Copilot-based virtual power plant optimal load response method, system and equipment and medium

Abstract

The invention discloses a virtual power plant optimal load response method, system and device based on Copilot and a medium. The method comprises the steps that a target virtual power plant Copilot response model is acquired; decomposing the demand response task by using a decomposition module to obtain a fine-grained task of each participating node, and inputting the fine-grained tasks into a fine-grained task processing module for processing; a solver module is used for solving each fine-grained result, and a recommended first response strategy is obtained; evaluating the first response strategy according to the performance influence data and the empirical parameters to obtain an evaluation result, and adjusting the first response strategy according to the evaluation result to obtain a second response strategy; and executing the second response strategy by using the energy controller module, obtaining execution result data, and feeding back the execution result data and performing optimization training. The response strategy is corrected and adjusted by using the monitored environment change and system performance change, so that the stability and flexibility of the model are improved, and the technical problem is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power load response of virtual power plants, and in particular to a Copilot-based virtual power plant optimal load response method, system, equipment and medium. Background Art

[0002] At present, the construction of virtual power plants is mainly focused on simple resource integration and primary energy management. Existing virtual power plant support platforms usually collect production and operation data of various distributed energy sources and optimize energy allocation through simple scheduling algorithms. For example, Chinese patent application CN118713098A discloses a method and device for aggregate declaration of virtual power plants under demand response conditions. The objective function of the model is to minimize the difference between the total operating cost and total revenue of the virtual power plant under the electric energy market and the demand response market; solve the virtual power plant aggregate declaration optimization model to obtain the optimization results of the bid amount, demand response plan amount and actual power of the virtual power plant in the electric energy market under the demand response invitation. Chinese patent application CN118589520A discloses a method, device and storage medium for dynamic aggregation and regulation of demand-side resources, establishes an optimized aggregation model under different scenarios, solves the problem that when the time interval of the aggregation area scenario is large, the aggregation scheme obtained has poor resource integration effect under the condition of more scenarios, and at the same time, in the process of model establishment, considers the mutual influence between resources in the resource aggregate based on load complementarity. Chinese patent application CN118710028A discloses a method, device, equipment and medium for demand response of a user-side integrated energy system, which calculates the adjustable capacity of each device in the current user-side integrated energy system; determines the demand response operation mode according to the user's wishes, and reports the adjustable capacity corresponding to the demand response operation mode according to the determined demand response operation mode and the adjustable capacity of each device; receives power grid adjustment instructions, and operates according to the determined demand response operation mode.

[0003] The existing system models have the following problems: they mainly focus on optimizing economic benefits, but not enough on system stability and flexibility; the models are relatively complex and parameter tuning is difficult; they focus on resource aggregation, but not enough on optimizing demand response strategies; the model building process is relatively cumbersome; they are mainly targeted at the user side, but lack global optimization of the entire virtual power plant system. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a Copilot-based virtual power plant optimal load response method, system, equipment and medium to solve the problems of insufficient stability and flexibility of existing solutions and complex system models.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a virtual power plant optimal load response method based on Copilot, which adopts the following technical solution, including:

[0006] Step 100: construct a virtual power plant Copilot response model, optimize and train the virtual power plant Copilot response model, and obtain a target virtual power plant Copilot response model;

[0007] Step 200: obtain the target virtual power plant Copilot response model, receive the demand response task, input the demand response task into the target virtual power plant Copilot response model, obtain the decomposition module of the target virtual power plant Copilot response model, use the decomposition module to decompose the demand response task to obtain the fine-grained task of each participating node, obtain the fine-grained task processing module of the target virtual power plant Copilot response model, and input the fine-grained task into the fine-grained task processing module for processing;

[0008] Step 300: Obtain a solver module of the target virtual power plant Copilot response model, and obtain fine-grained results of fine-grained task processing of each participating node by each fine-grained task processing module, and use the solver module to solve each fine-grained result to obtain a recommended first response strategy;

[0009] Step 400: obtaining a monitoring and evaluation module of the target virtual power plant Copilot response model, using the monitoring and evaluation module to obtain performance impact data generated by state change data on the target virtual power plant Copilot response model, evaluating the first response strategy according to the performance impact data and empirical parameters to obtain an evaluation result, and adjusting the first response strategy according to the evaluation result to obtain a second response strategy;

[0010] Step 500: obtain the energy controller module of the target virtual power plant Copilot response model, use the energy controller module to execute the second response strategy, obtain execution result data, and feed the execution result data back to the target virtual power plant Copilot response model for optimization training.

[0011] Furthermore, the step 200 includes:

[0012] Step 210: Obtain the response time period, participating nodes and response amount of the power load adjustment in the demand response task;

[0013] Step 220: input the time period, participating nodes and response amount into the target virtual power plant Copilot response model;

[0014] Among them, the time period is the time range for power load adjustment, the participating nodes are specific locations or devices in the power grid that require power load adjustment, and the response amount is the specific value of the power load that the participating nodes need to reduce or increase within the response time period.

[0015] Furthermore, after step 220, step 200 further includes:

[0016] Step 230: Analyze the demand response task to obtain task type-demand response information and response scenario information;

[0017] Step 240: Obtain participating nodes and subordinate equipment information corresponding to the response scenario information in the demand response task;

[0018] Step 250: Obtain historical data and real-time feedback of participating nodes and subordinate devices, formulate response tasks for each participating node and subordinate device based on the historical data and real-time feedback, and obtain the fine-grained tasks.

[0019] Furthermore, the step 300 includes:

[0020] Step 310: Obtain the optimization target of each fine-grained task;

[0021] Step 320: Calculate according to the optimization target to obtain a fine-grained result;

[0022] Step 330: Input each fine-grained result into the solver module for solving to obtain the first response strategy.

[0023] Furthermore, the step 400 includes:

[0024] Step 410: continuously monitor price fluctuations, demand changes, and weather conditions in the market environment, continuously monitor device performance changes in the system, and obtain state change data;

[0025] Step 420: Analyze the state change data using the data analysis unit in the target virtual power plant Copilot response model to obtain the performance impact data of the state change data on the target virtual power plant Copilot response model.

[0026] Furthermore, after step 420, step 400 further includes:

[0027] Step 430: Evaluate the first response strategy using the performance impact data to obtain an evaluation result;

[0028] Step 440: Adjust the first response strategy according to the evaluation result to obtain the second response strategy.

[0029] Furthermore, the step 500 includes:

[0030] Step 510: input the second response strategy into the energy controller module for execution;

[0031] Step 520: Obtain performance indicators, cost-benefit analysis, and user feedback obtained after executing the second response strategy;

[0032] Step 530: input the performance indicators, cost-benefit analysis and user feedback as execution result data into the target virtual power plant Copilot response model for optimization training.

[0033] In order to solve the above problems, a virtual power plant optimal load response system based on Copilot is also provided, which adopts the virtual power plant optimal load response method based on Copilot, including:

[0034] A construction unit, used to construct a virtual power plant Copilot response model, optimize and train the virtual power plant Copilot response model, and obtain a target virtual power plant Copilot response model;

[0035] An AI processing unit is used to obtain a target virtual power plant Copilot response model, receive a demand response task, input the demand response task into the target virtual power plant Copilot response model, obtain a decomposition module of the target virtual power plant Copilot response model, decompose the demand response task using the decomposition module to obtain a fine-grained task for each participating node, obtain a fine-grained task processing module of the target virtual power plant Copilot response model, and input the fine-grained task into the fine-grained task processing module for processing;

[0036] An AI computing unit is used to obtain a solver module of the target virtual power plant Copilot response model, and obtain fine-grained results of fine-grained task processing of each participating node by each fine-grained task processing module, and solve each fine-grained result by using the solver module to obtain a recommended first response strategy;

[0037] An AI adjustment unit is used to obtain a monitoring and evaluation module of the target virtual power plant Copilot response model, obtain performance impact data generated by state change data on the target virtual power plant Copilot response model by using the monitoring and evaluation module, evaluate the first response strategy according to the performance impact data and empirical parameters to obtain an evaluation result, and adjust the first response strategy according to the evaluation result to obtain a second response strategy;

[0038] An execution unit is used to obtain the energy controller module of the target virtual power plant Copilot response model, use the energy controller module to execute the second response strategy, obtain execution result data, and feed the execution result data back to the target virtual power plant Copilot response model for optimization training.

[0039] In order to solve the above problems, an embodiment of the present application also proposes a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of a Copilot-based virtual power plant optimal load response method.

[0040] In order to solve the above problems, an embodiment of the present application also proposes a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of a Copilot-based virtual power plant optimal load response method are implemented.

[0041] Compared with the existing technology, the target virtual power plant Copilot response model is constructed, the received response demand tasks are decomposed by AI to obtain fine-grained tasks, and the solver module is used to perform AI solution on each fine-grained result to obtain the response strategy. The response strategy is corrected and adjusted according to the monitored environmental changes and system performance changes, which improves the stability and flexibility of the model and solves technical problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is a flow chart of an embodiment of a Copilot-based virtual power plant optimal load response method of the present application;

[0044] Figure 2 yes Figure 1A flowchart of a specific implementation of S200;

[0045] Figure 3 yes Figure 2 A flowchart of a specific implementation method after S230;

[0046] Figure 4 yes Figure 1 A flowchart of a specific implementation of S300;

[0047] Figure 5 yes Figure 1 A flowchart of a specific implementation of S400;

[0048] Figure 6 yes Figure 5 A flowchart of a specific implementation method after S420;

[0049] Figure 7 yes Figure 1 A flowchart of a specific implementation of S500;

[0050] Figure 8 This is an interactive interface diagram of a Copilot-based virtual power plant optimal load response system of the present application;

[0051] Fig. 9 It is a structural diagram of a target virtual power plant Copilot response model of the present application;

[0052] Fig.10 It is a schematic diagram of the module structure of an embodiment of a virtual power plant optimal load response system based on Copilot of the present application;

[0053] Fig.11 It is a schematic diagram of the module structure of a computer device of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the accompanying drawings in the invention to clearly and completely describe the technical solutions in the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0055] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0057] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0058] The purpose of the embodiments of the present application is to propose a Copilot-based virtual power plant optimal load response method, system, equipment and medium to solve the problems of insufficient stability and flexibility of existing solutions and complex system models.

[0059] In order to solve the above technical problems, the embodiment of the present application provides a virtual power plant optimal load response method based on Copilot, which adopts the following technical solutions: Figure 1 , Figure 1 It is a flowchart of an embodiment of a Copilot-based virtual power plant optimal load response method of the present application; including:

[0060] S100, constructing a virtual power plant Copilot response model, optimizing and training the virtual power plant Copilot response model, and obtaining a target virtual power plant Copilot response model.

[0061] In this embodiment, a generative AI response model of a virtual power plant is built based on the Copilot architecture. The Copilot architecture can understand natural language and automatically generate code, and has functions such as code suggestions, document editing, modification of system settings, information search and processing, image creation and summary, and voice interaction.

[0062] In this embodiment, if Fig. 9, Fig. 9 : is a structural diagram of a target virtual power plant Copilot response model of the present application; the target virtual power plant Copilot response model includes:

[0063] Learning module, data acquisition module, decomposition module, fine-grained task processing module, solver module, monitoring and evaluation module, and energy control module;

[0064] The learning module can learn a large amount of input data based on a deep learning model, the data acquisition module is used to collect the operating data of various equipment in the virtual power plant, such as air conditioning, lighting, energy storage, charging piles, etc. The decomposition module is used to decompose the demand response task and obtain the fine-grained tasks of each participating node. The fine-grained task processing module is used to process the fine-grained tasks of each participating node to obtain fine-grained results. The solver module is used to make predictions based on the fine-grained results obtained and obtain the recommended first response strategy. The monitoring and evaluation module is used to continuously monitor price fluctuations, demand changes and weather conditions in the market environment, continuously monitor changes in equipment performance in the system state, obtain state change data, and evaluate the above-mentioned first response strategy based on the state change data to obtain an evaluation result. The energy control module is used to execute the adjusted second response strategy and provide feedback on the execution results.

[0065] Among them, the monitoring and evaluation module includes a data analysis unit, which is used to analyze the state change data to obtain the performance impact data of the state change data on the Copilot response model of the target virtual power plant.

[0066] S200. Obtain the target virtual power plant Copilot response model, receive the demand response task, input the demand response task into the target virtual power plant Copilot response model, obtain the decomposition module of the target virtual power plant Copilot response model, use the decomposition module to decompose the demand response task to obtain the fine-grained task of each participating node, obtain the fine-grained task processing module of the target virtual power plant Copilot response model, and input the fine-grained task into the fine-grained task processing module for processing.

[0067] In a preferred embodiment, Figure 2 , Figure 2 yes Figure 1A flowchart of a specific implementation method of S200; S200 includes: S210, obtaining the response time period, participating nodes and response amount of the power load adjustment in the demand response task; S220, inputting the time period, participating nodes and response amount into the target virtual power plant Copilot response model; wherein, the time period is the time range of the power load adjustment, the participating nodes are the specific locations or equipment in the power grid that need to adjust the power load, and the response amount is the specific value of the power load that the participating nodes need to reduce or increase within the response time period.

[0068] In this embodiment, the target virtual power plant Copilot response model receives demand response tasks, which are designed to balance grid supply and demand and optimize energy distribution, including response time period, participating nodes, response volume, etc.

[0069] The response time period specifically refers to the time frame during which the grid demand response task requires participants to adjust the power load. This time period may be based on the grid load forecast to ensure sufficient power supply during peak hours or reduce power consumption during off-peak hours.

[0070] Participating nodes specifically refer to specific locations or devices in the power grid that need to adjust the power load in the demand response task. These nodes can be substations, distribution networks, industrial users, commercial users or residential users, etc. They will adjust their power usage according to the requirements of the demand response task.

[0071] The response volume specifically refers to the specific value of the power load that the participating nodes need to reduce or increase during the response time period. This value is determined based on the needs of the power grid and the power consumption characteristics of the participating nodes. The purpose is to achieve the overall supply and demand balance of the power grid by adjusting the power consumption of these nodes.

[0072] In a preferred embodiment, Figure 3 , Figure 3 yes Figure 2 A flowchart of a specific implementation method after S230; after S220, S200 also includes: S230, analyzing the demand response task to obtain the task type - demand response information and response scenario information; S240, obtaining the participating nodes and subordinate equipment information corresponding to the response scenario information in the demand response task; S250, obtaining the historical data and real-time feedback of the participating nodes and subordinate equipment, and formulating the response tasks for each participating node and subordinate equipment based on the historical data and real-time feedback to obtain fine-grained tasks.

[0073] In this embodiment, specific scene information may specifically refer to scene information of cities such as Shanghai and Shenzhen, participating nodes and subordinate equipment information may specifically refer to node / equipment information such as air conditioning, lighting, energy storage, and charging piles, and fine-grained tasks may specifically refer to fine-grained tasks of nodes / equipment such as air conditioning, lighting, energy storage, and charging piles.

[0074] S300. Obtain the solver module of the target virtual power plant Copilot response model, and obtain the fine-grained results of the fine-grained task processing of each participating node by each fine-grained task processing module, use the solver module to solve each fine-grained result, and obtain the recommended first response strategy.

[0075] In a preferred embodiment, Figure 4 , Figure 4 yes Figure 1 A flowchart of a specific implementation method of S300; S300 includes: S310, obtaining the optimization target of each fine-grained task; S320, calculating according to the optimization target to obtain fine-grained results; S330, inputting each fine-grained result into the solver module, solving it, and obtaining the first response strategy.

[0076] In this embodiment, for example, for a fine-grained task, such as reducing the peak load, the optimization goal may be minimizing the peak-to-valley difference, maximizing the system stability, and the like.

[0077] In this embodiment, the fine-grained task processing module may specifically refer to a load and strategy processing model module of participating nodes such as air conditioning, lighting, energy storage, and charging piles. The fine-grained results calculated for each fine-grained task are input into the solver module for solving to obtain the first response strategy.

[0078] S400, obtaining a monitoring and evaluation module of the target virtual power plant Copilot response model, using the monitoring and evaluation module to obtain performance impact data of the state change data on the target virtual power plant Copilot response model, evaluating the first response strategy according to the performance impact data and empirical parameters, obtaining an evaluation result, and adjusting the first response strategy according to the evaluation result to obtain a second response strategy;

[0079] In a preferred embodiment, Figure 5 , Figure 5 yes Figure 1A flowchart of a specific implementation method of S400; S400 includes: S410, continuously monitoring price fluctuations, demand changes and weather conditions in the market environment, continuously monitoring changes in equipment performance in the system state, and obtaining state change data; S420, using the data analysis unit in the target virtual power plant Copilot response model to analyze the state change data, and obtain performance impact data of the state change data on the target virtual power plant Copilot response model.

[0080] In this embodiment, a monitoring and evaluation module is used to continuously monitor changes in the market environment and system status, including price fluctuations, changes in supply and demand, weather conditions, equipment status and performance, etc., to obtain state change data, which includes data on environmental state changes and system heavy equipment state changes. Use data analysis tools to identify the potential impact of these state change data on the performance of the target virtual power plant Copilot response model, that is, to obtain performance impact data. Evaluate the effectiveness of the current first strategy based on the performance impact data: Evaluate the effectiveness and adaptability of the current first strategy based on the monitored environmental changes. Determine whether the strategy needs to be adjusted to cope with new market conditions or system status.

[0081] In a preferred embodiment, Figure 6 , Figure 6 yes Figure 5 A flowchart of a specific implementation method after S420; after S420, S400 also includes: S430, using performance impact data to evaluate the first response strategy to obtain an evaluation result; S440, adjusting the first response strategy according to the evaluation result to obtain a second response strategy.

[0082] In this embodiment, based on the evaluation results, the first response strategy is automatically or semi-automatically adjusted, and an optimization algorithm can be used to find the best strategy to maximize benefits or minimize costs to obtain a second response strategy. The second response strategy is sent to the corresponding energy controller module and can be executed according to the new strategy.

[0083] S500, obtain the energy controller module of the target virtual power plant Copilot response model, use the energy controller module to execute the second response strategy, obtain the execution result data, and feed the execution result data back to the target virtual power plant Copilot response model for optimization training.

[0084] In a preferred embodiment, Figure 7 , Figure 7 yes Figure 1A flowchart of a specific implementation method of S500; S500 includes: S510, inputting the second response strategy into the energy controller module for execution; S520, obtaining the performance indicators, cost-benefit analysis and user feedback after executing the second response strategy; S530, inputting the performance indicators, cost-benefit analysis and user feedback as execution result data into the target virtual power plant Copilot response model for optimization training.

[0085] In this embodiment, data after the implementation of the new strategy is collected, including performance indicators, cost-benefit analysis, and user feedback. This data is fed back to the learning module for further training and model optimization. In order to obtain higher model performance, the learning and feedback process can be iterated and cycled, constantly learning from the data, adjusting the strategy, and optimizing the model. Ensure that the system can respond quickly to changes in the market and environment, maintain competitiveness and efficiency, thereby ensuring the performance of the target virtual power plant Copilot response model. By constructing the target virtual power plant Copilot response model, the received response demand task is AI decomposed to obtain fine-grained tasks, and the solver module is used to perform AI solution on each fine-grained result to obtain a response strategy, and the response strategy is corrected and adjusted according to the monitored environmental changes and system performance changes, which improves the stability and flexibility of the model and solves technical problems.

[0086] In order to solve the above problems, a virtual power plant optimal load response system based on Copilot is also provided, and the optimal load response method of the virtual power plant based on Copilot is adopted, such as Figure 8 , Figure 8 This is an interactive interface diagram of a virtual power plant optimal load response system based on Copilot in this application, such as Fig.10 , Fig.10 1 is a schematic diagram of a module structure of an embodiment of a Copilot-based virtual power plant optimal load response system 600 of the present application, including:

[0087] A construction unit 601 is used to construct a virtual power plant Copilot response model, optimize and train the virtual power plant Copilot response model, and obtain a target virtual power plant Copilot response model;

[0088] The AI ​​processing unit 602 is used to obtain the target virtual power plant Copilot response model, receive the demand response task, input the demand response task into the target virtual power plant Copilot response model, obtain the decomposition module of the target virtual power plant Copilot response model, decompose the demand response task using the decomposition module to obtain the fine-grained task of each participating node, obtain the fine-grained task processing module of the target virtual power plant Copilot response model, and input the fine-grained task into the fine-grained task processing module for processing;

[0089] The AI ​​computing unit 603 is used to obtain a solver module of the target virtual power plant Copilot response model, and obtain the fine-grained results of the fine-grained task processing of each participating node by each fine-grained task processing module, and use the solver module to solve each fine-grained result to obtain a recommended first response strategy;

[0090] The AI ​​adjustment unit 604 is used to obtain a monitoring and evaluation module of the target virtual power plant Copilot response model, obtain the performance impact data of the state change data on the target virtual power plant Copilot response model by using the monitoring and evaluation module, evaluate the first response strategy according to the performance impact data and the empirical parameters, obtain an evaluation result, and adjust the first response strategy according to the evaluation result to obtain a second response strategy;

[0091] The execution unit 605 is used to obtain the energy controller module of the target virtual power plant Copilot response model, use the energy controller module to execute the second response strategy, obtain the execution result data, and feed the execution result data back to the target virtual power plant Copilot response model for optimization training.

[0092] In order to solve the above problems, an embodiment of the present application also proposes a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of a Copilot-based virtual power plant optimal load response method.

[0093] The computer device may be a computer, server, workstation or other device, or a mobile phone, tablet, vehicle-mounted mobile terminal or other device with program execution capability. The internal structure diagram of the computer device may be as follows: Fig.11 As shown, Fig.11It is a structural diagram of an embodiment of a computer device according to the present application. The computer device includes a processor, a memory and a communication module. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, instructions or codes. The internal memory provides an environment for the operation of the operating system and instructions or codes in the non-volatile storage medium. When the instructions or codes are executed by the processor, a function or step of the above-mentioned Copilot-based virtual power plant optimal load response method is implemented. The communication module of the computer device may include a network interface and / or a wireless communication module, and the computer device may communicate with other devices or service platforms through the communication module. In addition, the computer device may also include a display screen and an input device, etc.

[0094] The memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the processor implements the following steps when executing the instructions or code:

[0095] S100, constructing a virtual power plant Copilot response model, optimizing and training the virtual power plant Copilot response model, and obtaining a target virtual power plant Copilot response model;

[0096] S200. Obtain the target virtual power plant Copilot response model, receive the demand response task, input the demand response task into the target virtual power plant Copilot response model, obtain the decomposition module of the target virtual power plant Copilot response model, use the decomposition module to decompose the demand response task, obtain the fine-grained task of each participating node, obtain the fine-grained task processing module of the target virtual power plant Copilot response model, and input the fine-grained task into the fine-grained task processing module for processing;

[0097] S300, obtaining a solver module of the target virtual power plant Copilot response model, and obtaining fine-grained results of fine-grained task processing of each participating node by each fine-grained task processing module, solving each fine-grained result by using the solver module, and obtaining a recommended first response strategy;

[0098] S400, obtaining a monitoring and evaluation module of the target virtual power plant Copilot response model, using the monitoring and evaluation module to obtain performance impact data of the state change data on the target virtual power plant Copilot response model, evaluating the first response strategy according to the performance impact data and empirical parameters, obtaining an evaluation result, and adjusting the first response strategy according to the evaluation result to obtain a second response strategy;

[0099] S500, obtain the energy controller module of the target virtual power plant Copilot response model, use the energy controller module to execute the second response strategy, obtain the execution result data, and feed the execution result data back to the target virtual power plant Copilot response model for optimization training.

[0100] In order to solve the above problems, an embodiment of the present application also proposes a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, steps of a Copilot-based virtual power plant optimal load response method are implemented.

[0101] The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes a Copilot-based virtual power plant optimal load response method.

[0102] The present application also provides a computer-readable storage medium storing a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, Figures 1 to 7 The optimal load response method of a virtual power plant based on Copilot is provided in each step. For details, please refer to the implementation methods provided in the above steps, which will not be repeated here.

[0103] The computer-readable storage medium may be a Copilot-based optimal load response device for a virtual power plant provided in any of the aforementioned embodiments, or an internal storage unit of the terminal device, such as a hard disk or memory of a computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device.

[0104] Furthermore, the computer-readable storage medium may also include both an internal storage unit of the computer device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0105] However, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0106] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0107] Compared with the existing technology, the target virtual power plant Copilot response model is constructed, the received response demand tasks are decomposed by AI to obtain fine-grained tasks, and the solver module is used to perform AI solution on each fine-grained result to obtain the response strategy. The response strategy is corrected and adjusted according to the monitored environmental changes and system performance changes, which improves the stability and flexibility of the model and solves technical problems.

[0108] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0109] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A virtual power plant optimal load response method based on Copil ot, characterized in that it includes: Step 100: construct a virtual power plant Copilot response model, optimize and train the virtual power plant Copilot response model, and obtain a target virtual power plant Copilot response model; Step 200: obtain a target virtual power plant Copil ot response model, input a demand response task into the target virtual power plant Copil ot response model, obtain a decomposition module of the target virtual power plant Copil ot response model, use the decomposition module to decompose the demand response task to obtain a fine-grained task of each participating node, obtain a fine-grained task processing module of the target virtual power plant Copil ot response model, and input the fine-grained task into the fine-grained task processing module for processing; Step 300: Obtain a solver module of the target virtual power plant Copil ot response model, and obtain the fine-grained results of the fine-grained task processing of each participating node by each fine-grained task processing module, and use the solver module to solve each fine-grained result to obtain a recommended first response strategy; Step 400: obtaining a monitoring and evaluation module of the target virtual power plant Copil ot response model, using the monitoring and evaluation module to obtain performance impact data generated by state change data on the target virtual power plant Copil ot response model, evaluating the first response strategy according to the performance impact data and empirical parameters to obtain an evaluation result, and adjusting the first response strategy according to the evaluation result to obtain a second response strategy; Step 500: obtain the energy controller module of the target virtual power plant Copil ot response model, use the energy controller module to execute the second response strategy, obtain execution result data, and feed the execution result data back to the target virtual power plant Copil ot response model for optimization training.

2. The optimal load response method of a virtual power plant based on Copil ot according to claim 1 is characterized in that: The step 200 comprises: Step 210: Obtain the response time period, participating nodes and response amount of the power load adjustment in the demand response task; Step 220: input the time period, participating nodes and response amount into the target virtual power plant Copil ot response model; Among them, the time period is the time range for power load adjustment, the participating nodes are specific locations or devices in the power grid that require power load adjustment, and the response amount is the specific value of the power load that the participating nodes need to reduce or increase within the response time period.

3. According to the Copil ot-based virtual power plant optimal load response method of claim 2, after step 220, step 200 further includes: Step 230: Analyze the demand response task to obtain task type-demand response information and response scenario information; Step 240: Obtain participating nodes and subordinate equipment information corresponding to the response scenario information in the demand response task; Step 250: Obtain historical data and real-time feedback of participating nodes and subordinate devices, formulate response tasks for each participating node and subordinate device based on the historical data and real-time feedback, and obtain the fine-grained tasks.

4. According to the Copil ot-based virtual power plant optimal load response method of claim 1, step 300 comprises: Step 310: Obtain the optimization target of each fine-grained task; Step 320: Calculate according to the optimization target to obtain a fine-grained result; Step 330: Input each fine-grained result into the solver module for solving to obtain the first response strategy.

5. According to the Copil ot-based virtual power plant optimal load response method of claim 1, step 400 comprises: Step 410: continuously monitor price fluctuations, demand changes, and weather conditions in the market environment, continuously monitor device performance changes in the system, and obtain state change data; Step 420: Analyze the state change data using the data analysis unit in the target virtual power plant Copil ot response model to obtain the performance impact data of the state change data on the target virtual power plant Copil ot response model.

6. According to the Copil ot-based virtual power plant optimal load response method of claim 5, after step 420, step 400 further includes: Step 430: Evaluate the first response strategy using the performance impact data to obtain an evaluation result; Step 440: Adjust the first response strategy according to the evaluation result to obtain the second response strategy.

7. According to the Copil ot-based virtual power plant optimal load response method of claim 1, step 500 comprises: Step 510: input the second response strategy into the energy controller module for execution; Step 520: Obtain performance indicators, cost-benefit analysis, and user feedback obtained after executing the second response strategy; Step 530: Input the performance indicators, cost-benefit analysis and user feedback as execution result data into the target virtual power plant Copil ot response model for optimization training.

8. A virtual power plant optimal load response system based on Copil ot, adopting the virtual power plant optimal load response method based on Copil ot according to any one of claims 1 to 7, characterized in that: include: A construction unit is used to construct a virtual power plant Copilot response model, optimize and train the virtual power plant Copilot response model, and obtain a target virtual power plant Copilot response model; An AI processing unit is used to obtain a target virtual power plant Copilot response model, receive a demand response task, input the demand response task into the target virtual power plant Copilot response model, obtain a decomposition module of the target virtual power plant Copilot response model, decompose the demand response task using the decomposition module to obtain a fine-grained task of each participating node, obtain a fine-grained task processing module of the target virtual power plant Copilot response model, and input the fine-grained task into the fine-grained task processing module for processing; The AI ​​computing unit is used to obtain a solver module of the target virtual power plant Copil ot response model, and obtain the fine-grained results of the fine-grained task processing of each participating node by each fine-grained task processing module, and use the solver module to solve each fine-grained result to obtain a recommended first response strategy; An AI adjustment unit is used to obtain a monitoring and evaluation module of the target virtual power plant Copil ot response model, use the monitoring and evaluation module to obtain performance impact data generated by state change data on the target virtual power plant Copil ot response model, evaluate the first response strategy according to the performance impact data and empirical parameters to obtain an evaluation result, and adjust the first response strategy according to the evaluation result to obtain a second response strategy; An execution unit is used to obtain an energy controller module of the target virtual power plant Copil ot response model, use the energy controller module to execute the second response strategy, obtain execution result data, and feed the execution result data back to the target virtual power plant Copil ot response model for optimization training.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the steps of the Copil ot-based virtual power plant optimal load response method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the Copil ot-based virtual power plant optimal load response method as described in any one of claims 1 to 7.

Images