the embodiment of the present application Figure 2 ;

[0068] Figure 7 A schematic diagram of the structure of an intelligent agent provided in an embodiment of the present application;

[0069] Figure 8 A schematic diagram of the structure of an edge computing device provided in an embodiment of the present application;

[0070] Fig. 9 A schematic diagram of the structure of the electric energy dispatching system provided in an embodiment of the present application.

[0071] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0072] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0073] In traditional power systems, the centralized management model lacks flexibility and real-time response capabilities. In addition, the centralized management model fails to fully utilize the potential of distributed energy and renewable energy, limiting the adaptability and efficiency of the power system.

[0074] In order to improve this situation, the concept of multi-agent system has emerged in recent years. Multi-agent system divides the power grid into multiple independent subsystems, each of which is composed of agents that can make autonomous decisions based on real-time data. This decentralized approach helps improve dispatch accuracy and enhances the system's ability to cope with dynamic changes, thereby effectively reducing power quality fluctuations.

[0075] However, the inventors found in their research that although multi-agent systems theoretically provide higher flexibility and response speed, they still face many challenges in practical applications, including collaboration between agents, information sharing, and optimization strategies for the overall system. Therefore, new algorithms and methods are urgently needed to further improve the efficiency and accuracy of power dispatching to meet the growing power demand and complex market environment.

[0076] In response to the above problems, the present application provides an electric energy dispatching method, which uses an ant colony algorithm to determine the agent to be executed from the target agent to adjust the electric energy strategy, improve the accuracy of the electric energy dispatching path selection, and make the power output adjustment of the power node depend on the operating parameters of the agent itself and the operating parameters of the adjacent agents through information sharing and collaborative work between agents, so as to ensure the power balance between multiple power nodes and achieve global optimization of electric energy dispatching. In this way, distributed dispatching control based on ant colony algorithm and agents is realized, providing higher accuracy, efficiency, flexibility and real-time response capability for the dynamic dispatching of power systems.

[0077] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0078] Figure 1 A schematic diagram of a scenario of an electric energy dispatching method provided in an embodiment of the present application, such as Figure 1 As shown, the power grid topology includes power generation nodes, load power nodes, energy storage power nodes and edge computing devices. An intelligent agent is independently deployed on each power node. The operating parameters, behaviors and decision-making rules of the intelligent agent are defined in advance, so that each intelligent agent can share information and collaborate with other intelligent agents while operating independently. These intelligent agents can perform autonomous data collection, analysis and decision-making to form a distributed multi-agent system. Each intelligent agent can be regarded as an entity with autonomous decision-making capabilities, and each intelligent agent can communicate with the edge computing device. Among them, the intelligent agents share information, pass their own state parameters to other adjacent intelligent agents, and the operating parameters of other adjacent intelligent agents to update and adjust their own operating parameters. The intelligent agent can specifically execute the power dispatching method proposed in this application to control the power output of the corresponding power node. The intelligent agent can monitor the power quality of the corresponding power node in real time, interact with the edge computing device, and perform feedback control on the power quality of the power node through the edge computing device.

[0079] It should be noted that the power grid topology is not limited to power nodes with power generation, load and energy storage functions, but may also include other types of power nodes. Figure 1This is only an example and does not limit the topology of the power grid. In addition, the number of various types of power nodes and edge computing devices is not limited. The deployment form of the intelligent agent can be software (such as intelligent components), or hardware (such as chip-level intelligent agents), or a combination of software and hardware. Its form depends on the specific application scenario and technical implementation method, which is not limited in this application. In addition, the edge computing device can be a high-performance, high-computing intelligent terminal, customized edge device, edge server, embedded industrial computer, etc., which is not limited in this application.

[0080] Figure 2 Schematic diagram of the process of the power dispatching method provided in the embodiment of the present application Figure 1 The power dispatching method provided in the embodiment of the present application is applied to an intelligent agent, and the intelligent agent is independently deployed on each power node in the power system. Figure 2 As shown, the electric energy scheduling method includes the following steps:

[0081] S201. Monitor the power flow between the directly connected intelligent entities, where the power flow is used to reflect the intensity of the electric energy flow between the intelligent entities.

[0082] For example, smart meters and sensors can be deployed on power nodes to monitor real-time parameters such as voltage, current, and power factor in real time. After the intelligent agent obtains the real-time parameters, it calculates the power flow based on the obtained real-time parameters to realize the monitoring of the power flow. Alternatively, the intelligent agent directly reads the power flow from a computing device, which is used to obtain real-time parameters from smart meters and sensors and calculate the power flow corresponding to the real-time parameters. For example, the power flow P between two power nodes (power node i and power node j) is determined by the voltage and impedance of the power node. ij , V i represents the voltage of power node i, V j represents the voltage of power node j, Z ij Represents the impedance between power nodes i and j:

[0083]

[0084] In the embodiment of the present application, the power flow also represents the power flow intensity from the current agent to the agent directly connected to the current agent, and also reflects the power flow distribution on the agent connection path. The directly connected agent can be understood as the neighboring agent of the current agent.

[0085] In a power grid, power flow calculation between power nodes helps balance the load of the power grid, optimize resource allocation, and avoid overload or power quality fluctuation when power flows in the power grid. It should be noted that the embodiment of the present application does not specifically limit the method for determining power flow.

[0086] S202: If the power flow does not meet the power flow intensity requirement, determine the directly connected intelligent agent corresponding to the power flow as the target intelligent agent.

[0087] Among them, the power flow intensity requirement is preset in each intelligent agent. The power flow intensity requirement can be set based on the stable operation requirements of the power system, the power quality requirements, etc. For different types of power nodes (ie, intelligent agents), the power flow intensity requirements are different.

[0088] For example, for power node i, the power nodes directly connected to it include power nodes j, m, and n, that is, i Directly connected agents include Agent A j , A m , A n , Agent A i , A j , A m , A n They can be agents of the same type or agents of different types. For example, the neighboring agents of a power generation agent can be load agents and energy storage agents, or other power generation agents.

[0089] When it is detected that the power flow does not meet the power flow intensity requirement, for example, i and A j , the power flow intensity requirement is 0.8, for agent A i and A m , the power flow intensity requirement is 0.9, for agent A i and A n , the power flow intensity requirement is 0.8, while the actual monitored power flow P ij is 0.7, P im is 0.95, P in is 0.65, then it is determined that agent A j and A n The power output of the node needs to be adjusted, that is, Agent A j and A n is the target agent.

[0090] S203: Based on the ant colony algorithm, determine whether the target intelligent agent is an intelligent agent for which the power adjustment strategy is to be executed.

[0091] The ant colony algorithm is a heuristic algorithm that aims to simulate the foraging behavior of ants in nature. It can find the optimal adjustment path from multiple paths. The optimal adjustment path will reflect the direction and method of power scheduling.

[0092] For example, based on S202, the ant colony algorithm will determine an optimal adjustment path from the path (i, j) and the path (i, n). Assuming that the path (i, j) is determined to be the optimal adjustment path, then agent j is the agent for executing the power adjustment strategy.

[0093] S204. If the target intelligent agent is an intelligent agent to execute the power adjustment strategy, the target intelligent agent is triggered to execute the power adjustment strategy, and the power adjustment strategy includes controlling the target power node corresponding to the target intelligent agent to output the first power according to the current operating parameters of the target intelligent agent and the operating parameters of the adjacent intelligent agents.

[0094] Among them, the operating parameters are related to the type of intelligent agent. Different types of intelligent agents may have different operating parameters. For example, the operating parameters are not limited to the power output of the power generation node, the power demand of the load node, or the charging and discharging status of the energy storage node.

[0095] Accordingly, different operating parameters determine the behavior of the agent, that is, the operations that the agent can perform, such as load regulation, power distribution, energy storage control, etc.

[0096] For example, when determining the target agent A j After becoming the agent to be executed the power adjustment strategy, agent i can send j Send power adjustment instructions to trigger target agent A j Execute the power adjustment strategy corresponding to its operating parameters. j In response to the power adjustment instruction, according to its own latest operating parameters, it controls the target power node where it is located to output the first power that matches its own latest operating parameters, so that the power flow distribution on the path (i, j) meets the power flow intensity requirements, that is, optimizes the power quality of the target power node.

[0097] It should be noted that the intelligent agent will send its own operating parameters to the adjacent intelligent agents in real time or periodically. At the same time, it will also update its own operating parameters according to its current operating parameters and the operating parameters received from the adjacent intelligent agents to obtain the latest operating parameters.

[0098] In the embodiment of the present application, independent intelligent agents are deployed on each power node to realize distributed control and decision-making in a complex power environment, which not only improves the dispatching accuracy, but also provides flexibility and real-time response capabilities for the dynamic dispatching of the power system. By monitoring the power flow between directly connected intelligent agents, the power transmission characteristics of the power nodes in the power grid are accurately reflected, which facilitates the timely identification of target intelligent agents that do not meet the power transmission requirements. Further based on the ant colony algorithm, the power dispatching path is optimized to provide important support for effectively guiding the power dispatching of various parts of the power grid, making the dispatching more accurate and efficient. On this basis, information is shared and worked together between intelligent agents, so that the power output adjustment of the power node depends on the operating parameters of the intelligent agent itself and the operating parameters of the adjacent intelligent agents, ensuring the power balance between multiple power nodes. To a certain extent, the global optimization of power dispatching is achieved and the stability of power quality is improved.

[0099] In some embodiments, based on the ant colony algorithm, determining whether the target intelligent agent is the target intelligent agent of the power adjustment strategy to be executed includes: based on the ant colony algorithm, determining whether the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability; if the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability, determining that the target intelligent agent is the target intelligent agent of the power adjustment strategy to be executed.

[0100] The ant colony algorithm can select the optimal path through the path selection probability to perform power scheduling and optimize power quality.

[0101] For example, by initializing pheromone concentration, path selection strategy, dynamically adjusting pheromone and defining path selection probability and heuristic function, effective scheduling of power quality can be achieved. This algorithm aims to simulate the foraging behavior of ants in nature, so that adaptive and optimized power adjustment strategy can be implemented in the power system.

[0102] First, the initial pheromone concentration of all paths is set, usually set to a small constant τ 0 The pheromone concentration represents the traces left by the ants on the path, and the initial setting can be expressed as:

[0103]

[0104] in, represents the initial pheromone concentration on path (i, j).

[0105] In this embodiment, ants will schedule the power quality according to the path selection probability. The formula of the pheromone update mechanism is as follows:

[0106]

[0107] in, represents the pheromone concentration of path (i, j) after the kth iteration, is the current pheromone concentration of path (i, j), ρ is the pheromone volatility coefficient, It is a new pheromone added in this iteration.

[0108] In this embodiment, the pheromone concentration is dynamically adjusted to reflect the quality of the path. After the ant completes the path, the corresponding new pheromone will be added according to the path quality (such as the degree of improvement of the power quality index). For example, for the traversed path (i, j), if the quality improvement effect of the path is significant, the added pheromone can be expressed as:

[0109]

[0110] Among them, Q is a constant and L is the path length or cost, indicating the "cost" of the ant on the path.

[0111] In this embodiment, the path selection probability is calculated by the following formula:

[0112]

[0113] in, is the probability of selecting path (i,j), is the current pheromone concentration of path (i, j), η ij is the heuristic function, N k is the set of adjacent nodes (agents) of the current node (agent). The heuristic function is defined as:

[0114]

[0115] Among them, d ij Represents the distance of path (i, j), which is usually inversely proportional to the distance of the path. By defining such a heuristic function, ants can be guided to choose paths with shorter distances and higher pheromone concentrations, thereby optimizing power quality scheduling.

[0116] In summary, the ant colony algorithm will give priority to paths with shorter distances and higher pheromone concentrations as the optimal power adjustment paths with a greater probability, and release a certain amount of pheromones to enhance the pheromone concentration on the path, thereby forming a positive feedback so that these paths can be more likely to be selected in the next iteration. The optimal power adjustment path is determined, which means the target agent for the power adjustment strategy to be executed is determined.

[0117] In the embodiment of the present application, the ant colony algorithm searches for the optimal power adjustment path according to the path selection probability by dynamically updating pheromones, thereby providing important support for effectively guiding the power dispatching of various parts of the power grid, making the dispatching more flexible, accurate and efficient.

[0118] In some embodiments, the electric energy scheduling method also includes: if the intelligent agent is a target intelligent agent, performing weighted summation on the current operating parameters of the target intelligent agent and the operating parameters of adjacent intelligent agents to obtain updated operating parameters corresponding to the target intelligent agent; based on the mapping relationship between the operating parameters and the power, determining the first power corresponding to the updated operating parameters; and controlling the target power node to output the first power.

[0119] Among them, each intelligent agent plays a role of distributed control in the power system, and can make decisions based on its own local information and information shared with other intelligent agents, and collaboratively complete the overall power dispatch task.

[0120] For example, agent A i The decision rule can be expressed as: i =f(S i ,I j )(j∈N i ), where S i Represents agent A i The current operating parameters, I j represents the information input from neighboring agents, N i For Agent A i The set of neighbors.

[0121] Through this decision rule, each agent can make decisions on power dispatching autonomously based on its operating parameters and the operating parameters received from neighboring agents.

[0122] Furthermore, standard protocols are used to achieve information sharing between agents. The information sharing mechanism between agents can be expressed as: Information sharing Update. Specifically, each agent periodically or according to a specific event trigger, transmits its own operating parameters to other neighboring agents. For the state parameters of the neighboring agents received, the agent uses the weighted summation method to integrate the information to update and adjust its own operating parameters to obtain the updated operating parameters. The updated operating parameters satisfy the following formula:

[0123]

[0124] Among them, S i ′ represents the target agent A i The updated operating parameters, S i represents the current operating parameters of the target agent, S j represents the operating parameters of the neighboring agents, N i represents the neighbor set of the target agent, α and β j is the weight coefficient. It should be noted that in actual application scenarios, α and β j It can be determined according to actual business needs to meet That is, the embodiment of the present application is for α and β j There is no limit on the specific value of .

[0125] Through this formula, each agent can adjust its own operating parameters according to the operating parameters of its neighbors. Through the information sharing and integration mechanism, the agents work together to update their own power output in the power grid and achieve power quality optimization. It can be understood that when controlling the power output of the power node, the agent combines the operating parameters of the adjacent agents and performs weighted summation to ensure the stability and efficiency of the power quality. For example, when there is a problem with the power quality of a power node (such as low voltage or excessive load), the agent of the power node can adjust the power output by integrating information with neighboring agents (i.e., weighted summation) to achieve the global optimization goal.

[0126] The operating parameters of an agent usually have a specific corresponding relationship with the power output of the power node corresponding to the agent. If the updated operating parameters of the target agent are known, the first power matching the updated operating parameters can be determined, and then the target power node can be controlled to output the first power. For example, if the target agent is a wind power generation agent, and its updated operating parameters are an output power of 250kw, then the wind power generation agent controls the corresponding wind power generation node to output 250kw of power.

[0127] In the embodiment of the present application, by performing weighted summation on the current operating parameters of the intelligent agent and the operating parameters of the adjacent intelligent agents, the intelligent agent can take into account the global grid status information (operating parameters), that is, the flow of electricity between the intelligent agents, when adjusting the power output of the power node, thereby achieving local optimization and global collaboration, improving the accuracy of power dispatch, and ensuring the power balance of the power grid between multiple nodes.

[0128] To ensure that the electric energy dispatching system can better and more promptly respond to abnormal situations such as dynamic load changes, equipment failures, etc. of the power system, in some embodiments, the electric energy dispatching method also includes: after controlling the target power node to output the first power, determining the power quality index of the target power node based on the first power, the power quality index is used to measure the power output quality of the power node; sending the power quality index to the edge computing device, the edge computing device is used to feedback the electric energy dispatching instruction based on the power quality index, the electric energy dispatching instruction carries the power distribution amount to be adjusted; receiving the electric energy dispatching instruction, and determining the second power corresponding to the power distribution amount to be adjusted based on the mapping relationship between the power distribution amount and the power; controlling the target power node to output the second power.

[0129] Among them, the power quality index is used to measure the power output quality of the power node. The intelligent agent monitors the power output of the power node, and the power quality index corresponding to the power output can be calculated through the power output data. Power quality indicators include voltage deviation, frequency deviation, harmonic content, etc. These indicators can be used as key reference data for subsequent scheduling optimization.

[0130] The intelligent agent interacts with the edge computing device. The edge computing device collects the power quality indicators reported by the intelligent agent, dynamically adjusts the power distribution amount according to the received power quality indicators, generates a power dispatch instruction carrying the power distribution amount to be adjusted, and feeds it back to the intelligent agent. For example, when the voltage fluctuation or frequency deviation of the target power node occurs, the power quality indicator monitored by the target intelligent agent changes abnormally. After receiving the power quality indicator, the edge computing device feeds back the power dispatch instruction. The target intelligent agent controls the target power node to output a second power that matches the power distribution amount to be adjusted according to the power distribution amount to be adjusted carried in the power dispatch instruction, so as to meet the power quality requirements.

[0131] The embodiment of the present application utilizes the power quality indicators collected in real time by edge computing devices to dynamically adjust the power output in response to load changes and emergencies in the power system, thereby achieving real-time monitoring and optimization control of power quality, thereby ensuring the stability of power quality. In addition, the application of edge computing enables data processing to be performed close to the data source, improving the real-time performance and response speed of data processing.

[0132] In some embodiments, intelligent agents communicate based on a message passing protocol; and / or, each power node and edge computing device in the power system are deployed in a blockchain network.

[0133] In one implementation, intelligent agents communicate based on a message passing protocol, and each power node and edge computing device in the power system are deployed in a blockchain network.

[0134] Among them, the messaging protocol is the core mechanism for achieving distributed collaboration. Different from the traditional centralized communication mode, message-based asynchronous communication can support loose coupling and high-concurrency interactions between agents. The messaging protocol can be, for example, the Message Queuing Telemetry Transport (MQTT) protocol, the Constrained Application Protocol (CoAP), or more efficient protocols such as the Zero Message Queue (ZeroMQ) protocol, the NATS protocol, etc. It should be noted that through the reasonable design of the messaging protocol, the agent system can achieve efficient, secure, and low-latency collaboration.

[0135] To further improve the security, transparency and decentralized operation of the system, blockchain can provide tamper-proof records and automatic execution of smart contracts. Deploying each node in the power system (generation, transmission, distribution, and consumption) and edge computing devices in the blockchain network can build a decentralized, transparent and secure energy management and trading system.

[0136] Blockchain technology can realize transaction verification, data storage and consensus mechanism between nodes, and define transaction rules, participant roles and execution conditions in smart contracts. At the same time, blockchain technology is used to ensure the transparency and immutability of transaction data, and to achieve efficient management of power transactions.

[0137] In another implementation, agents communicate with each other based on a message passing protocol.

[0138] In another implementation, each power node and edge computing device in the power system are deployed in the blockchain network.

[0139] It should be noted that in actual applications, the communication protocol between intelligent agents and the form of environmental deployment can be determined according to specific needs, and this application does not make specific limitations on this.

[0140] Figure 3 Schematic diagram of the process of the power dispatching method provided in the embodiment of the present application Figure 2 , the power scheduling method provided in the embodiment of the present application is applied to edge computing devices, such as Figure 3 As shown, the electric energy dispatching method includes:

[0141] S301. Receive a power quality indicator sent by an intelligent agent, where the intelligent agent is independently deployed on a power node in a power system. The power quality indicator is determined based on a first power output by the power node, and the power quality indicator is used to measure the power output quality of the power node.

[0142] The intelligent agent interacts with the edge computing device, and the edge computing device receives the power quality indicators reported by the intelligent agent. The power quality indicators include voltage deviation (V), frequency deviation (f), total harmonic distortion (THD), etc.

[0143] S302: Determine the power distribution amount to be adjusted according to the power quality index and the preset power quality index.

[0144] The edge computing device has built-in preset power quality indicators and the required range of power quality indicators. For example, the voltage range should be kept within V min ≤V≤V max The frequency range should be kept between f min ≤f≤f max, and the total harmonic distortion THD is set to not exceed the maximum allowable value THD max .

[0145] When the edge computing device detects that the power quality index does not meet the required range of the power quality index, for example, when it detects that the intelligent agent A i The power quality index is 50v, which is lower than V min =100v, at this time, the power distribution amount to be adjusted will be determined according to the power quality index and the preset power quality index, and the power dispatch instruction will be sent to the intelligent agent to control the power quality index of the power node to meet the requirements.

[0146] S303. Send an electric energy dispatching instruction to the intelligent agent according to the electric energy distribution amount to be adjusted, wherein the electric energy dispatching instruction carries the electric energy distribution amount to be adjusted, and the intelligent agent is used to control the power node to output the second electric power according to the electric energy distribution amount to be adjusted.

[0147] Furthermore, in some embodiments, the power distribution amount to be adjusted is determined based on the power quality index and the preset power quality index, including: based on the feedback control mechanism, integrating the difference between the power quality index and the preset power quality index in time domain, and multiplying it by the integral gain to obtain a first intermediate value; differentiating the difference in time domain, and multiplying it by the differential gain to obtain a second intermediate value; multiplying the difference by the proportional gain to obtain a third intermediate value; and determining the power distribution amount to be adjusted based on the sum of the first intermediate value, the second intermediate value and the third intermediate value.

[0148] For example, the power distribution amount to be adjusted may satisfy the following formula (feedback control equation):

[0149]

[0150] Where u(t) represents the power distribution to be adjusted, e(t) is the current error, and the current error is defined as the difference between the target power quality index and the power quality index, K p Represents proportional gain, K m Indicates the integral gain, K d Represents the differential gain. K p , K m and K d Used to adjust the response characteristics of the controller.

[0151] Proportional gain K p : Used to adjust the control output to be proportional to the current error, affecting the transient response of the system.

[0152] Integral gain K i : Used to eliminate steady-state errors and enhance the system's response to long-term deviations.

[0153] Differential gain Kd : Used to predict future error changes and improve the dynamic response of the system.

[0154] It should be noted that in practical applications, K can be obtained by trial and error, Ziegler-Nichols method, etc. p , K m and K d Adjust to the appropriate value so that the system can achieve both fast response and stable effect.

[0155] By calculating the error e(t) in real time and applying it to the feedback control equation, the edge computing device can quickly adjust the power distribution strategy to ensure that the power quality is always within the preset target range.

[0156] In the embodiment of the present application, the power dispatch strategy is dynamically adjusted through feedback through real-time power quality data, ensuring that the power system can quickly recover stability in the face of load fluctuations and sudden failures, and ensuring that the system can maintain stable power quality in different scenarios. In addition, by implementing data processing and dynamically adjusting the power distribution strategy on edge devices, real-time monitoring and optimized control of power quality are achieved. The application of edge computing enables data processing to be performed close to the data source, improving the real-time performance and response speed of data processing.

[0157] In one possible implementation, each power node and edge computing device in the power system are deployed in a blockchain network.

[0158] In summary, this application has at least the following advantages:

[0159] First, by deploying independent intelligent agents at each power node, distributed control and decision-making can be achieved in a complex power environment, which not only improves the dispatching accuracy, but also provides flexibility and real-time response capabilities for the dynamic dispatching of the power system. By monitoring the power flow between directly connected intelligent agents, the power transmission characteristics of the power nodes in the power grid are accurately reflected, which facilitates the timely identification of target intelligent agents that do not meet the power transmission requirements. Further based on the ant colony algorithm, the power dispatching path is optimized to provide important support for effectively guiding the power dispatching of various parts of the power grid, making the dispatching more accurate and efficient. On this basis, the intelligent agents share information and work together, so that the power output adjustment of the power node depends on the operating parameters of the intelligent agent itself and the operating parameters of the adjacent intelligent agents, ensuring the power balance between multiple power nodes. To a certain extent, the global optimization of power dispatching is achieved and the stability of power quality is improved.

[0160] Second, use the power quality indicators collected in real time by edge computing devices to dynamically adjust the power dispatch strategy, realize real-time monitoring and optimization control of power quality, ensure that the power system can quickly restore stability in the face of load fluctuations and sudden failures, and ensure that the system can maintain stable power quality in different scenarios. In addition, the application of edge computing enables data processing to be carried out close to the data source, improving the real-time and response speed of data processing.

[0161] 3. Agents communicate with each other through message passing protocols, enabling multi-agent systems to achieve efficient, secure, and low-latency collaboration.

[0162] 4. Use blockchain technology to ensure the transparency and immutability of transaction data in the electric energy dispatching system, achieve efficient management of electric energy transactions, and improve the security of the system.

[0163] Next, based on the above embodiments, the electric energy dispatching method is described in detail through a specific embodiment.

[0164] Figure 4 Schematic diagram of the process of the power dispatching method provided in the embodiment of the present application Figure 3 The electric energy dispatching method can be implemented based on simulation. This embodiment will be described from the perspective of environmental modeling and simulation. Figure 4 As shown, the electric energy scheduling method provided in this embodiment includes:

[0165] S401, Environmental modeling, including grid topology modeling and power quality index definition.

[0166] By analyzing the structure of each power generation node, transmission line, load node and energy storage node in the power system, a graphical model of the power grid is constructed. At the same time, power quality indicators are defined, including voltage fluctuation, frequency deviation, harmonic content, etc. These indicators will serve as key reference data for subsequent scheduling optimization.

[0167] For example, the environment modeling may further include the following steps:

[0168] S4011. Construct a power grid model, including a node set V and an edge set E.

[0169] The node set V represents the power generation nodes, load nodes and energy storage nodes in the power grid, and the edge set E represents the transmission lines connecting these nodes. The power grid topology can be represented as G(V,E), where each edge e ij Connect two nodes v i and v j .

[0170] S4012, define the properties of the edge, and Z ij and power flow Pij The calculation formula for .

[0171] The attributes of the edge reflect the connection characteristics between nodes. The attributes of the edge mainly include the impedance Z between two nodes. ij and power flow P ij ,The power flow describes the power flow distribution between two nodes and reflects the ,power transmission characteristics between different nodes in the power grid.

[0172] S4013. Determine the target range of power quality indicators, including voltage, frequency and total harmonic distortion.

[0173] For example, the power quality indicators include voltage deviation (V), frequency deviation (f), and total harmonic distortion (THD). The voltage range should be kept within V min ≤V≤V max The frequency range should be kept between f min ≤f≤f max , and the total harmonic distortion THD is set to not exceed the maximum allowable value THD max .

[0174] S402. Multi-agent design, including agent model construction and information sharing mechanism.

[0175] Deploy independent intelligent agents for each subsystem in the smart grid to achieve distributed control and decision-making in a complex power environment. By defining the state (i.e., the operating parameters in the above embodiment), behavior, and decision-making rules of the intelligent agent, each intelligent agent can share information and operate collaboratively with other intelligent agents while operating independently. In addition, a standard information sharing protocol is established to ensure information exchange and integration between intelligent agents in the system.

[0176] For example, the multi-agent design may further include the following steps:

[0177] S4021. Deployment of independent agent A i For each subsystem, define its state S i Behavior B i and decision rule R i .

[0178] Status S i : Indicates the current operating parameters of the intelligent agent, such as the power output of the power generation node, the power demand of the load power node, or the charging and discharging status of the energy storage power node.

[0179] Behavior B i : The operations that the agent can perform in different states, such as load regulation, power distribution, energy storage control, etc.

[0180] Decision Rule R i: The decision made by the agent based on the information received and its own state:

[0181]

[0182] Among them, S i ′ represents the target agent A i The updated operating parameters, S i represents the current operating parameters of the target agent, S j represents the operating parameters of the neighboring agents, N i represents the neighbor set of the target agent, α and β j is the weight coefficient.

[0183] S4022. Realize information sharing and integration among intelligent agents through standard protocols.

[0184] Intelligent agents communicate with each other based on the messaging protocol, which can be, for example, the Message Queuing Telemetry Transport (MQTT) protocol, the Constrained Application Protocol (CoAP) protocol, or more efficient ones such as the Zero Message Queue (ZeroMQ) protocol, the NATS protocol, etc.

[0185] S403, Ant colony algorithm design, including algorithm process design, pheromone update mechanism, path selection and heuristic strategy.

[0186] The implementation here is the same as that described in the previous embodiment (such as formulas (1) to (5)), and will not be repeated here.

[0187] S404, edge computing and adaptive control, including edge computing architecture and feedback control mechanism.

[0188] Distribute edge computing resources close to data sources (power nodes) to reduce latency and improve real-time performance, so that scheduling strategies can be adjusted in time to cope with load changes and equipment status fluctuations.

[0189] Data processing is performed on edge computing devices to obtain power quality indicators on the intelligent agent in real time. Power dispatch instructions are fed back to the intelligent agent based on the power quality indicators, and the power dispatch instructions carry the power distribution amount to be adjusted.

[0190] The power distribution to be adjusted can satisfy the following formula (feedback control equation):

[0191]

[0192] Where u(t) represents the power distribution to be adjusted, e(t) is the current error, and the current error is defined as the difference between the target power quality index and the power quality index, K p Represents proportional gain, K m Indicates the integral gain, K d Represents the differential gain.

[0193] S405. Integration of smart contracts and blockchain, including smart contract design and data storage and access.

[0194] S406, system integration and simulation, including simulation environment construction and performance evaluation.

[0195] For example, a simulation platform is built using MATLAB / Simulink and blockchain simulation tools, and power quality, dispatch efficiency, and emergency response capabilities are evaluated through multi-scenario testing.

[0196] Specifically, they may include:

[0197] S4061. Construction and simulation of power grid model: Use MATLAB / Simulink to build a physical model of the power grid, establish the topology of power generation nodes, transmission lines, load power nodes and energy storage power nodes, and simulate the dynamic behavior of the power grid.

[0198] For example, the electrical system module provided in the Simulink platform is used to define the electrical characteristics and operating parameters of each unit and simulate the dynamic behavior of the power grid. The construction of the power grid model should cover actual scenarios such as power flow under different working conditions, equipment load changes, renewable energy access, and emergency events (such as power generation unit failure, load surge, etc.).

[0199] S4062, Integration of intelligent scheduling algorithms: Write and integrate the ant colony algorithm in the Simulink platform for the optimization of power scheduling, define the algorithm's path selection and pheromone concentration update.

[0200] S4063. Configuration of blockchain simulation tools: Use blockchain simulation tools to configure the blockchain network, define node roles, and establish transaction verification, data storage, and consensus mechanisms between nodes.

[0201] Use blockchain simulation tools to configure the blockchain network, set up network nodes, and assign corresponding roles to each node (such as data verification node, transaction execution node, and data storage node, etc.). Configure the blockchain's consensus mechanism (such as PoW, PoS, or DPoS, etc.) and data storage mechanism to ensure the authenticity of transactions and the security of data.

[0202] S4064, data interface and integration platform construction: design data interface to realize data transmission between MATLAB / Simulink and blockchain simulation tools, and transmit power quality data, transaction information and scheduling results.

[0203] The main functions of the data interface include transmitting power quality data, transaction information and dispatch results in the simulation platform. The integrated platform obtains real-time data in the simulation platform through the interface, and transmits the dispatch results to the blockchain network for verification and recording, forming a closed-loop power dispatch system.

[0204] Finally, the simulation platform was run to test different design scenarios, collect simulation data, and calculate and analyze various indicators of power quality, dispatch efficiency (response time, power distribution balance, strategy execution success rate, etc.) and emergency response capability (time from fault occurrence to restoration of normal state, adjustment frequency, etc.). The statistical analysis tools in MATLAB were used to generate relevant charts (such as voltage fluctuation curves, response time histograms, etc.) to compare performance under different scenarios and strategies.

[0205] S407, summary and optimization, including system effect evaluation and continuous optimization.

[0206] Analyze the test results and evaluate the coordination effect of the dispatch algorithm and blockchain network, including the improvement of power quality, the improvement of dispatch efficiency and the emergency response capability of the system. Find problems based on the data results, propose improvement plans, and further adjust the simulation model, dispatch algorithm and blockchain configuration to ensure the continuous improvement and efficient operation of the power dispatch system.

[0207] Figure 5 A schematic diagram of the structure of the electric energy dispatching device provided in the embodiment of the present application Figure 1 ,like Figure 5 As shown, the electric energy dispatching device provided in this embodiment is applied to an intelligent agent, and the intelligent agent is independently deployed on each power node in the power system. The electric energy dispatching device 50 includes a monitoring module 51, a first determination module 52, a second determination module 53 and a trigger module 54. Among them:

[0208] A monitoring module 51 is used to monitor the power flow between the directly connected intelligent bodies, and the power flow is used to reflect the intensity of the electric energy flow between the intelligent bodies;

[0209] A first determination module 52, configured to determine the directly connected agent corresponding to the power flow as the target agent when the power flow does not meet the power flow intensity requirement;

[0210] A second determination module 53 is used to determine whether the target agent is an agent for which a power adjustment strategy is to be executed based on an ant colony algorithm;

[0211] The trigger module 54 is used to trigger the target intelligent body to execute the power adjustment strategy when the target intelligent body is an intelligent body to execute the power adjustment strategy. The power adjustment strategy includes controlling the target power node corresponding to the target intelligent body to output the first power according to the current operating parameters of the target intelligent body and the operating parameters of the adjacent intelligent bodies.

[0212] In a possible implementation, the second determination module 53 is specifically used to: determine whether the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability based on the ant colony algorithm; if the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability, determine the target intelligent agent as the target intelligent agent for the power adjustment strategy to be executed.

[0213] In a possible implementation, the second determination module 53 is also used for: if the intelligent agent is a target intelligent agent, performing a weighted summation on the current operating parameters of the target intelligent agent and the operating parameters of the adjacent intelligent agents to obtain updated operating parameters corresponding to the target intelligent agent; based on the mapping relationship between the operating parameters and the power, determining the first power corresponding to the updated operating parameters; and controlling the target power node to output the first power.

[0214] In one possible implementation, the second determination module 53 is also used to: after controlling the target power node to output the first power, determine the power quality index of the target power node based on the first power, the power quality index is used to measure the power output quality of the power node; send the power quality index to the edge computing device, the edge computing device is used to feedback the power scheduling instruction based on the power quality indicator, the power scheduling instruction carries the power distribution amount to be adjusted; receive the power scheduling instruction, and based on the mapping relationship between the power distribution amount and the power, determine the second power corresponding to the power distribution amount to be adjusted; control the target power node to output the second power.

[0215] In one possible implementation, intelligent agents communicate with each other based on a message passing protocol; and / or, each power node and edge computing device in the power system are deployed in a blockchain network.

[0216] The electric energy dispatching device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0217] Figure 6 A schematic diagram of the structure of the electric energy dispatching device provided in the embodiment of the present application Figure 2 ,like Figure 6 As shown, the power scheduling device provided in this embodiment is applied to edge computing equipment, and the power scheduling device 60 includes a receiving module 61, a determining module 62 and a sending module 63. Among them:

[0218] A receiving module 61 is used to receive a power quality indicator sent by an intelligent agent, the intelligent agent is independently deployed on a power node in the power system, the power quality indicator is determined according to the first power output by the power node, and the power quality indicator is used to measure the power output quality of the power node;

[0219] A determination module 62, configured to determine the power distribution amount to be adjusted according to the power quality indicator and the preset power quality indicator;

[0220] The sending module 63 is used to send an electric energy dispatching instruction to the intelligent agent according to the electric energy distribution amount to be adjusted. The electric energy dispatching instruction carries the electric energy distribution amount to be adjusted. The intelligent agent is used to control the power node to output the second power according to the electric energy distribution amount to be adjusted.

[0221] In one possible implementation, the determination module 62 is specifically used to: based on the feedback control mechanism, perform time domain integration on the difference between the power quality index and the preset power quality index, and multiply it by the integral gain to obtain a first intermediate value; perform time domain differentiation on the difference, and multiply it by the differential gain to obtain a second intermediate value; multiply the difference by the proportional gain to obtain a third intermediate value; and determine the power distribution amount to be adjusted based on the sum of the first intermediate value, the second intermediate value and the third intermediate value.

[0222] In one possible implementation, each power node and edge computing device in the power system are deployed in a blockchain network.

[0223] The electric energy dispatching device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0224] Figure 7 This is a schematic diagram of the structure of the intelligent agent provided in the embodiment of the present application. Figure 7 As shown, the agent 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the agent 70 also includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus 704.

[0225] In a specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that at least one processor 701 executes the above method.

[0226] The specific implementation process of the processor 701 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0227] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0228] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0229] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0230] Figure 8 A schematic diagram of the structure of the edge computing device provided in the embodiment of the present application, such as Figure 8 As shown, the edge computing device 80 provided in this embodiment includes: at least one processor 801 and a memory 802. Optionally, the agent 80 also includes a communication component 803. The processor 801, the memory 802 and the communication component 803 are connected via a bus 804.

[0231] In a specific implementation process, at least one processor 801 executes the computer-executable instructions stored in the memory 802, so that at least one processor 801 executes the above method.

[0232] The specific implementation process of the processor 801 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0233] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0234] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0235] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0236] Fig. 9 A schematic diagram of the structure of the electric energy dispatching system provided in the embodiment of the present application is shown in FIG. Fig. 9 As shown, the electric energy dispatching system 90 includes the intelligent agent 70 and the edge computing device 80 as described in the above embodiment, and the intelligent agent 70 is deployed on each power node in the power system.

[0237] It can be understood that in the electric energy dispatching system, including a multi-agent system composed of multiple agents and edge computing devices, the number of edge computing devices can also be multiple.

[0238] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0239] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0240] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0241] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0242] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0243] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0244] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0245] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0246] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0247] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for dispatching electric energy, characterized in that: Applied to an intelligent agent, the intelligent agent is independently deployed on each power node in the power system, and the power dispatching method includes: Monitoring power flow between directly connected intelligent entities, wherein the power flow is used to reflect the intensity of electric energy flow between the intelligent entities; If the power flow does not meet the power flow intensity requirement, determining the directly connected intelligent agent corresponding to the power flow as the target intelligent agent; Based on the ant colony algorithm, determining whether the target intelligent agent is an intelligent agent for which the power adjustment strategy is to be executed; If the target intelligent agent is an intelligent agent for which an electric energy adjustment strategy is to be executed, the target intelligent agent is triggered to execute the electric energy adjustment strategy, wherein the electric energy adjustment strategy includes controlling the target power node corresponding to the target intelligent agent to output the first power according to the current operating parameters of the target intelligent agent and the operating parameters of the adjacent intelligent agents.

2. The electric energy dispatching method according to claim 1, characterized in that: The step of determining whether the target intelligent agent is a target intelligent agent of a power adjustment strategy to be executed based on an ant colony algorithm comprises: Based on the ant colony algorithm, determining whether the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability; If the path between the target intelligent agent and the target intelligent agent is the path with the highest selection probability, the target intelligent agent is determined to be the target intelligent agent for executing the power adjustment strategy.

3. The electric energy dispatching method according to claim 1 or 2, characterized in that: Also includes: If the agent is a target agent, weighted summing the current operating parameters of the target agent and the operating parameters of the adjacent agents is performed to obtain updated operating parameters corresponding to the target agent; Based on the mapping relationship between the operating parameters and the power, determining a first power corresponding to the updated operating parameters; The target power node is controlled to output a first power.

4. The electric energy dispatching method according to claim 3, characterized in that: Also includes: After controlling the target power node to output a first power, determining a power quality indicator of the target power node according to the first power, wherein the power quality indicator is used to measure the power output quality of the power node; Sending the power quality indicator to an edge computing device, wherein the edge computing device is used to feedback a power dispatching instruction according to the power quality indicator, wherein the power dispatching instruction carries a power distribution amount to be adjusted; receiving the electric energy dispatching instruction, and determining a second electric power corresponding to the electric power distribution amount to be adjusted based on a mapping relationship between the electric power distribution amount and the electric power; The target power node is controlled to output the second power.

5. The electric energy dispatching method according to claim 4, characterized in that: Agents communicate with each other based on a message passing protocol; And / or, each power node in the power system and the edge computing device are deployed in a blockchain network.

6. A method for dispatching electric energy, characterized in that: Applied to edge computing equipment, the power scheduling method includes: receiving a power quality indicator sent by an intelligent agent, the intelligent agent being independently deployed on a power node in a power system, the power quality indicator being determined according to a first power output by the power node, and the power quality indicator being used to measure the power output quality of the power node; Determining the power distribution amount to be adjusted according to the power quality indicator and the preset power quality indicator; According to the power distribution amount to be adjusted, an electric energy dispatching instruction is sent to the intelligent agent, the electric energy dispatching instruction carries the power distribution amount to be adjusted, and the intelligent agent is used to control the power node to output the second power according to the power distribution amount to be adjusted.

7. The electric energy dispatching method according to claim 6, characterized in that: The step of determining the power distribution amount to be adjusted according to the power quality indicator and the preset power quality indicator comprises: Based on the feedback control mechanism, a difference between the power quality indicator and the preset power quality indicator is integrated in the time domain, and multiplied by the integral gain to obtain a first intermediate value; Performing time domain differentiation on the difference, and multiplying the difference with a differential gain to obtain a second intermediate value; multiplying the difference by a proportional gain to obtain a third intermediate value; The power distribution amount to be adjusted is determined according to the sum of the first intermediate value, the second intermediate value and the third intermediate value.

8. An electric energy dispatching device, characterized in that: Applied to an intelligent agent, the intelligent agent is independently deployed on each power node in the power system, and the electric energy dispatching device includes: A monitoring module, used to monitor the power flow between the directly connected intelligent bodies, wherein the power flow is used to reflect the intensity of the electric energy flow between the intelligent bodies; A first determination module, configured to determine, when the power flow does not meet the power flow intensity requirement, a directly connected intelligent agent corresponding to the power flow as a target intelligent agent; A second determination module is used to determine whether the target intelligent agent is an intelligent agent for which a power adjustment strategy is to be executed based on an ant colony algorithm; A trigger module is used to trigger the target intelligent agent to execute an electric energy adjustment strategy when the target intelligent agent is an intelligent agent to execute an electric energy adjustment strategy. The electric energy adjustment strategy includes controlling the target power node corresponding to the target intelligent agent to output the first power according to the current operating parameters of the target intelligent agent and the operating parameters of adjacent intelligent agents.

9. An electric energy dispatching device, characterized in that: Applied to edge computing equipment, the electric energy dispatching device includes: A receiving module, used to receive a power quality indicator sent by an intelligent agent, wherein the intelligent agent is independently deployed on a power node in a power system, wherein the power quality indicator is determined according to a first power output by the power node, and wherein the power quality indicator is used to measure the power output quality of the power node; A determination module, used to determine the power distribution amount to be adjusted according to the power quality indicator and the preset power quality indicator; A sending module is used to send an electric energy dispatching instruction to the intelligent agent according to the electric energy distribution amount to be adjusted, wherein the electric energy dispatching instruction carries the electric energy distribution amount to be adjusted, and the intelligent agent is used to control the power node to output the second power according to the electric energy distribution amount to be adjusted.

10. An intelligent agent, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

11. An edge computing device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to claim 6 or 7.

12. An electric energy dispatching system, characterized in that: include: The intelligent agent according to claim 10, wherein the intelligent agent is deployed on each power node in the power system; The edge computing device as claimed in claim 11.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method according to any one of claims 1 to 5, and / or, which, when executed, are used to implement the method according to claim 6 or 7.

14. A computer program product, characterized in that The method comprises a computer program, which is used to implement the method according to any one of claims 1 to 5 when executed, and / or, which is used to implement the method according to claim 6 or 7 when executed.

Images