Power grid operation transfer method and device based on genetic algorithm, computer equipment, readable storage medium and program product

Through the power grid operation transfer method based on genetic algorithm, the problem that traditional power grid operation strategies are difficult to predict power demand is solved, the accuracy and reliability of power grid operation are improved, and the efficient utilization of power resources and the intelligent adaptability of the power grid are achieved.

CN119067358APending Publication Date: 2024-12-03MAOMING POWER SUPPLY BUREAU GUANGDONG POWER GRID CORP
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411052722.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional power grid operation strategies are difficult to accurately predict future power demand, resulting in low accuracy of power grid operation plans and unable to effectively ensure the balance between power grid supply and demand, especially when peak and valley electricity price policies and renewable energy are connected to the grid.

Method used

Using the power grid operation and supply method based on genetic algorithm, the power demand information is generated by obtaining preset feature information and pre-trained power demand information prediction model, and the predicted power demand information is generated based on the genetic algorithm model, and the supply and demand status is monitored in real time. Generate and execute load transfer plans under circumstances.

Benefits of technology

It improves the accuracy and reliability of power grid operation, reduces supply and demand imbalances, ensures efficient utilization of power resources, improves the economic benefits and stability of the power grid, can quickly respond to emergencies, and ensures the continuity and intelligence level of power supply.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067358A_ABST
    Figure CN119067358A_ABST
Patent Text Reader

Abstract

The invention relates to a power grid operation transfer method and device based on a genetic algorithm, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring preset feature information of a to-be-predicted power grid, and acquiring a pre-trained power demand information prediction model; inputting the preset feature information into a pre-trained power demand information prediction model to obtain predicted power demand information of the to-be-predicted power grid; based on the genetic algorithm model, according to the predicted power demand information, generating a predicted operation scheme of the to-be-predicted power grid; executing the prediction operation scheme, and monitoring supply and demand state information of the to-be-predicted power grid in real time; and under the condition that the supply and demand state information is abnormal, generating a load transfer scheme of the to-be-predicted power grid according to the supply and demand state information and the power grid topology information of the to-be-predicted power grid, and executing the load transfer scheme. By adopting the method, the accuracy of power grid operation transfer based on the genetic algorithm can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of power optimization, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for power grid operation and supply transfer based on genetic algorithms. Background Art

[0002] With the development of economy and the improvement of social electrification, the operation of power grid faces more and more complex challenges. The current power grid operation strategy mainly relies on historical data and manual experience, which can effectively target static or deterministic problems.

[0003] However, under the current peak-valley electricity price policy and the background of large-scale grid connection of renewable energy, traditional methods are difficult to accurately predict future electricity demand, resulting in low accuracy of the obtained grid operation plan, making it impossible for the operation of the grid to well ensure the balance of supply and demand of the grid. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product based on genetic algorithm for power grid operation transfer, which can improve the accuracy of power grid operation transfer based on genetic algorithm, in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a power grid operation and power transfer method based on a genetic algorithm, comprising:

[0006] Obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model;

[0007] Inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted;

[0008] Based on the genetic algorithm model, generating a forecast operation plan for the power grid to be forecasted according to the forecast power demand information;

[0009] Execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time;

[0010] When the supply and demand status information is abnormal, a load transfer plan for the power grid to be predicted is generated based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed.

[0011] In one embodiment, the method of generating a forecast operation plan of the power grid to be forecasted based on the forecast power demand information based on the genetic algorithm model includes:

[0012] Determining a penalty term of an individual fitness function in a genetic algorithm according to the predicted power demand information;

[0013] Determining the objective function term of the individual fitness function in the genetic algorithm according to the scheme evaluation information of each operation scheme;

[0014] According to the individual fitness function in the genetic algorithm, a prediction operation plan of the power grid to be predicted is generated through a genetic algorithm model.

[0015] In one embodiment, generating a forecast operation plan of the power grid to be forecasted through a genetic algorithm model according to the individual fitness function in the genetic algorithm includes:

[0016] Randomly generate multiple operation plans according to the value range of the operation parameters of the power grid to be predicted;

[0017] Taking the multiple operation schemes as the corresponding number of initial genetic individuals, and constructing an initial genetic population based on the corresponding number of initial genetic individuals;

[0018] Based on the initial genetic population, determining the optimal genetic individual through the genetic algorithm model; the optimal genetic individual is the individual with the best individual fitness;

[0019] A forecast operation plan of the power grid to be forecasted is determined according to the optimal genetic individual.

[0020] In one embodiment, after real-time monitoring of the supply and demand status information of the power grid to be predicted, the method further includes:

[0021] Determining the load status of the power supply equipment in the power grid to be predicted according to the supply and demand status information;

[0022] When the load status is greater than or equal to a preset warning threshold of the power supply device, it is determined that the supply and demand status information is abnormal.

[0023] In one embodiment, generating a load transfer scheme of the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted includes:

[0024] Randomly generate a plurality of candidate power transfer schemes according to the supply and demand status information and the power grid topology information;

[0025] On the basis of the multiple candidate transfer schemes, an optimal transfer scheme is determined through a preset load transfer prediction model as the load transfer scheme of the power grid to be predicted.

[0026] In one embodiment, determining the optimal load transfer scheme based on the multiple candidate load transfer schemes by using a preset load transfer prediction model includes:

[0027] Determining objective function values ​​of the plurality of candidate power transfer schemes respectively according to the supply and demand state information and the power grid topology information;

[0028] Generate multiple new candidate power transfer schemes according to the objective function value and the multiple candidate power transfer schemes, and jump to the step of determining the objective function values ​​of the multiple candidate power transfer schemes according to the supply and demand state information and the power grid topology information, until the preset iteration conditions are met, and the final multiple candidate power transfer schemes are obtained;

[0029] The optimal supply transfer plan is determined from the final multiple candidate supply transfer plans.

[0030] In a second aspect, the present application also provides a power grid operation and supply transfer device based on a genetic algorithm, comprising:

[0031] An information acquisition module is used to obtain preset characteristic information of the power grid to be predicted and to obtain a pre-trained power demand information prediction model;

[0032] A demand prediction module, used for inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted;

[0033] An operation prediction module is used to generate a prediction operation plan of the power grid to be predicted based on a genetic algorithm model and according to the predicted power demand information;

[0034] An operation monitoring module, used to execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time;

[0035] The load transfer prediction module is used to generate a load transfer plan for the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and execute the load transfer plan when the supply and demand status information is abnormal.

[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model;

[0038] Inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted;

[0039] Based on the genetic algorithm model, generating a forecast operation plan for the power grid to be forecasted according to the forecast power demand information;

[0040] Execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time;

[0041] When the supply and demand status information is abnormal, a load transfer plan for the power grid to be predicted is generated based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model;

[0044] Inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted;

[0045] Based on the genetic algorithm model, generating a forecast operation plan for the power grid to be forecasted according to the forecast power demand information;

[0046] Execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time;

[0047] When the supply and demand status information is abnormal, a load transfer plan for the power grid to be predicted is generated based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed.

[0048] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0049] Obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model;

[0050] Inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted;

[0051] Based on the genetic algorithm model, generating a forecast operation plan for the power grid to be forecasted according to the forecast power demand information;

[0052] Execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time;

[0053] When the supply and demand status information is abnormal, a load transfer plan for the power grid to be predicted is generated based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed.

[0054] The above-mentioned power grid operation and supply transfer method, device, computer equipment, computer-readable storage medium and computer program product based on genetic algorithm first obtain the preset characteristic information of the power grid to be predicted, and obtain the pre-trained power demand information prediction model. By obtaining the preset characteristic information of the power grid to be predicted, it is possible to provide rich data support for the power demand information prediction model and improve the accuracy of the prediction model. The pre-trained power demand information prediction model can use historical data and characteristic information to make accurate power demand predictions; then, the preset characteristic information is input into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted. Through the pre-trained power demand information prediction model, accurate power demand prediction information can be obtained, providing a reliable data basis for the subsequent generation of operation plans; then, based on the genetic algorithm model, the power grid to be predicted is generated according to the predicted power demand information. Predictive operation plan, based on accurate power demand forecast information, the generated power grid operation plan can better match actual demand, reduce supply and demand imbalance, improve the economic benefits and reliability of power grid operation, and ensure efficient use of power resources; then, execute the predictive operation plan, and monitor the supply and demand status information of the power grid to be predicted in real time. By real-time monitoring of the supply and demand status information of the power grid, it is possible to promptly discover and respond to supply and demand imbalance problems and ensure the stability and safety of power grid operation; in the event of abnormal supply and demand status information, generate a load transfer plan for the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and execute the load transfer plan. When the supply and demand status is abnormal, generate a load transfer plan through the power grid topology information, which can quickly and effectively adjust the load, avoid power grid overload or insufficient power supply, improve the reliability and stability of the power grid, and ensure the continuity of power supply. In the above method, by utilizing the pre-trained electricity demand information prediction model, an accurate predicted electricity demand is first obtained; then the operation plan is predicted based on the predicted electricity demand, and then the load transfer plan is generated and executed in combination with real-time monitoring and dynamic adjustment mechanisms. This can greatly improve the operating efficiency and reliability of the power grid, quickly respond to emergencies in the power grid, ensure the stability and continuity of power supply, significantly improve the intelligence level and adaptability of power grid operation, and meet the needs of efficient and stable operation of modern power grids. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0056] Figure 1 A schematic diagram of a flow chart of a power grid operation and power transfer method based on a genetic algorithm in one embodiment;

[0057] Figure 2 It is a flow chart of a method for power grid operation and power transfer based on a genetic algorithm in another embodiment;

[0058] Figure 3 A schematic diagram of a power grid operation and supply transfer system based on a genetic algorithm in one embodiment;

[0059] Figure 4 It is a structural block diagram of a power grid operation transfer device based on a genetic algorithm in one embodiment;

[0060] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] In one embodiment, Figure 1 As shown, a method for power grid operation and power transfer based on a genetic algorithm is provided. This embodiment uses the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. In this embodiment, the method includes the following steps:

[0063] Step S101, obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model.

[0064] Exemplarily, the terminal extracts preset characteristic information of the power grid to be predicted from the database, which may include the geographical location, population, meteorological information, and economic activity indicators of the power grid. The terminal also obtains a pre-trained power demand information prediction model from the model library. The model is trained by using a large amount of historical data and machine learning algorithms and has high-precision demand prediction capabilities. By combining the preset characteristic information with the pre-trained model, the terminal can lay the foundation for subsequent power demand prediction and operation plan generation.

[0065] Step S102: input the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted.

[0066] Exemplarily, the terminal obtains preset feature information of the power grid to be predicted from the database, and inputs these data into the pre-trained power demand information prediction model. First, the terminal performs data preprocessing on the preset feature information, including data cleaning to remove noise and outliers, data normalization to unify the dimensions of different features, and feature extraction to select the most representative data input model. Next, the pre-processed feature information is input into the pre-trained power demand information prediction model, which uses the complex patterns and laws learned during the training process to generate the predicted power demand information of the power grid in the future. The results calculated by the model, including the load demand in each time period, the peak load time point, etc., are recorded by the terminal and stored in the database of the system for use in the subsequent generation of operation plans and real-time monitoring. This step ensures the foresight and accuracy of the power grid operation plan and helps to optimize the configuration of power resources.

[0067] Step S103, based on the genetic algorithm model and according to the predicted power demand information, a predicted operation plan of the power grid to be predicted is generated.

[0068] Exemplarily, the terminal uses the obtained predicted power demand information to generate a predicted operation plan for the power grid to be predicted through an optimization model. Specifically, the terminal first inputs the predicted power demand information into the optimization model. The optimization model can be a linear programming (LP), a mixed integer linear programming (MILP) or a genetic algorithm (GA), etc. The specific selection depends on the complexity of the power grid and the optimization requirements. This embodiment adopts a genetic algorithm model. The optimization model generates a predicted operation plan through the following steps: Objective function definition: Determine the optimization goal, such as minimizing the operating cost, maximizing the power supply reliability, and optimal load scheduling. Constraint setting: Set constraints according to the physical and operational constraints of the power grid, including the output range of the generator set, the capacity limit of the substation, the load capacity of the transmission line, etc. Solve the optimization problem: The optimization model solves the optimal load scheduling and power generation plan according to the objective function and constraints. In the process of solving the optimization model, the terminal gradually iterates and adjusts the operating parameters until the optimal solution is found. The predicted operation plan finally generated includes a specific load scheduling plan, a power generation plan, etc., to ensure efficient allocation of power resources and stable power supply. Load dispatch planning involves the reasonable allocation of power loads to various power generation units and substations to ensure efficient operation and stable power supply. The power generation plan is used to determine the power generation of each power generation unit in different time periods to meet the expected power demand. The power generation plan takes into account the operating efficiency, power generation cost and environmental protection requirements of different power generation units to ensure economical and efficient power supply.

[0069] Step S104, executing the forecasting operation plan, and monitoring the supply and demand status information of the power grid to be forecasted in real time.

[0070] Exemplarily, the terminal adjusts the output power of the generator set by sending a control signal and allocates power resources according to the load scheduling plan. Adjust the load distribution of each substation to ensure that the power supply of each node matches the expectation and avoid overload or underload. The terminal controls the power generation of each power generation unit in real time to ensure that the total power generation meets the real-time needs of the power grid. Optimize the operating efficiency of the generator set according to the power generation plan to minimize the operating cost. At the same time, the terminal monitors the supply and demand status information of the power grid in real time, including: collecting voltage, current and power data in real time through sensors installed at each node of the power grid. The collected data is transmitted to the data processing center for real-time analysis. Based on the preset supply and demand balance algorithm, the actual supply and demand status of the power grid is calculated, including the difference between the power supply and power consumption of each node.

[0071] Step S105, when the supply and demand status information is abnormal, a load transfer plan for the power grid to be predicted is generated according to the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed.

[0072] Exemplarily, the terminal continuously monitors the supply and demand status information to detect whether there are abnormal supply and demand conditions, such as voltage exceeding the limit, node overload, or insufficient power supply. When an abnormality is detected, the terminal generates an early warning signal to prompt the grid operator or automatically trigger the load transfer plan generation program. The terminal inputs the supply and demand status information and the grid topology information into an optimization model (such as a mixed integer linear programming model or a genetic algorithm) to calculate the optimal load transfer plan. The terminal sends the generated load transfer plan to the grid control system, and performs the load transfer operation automatically or manually by the operator. Monitor the execution of the load transfer in real time to ensure the effective implementation of the transfer plan. In addition, the terminal can also perform multiple predictions to obtain multiple load transfer plans for users to choose to execute.

[0073] Secondly, the forecast operation plan and load transfer plan are both power grid operation plans.

[0074] In the above-mentioned power grid operation and supply transfer method based on genetic algorithm, first, the preset feature information of the power grid to be predicted is obtained, and the pre-trained power demand information prediction model is obtained. By obtaining the preset feature information of the power grid to be predicted, rich data support can be provided for the power demand information prediction model, and the accuracy of the prediction model can be improved. The pre-trained power demand information prediction model can use historical data and feature information to make accurate power demand predictions; then, the preset feature information is input into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted. Through the pre-trained power demand information prediction model, accurate power demand prediction information can be obtained, providing a reliable data basis for the subsequent generation of operation plans; then, based on the genetic algorithm model, according to the predicted power demand information, a predicted operation plan of the power grid to be predicted is generated, and according to the accurate power The power demand forecast information is used to generate a power grid operation plan that can better match actual demand, reduce the imbalance between supply and demand, improve the economic benefits and reliability of power grid operation, and ensure the efficient use of power resources; then, the forecast operation plan is executed, and the supply and demand status information of the power grid to be predicted is monitored in real time. By monitoring the supply and demand status information of the power grid in real time, the problem of imbalance between supply and demand can be discovered and responded to in a timely manner to ensure the stability and safety of power grid operation; in the event of an abnormality in the supply and demand status information, a load transfer plan for the power grid to be predicted is generated based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed. When the supply and demand status is abnormal, a load transfer plan is generated through the power grid topology information, which can quickly and effectively adjust the load, avoid power grid overload or insufficient power supply, improve the reliability and stability of the power grid, and ensure the continuity of power supply. In the above method, by utilizing the pre-trained electricity demand information prediction model, an accurate predicted electricity demand is first obtained; then the operation plan is predicted based on the predicted electricity demand, and then the load transfer plan is generated and executed in combination with real-time monitoring and dynamic adjustment mechanisms. This can greatly improve the operating efficiency and reliability of the power grid, quickly respond to emergencies in the power grid, ensure the stability and continuity of power supply, significantly improve the intelligence level and adaptability of power grid operation, and meet the needs of efficient and stable operation of modern power grids.

[0075] In an exemplary embodiment, the above-mentioned step S103 generates a predicted operation plan for the power grid to be predicted based on a genetic algorithm model and according to predicted power demand information, and also includes: determining the penalty term of the individual fitness function in the genetic algorithm based on the predicted power demand information; determining the objective function term of the individual fitness function in the genetic algorithm based on the scheme evaluation information of each operation scheme; and generating a predicted operation plan for the power grid to be predicted through the genetic algorithm model based on the individual fitness function in the genetic algorithm.

[0076] Among them, the fitness function is a function used to evaluate the quality of each individual (operating plan) in the genetic algorithm, including the objective function term and the penalty term.

[0077] Exemplarily, first, the terminal determines the penalty term of the individual fitness function in the genetic algorithm based on the predicted power demand information. The penalty term is used to constrain the scheme that does not meet the predicted power demand, such as the situation of supply and demand imbalance or load overload. That is, the terminal calculates the deviation of each scheme in meeting the predicted demand, such as the difference between the power supply and the demand, and adds the deviation as a penalty term to the fitness function. Secondly, the terminal determines the objective function term of the individual fitness function in the genetic algorithm based on the scheme evaluation information of each operation scheme. The objective function term evaluates the performance of the operation scheme in achieving optimization goals, such as economic benefits, power supply reliability, and renewable energy utilization. That is, the terminal calculates the contribution of each scheme in these goals, such as minimizing operating costs, maximizing reliability, etc., and adds these evaluation information as objective function terms to the fitness function. Then, the terminal generates a predicted operation scheme for the power grid to be predicted through the genetic algorithm model according to the individual fitness function in the genetic algorithm. The genetic algorithm includes steps such as initial population generation, fitness evaluation, selection, crossover, and mutation.

[0078] In this embodiment, by incorporating the predicted power demand information into the penalty term of the fitness function, it is ensured that the generated operation plan can better meet future power demand and reduce the imbalance between supply and demand. The objective function term of the fitness function comprehensively considers economic benefits, power supply reliability and renewable energy utilization, and the generated operation plan is optimized in multiple objectives, improving the efficiency and reliability of power grid operation, and reducing the overall operation cost of the power grid, so as to achieve economical and efficient power supply.

[0079] In an exemplary embodiment, the above-mentioned generation of a predicted operation plan for the power grid to be predicted through a genetic algorithm model based on the individual fitness function in the genetic algorithm also includes: randomly generating multiple operation plans based on the value range of the operation parameters of the power grid to be predicted; using the multiple operation plans as a corresponding number of initial genetic individuals, and forming an initial genetic population based on the corresponding number of initial genetic individuals; on the basis of the initial genetic population, determining the optimal genetic individual through the genetic algorithm model; the optimal genetic individual is the individual with the best individual fitness; and determining the predicted operation plan for the power grid to be predicted based on the optimal genetic individual.

[0080] The range of operating parameter values ​​is the feasible range of various operating parameters of the power grid to be predicted (such as generator set output power, load distribution, etc.).

[0081] Exemplarily, first, the terminal randomly generates individuals in the initial population according to the range of values ​​of the operating parameters of the power grid to be predicted, and each individual represents a candidate operating scheme. Then, the terminal calculates the fitness value of each individual, and the fitness function comprehensively considers the objective function term and the penalty term. The terminal selects individuals with better performance according to the fitness value for crossover and mutation operations. Through crossover and mutation, new offspring are generated to maintain the diversity and evolutionary ability of the population. The terminal repeats fitness evaluation, selection, crossover and mutation until the optimal operating scheme is found. Based on the initial genetic population, the terminal determines the optimal genetic individual through the genetic algorithm model; the optimal genetic individual is the individual with the best individual fitness. The terminal transforms and determines the predicted operating scheme of the power grid to be predicted based on the gene expression of the optimal genetic individual.

[0082] In this embodiment, the genetic algorithm can find the optimal solution in the complex and changeable power grid operation environment through multiple generations of iteration and evolution, and improve the resilience and intelligence level of the power grid. By optimizing load scheduling and power generation planning, the terminal reduces the overall operation cost of the power grid and realizes economical and efficient power supply.

[0083] In an exemplary embodiment, after the supply and demand status information of the power grid to be predicted is monitored in real time in the above-mentioned step S104, it also includes: determining the load status of the power supply equipment in the power grid to be predicted based on the supply and demand status information; when the load status is greater than or equal to the preset warning threshold of the power supply equipment, determining that the supply and demand status information is abnormal.

[0084] Exemplarily, the terminal collects voltage, current and power data in real time through sensors installed at each node of the power grid. The terminal determines the load status of each power supply device in the power grid to be predicted based on the supply and demand status information monitored in real time. The specific method includes calculating the real-time voltage, current and power values ​​of the power supply equipment and evaluating the current operating load of the equipment. The terminal compares the load status of each power supply device with a preset early warning threshold, and the early warning threshold is less than the maximum load capacity of the power supply equipment to ensure that the early warning is prior to possible load abnormalities. When the load status is greater than or equal to the preset early warning threshold of the power supply equipment, the terminal determines that the supply and demand status information is abnormal. When an abnormal supply and demand status is detected, the terminal generates an early warning signal to prompt the power grid operator or automatically trigger the subsequent load transfer plan generation program.

[0085] In this embodiment, the supply and demand status information of the power grid is monitored in real time, and a warning signal is generated in time according to the load status of the power supply equipment to ensure the safety and stability of the power grid operation. By setting a warning threshold, a warning can be issued when the load status of the equipment reaches the threshold, preventing equipment overload and operation failure, and improving the reliability of the power grid.

[0086] In an exemplary embodiment, the above-mentioned step S105 generates a load transfer plan for the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and also includes: randomly generating multiple candidate transfer plans based on the supply and demand status information and the power grid topology information; on the basis of the multiple candidate transfer plans, determining the optimal transfer plan through a preset load transfer prediction model as the load transfer plan for the power grid to be predicted.

[0087] The grid topology information is the structural information describing the nodes and connection relationships of the grid, including power stations, substations, transmission lines, etc.

[0088] Among them, the load transfer plan is a plan to restore the supply and demand balance by adjusting the load distribution and transferring the power load when the supply and demand status of the power grid is abnormal.

[0089] Exemplarily, the terminal randomly generates multiple candidate transfer schemes based on the supply and demand status information and the grid topology information. Each candidate scheme represents a possible load transfer path and strategy. That is, load nodes and power supply nodes in the grid are randomly selected, and different load transfer paths are designed to ensure that each scheme is feasible under the grid topology. Then, based on multiple candidate transfer schemes, the terminal evaluates the pros and cons of each scheme through a preset load transfer prediction model. The preset load transfer prediction model includes an objective function and constraints. The objective function may be to minimize the power supply interruption time, minimize the power transmission loss, maximize the power supply reliability, etc. The constraints include the physical and operational limitations of the grid, such as the capacity of the transmission line, the load capacity of the node, etc. The terminal calculates the fitness value of each candidate scheme, comprehensively considers the objective function and the constraints, and evaluates the performance of each scheme in achieving the load transfer target. Then, the terminal selects the scheme with the highest fitness value as the optimal transfer scheme based on the evaluation result of the preset load transfer prediction model. The optimal transfer scheme is the candidate transfer scheme with the best individual fitness, which can most effectively restore the supply and demand balance of the grid when the supply and demand status is abnormal. Finally, the terminal uses the optimal transfer plan as the load transfer plan for the power grid to be predicted, records it and prepares to execute it to deal with supply and demand anomalies.

[0090] In this embodiment, by quickly generating and evaluating multiple candidate transfer plans, the optimal transfer plan is quickly determined when the supply and demand status is abnormal, thereby improving the emergency response speed of the power grid. By presetting the load transfer prediction model, it is possible to comprehensively consider multiple objectives and constraints, optimize the load transfer path and strategy, and ensure the effectiveness of the optimal transfer plan in restoring the balance between supply and demand. The optimal transfer plan minimizes the power outage time and power transmission loss by optimizing the load transfer path and strategy, thereby ensuring the continuous and stable power supply of the power grid.

[0091] In an exemplary embodiment, the above-mentioned method of determining the optimal transfer scheme through a preset load transfer prediction model based on multiple candidate transfer schemes also includes: determining the objective function value of each of the multiple candidate transfer schemes according to the supply and demand status information and the grid topology information; generating multiple new candidate transfer schemes according to the objective function value and the multiple candidate transfer schemes, and jumping to the step of determining the objective function value of each of the multiple candidate transfer schemes according to the supply and demand status information and the grid topology information, until the preset iteration conditions are met to obtain the final multiple candidate transfer schemes; and determining the optimal transfer scheme from the final multiple candidate transfer schemes.

[0092] Exemplarily, the terminal determines the objective function values ​​of each of the multiple initial candidate transfer schemes according to the supply and demand status information and the power grid topology information. The objective function may be to minimize the power supply interruption time, minimize the power transmission loss, maximize the power supply reliability, etc. Then, the terminal generates multiple new candidate transfer schemes according to the objective function value and the multiple candidate transfer schemes. Specific methods include genetic algorithms, simulated annealing algorithms, etc. Then, the terminal repeats the steps of evaluating and generating candidate transfer schemes, that is, according to the supply and demand status information and the power grid topology information, the objective function values ​​of each of the multiple candidate transfer schemes are determined, and new candidate transfer schemes are generated. The terminal continues to iterate the above process until the preset iteration conditions (such as reaching the maximum number of iterations or the objective function value converges) are met, and the final multiple candidate transfer schemes are obtained. From the final multiple candidate transfer schemes, the terminal determines the optimal transfer scheme according to the objective function value. The optimal transfer scheme is the scheme with the best objective function value, which can most effectively restore the supply and demand balance of the power grid when the supply and demand state is abnormal.

[0093] In this embodiment, by randomly generating the initial candidate power transfer scheme and iterative optimization, it is possible to flexibly respond to different abnormal situations and improve the adaptability and operational reliability of the power grid. The optimal power transfer scheme minimizes power outage time and power transmission loss by optimizing the load transfer path and strategy, ensuring continuous and stable power supply of the power grid.

[0094] In another exemplary embodiment, Figure 2 As shown, the present application provides a power grid operation and power transfer method based on a genetic algorithm, the method comprising the following steps:

[0095] Step S201, obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model.

[0096] Step S202: input the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted.

[0097] Step S203, determining the penalty term of the individual fitness function in the genetic algorithm according to the predicted power demand information, and determining the objective function term of the individual fitness function in the genetic algorithm according to the scheme evaluation information of each operation scheme.

[0098] Step S204, randomly generating multiple operation plans according to the value range of the operation parameters of the power grid to be predicted, taking the multiple operation plans as the corresponding number of initial genetic individuals, and constructing an initial genetic population based on the corresponding number of initial genetic individuals.

[0099] Step S205, based on the initial genetic population, determine the optimal genetic individual through a genetic algorithm model.

[0100] Among them, the optimal genetic individual is the individual with the best individual fitness.

[0101] Step S206, determining a forecasting operation plan for the power grid to be forecasted based on the optimal genetic individual, executing the forecasting operation plan, and monitoring the supply and demand status information of the power grid to be forecasted in real time.

[0102] Step S207: determining the load state of the power supply equipment in the power grid to be predicted according to the supply and demand state information.

[0103] Step S208: When the load state is greater than or equal to a preset warning threshold of the power supply device, it is determined that the supply and demand state information is abnormal.

[0104] Step S209, when the supply and demand status information is abnormal, a plurality of candidate power transfer schemes are randomly generated according to the supply and demand status information and the power grid topology information.

[0105] Step S210, determining the objective function values ​​of the respective candidate power transfer schemes according to the supply and demand status information and the power grid topology information.

[0106] Step S211, generating multiple new candidate power transfer schemes according to the objective function value and multiple candidate power transfer schemes, and jumping to step S210 until the preset iteration conditions are met to obtain the final multiple candidate power transfer schemes.

[0107] Step S212, determining the optimal load transfer scheme from the final multiple candidate load transfer schemes as the load transfer scheme for the power grid to be predicted, and executing the load transfer scheme.

[0108] Exemplarily, the training process of the pre-trained power demand information prediction model can be: first, the terminal collects indicators such as industrial, commercial and residential power consumption of the target power grid within a preset time. Determine the type and related parameters of each power-consuming device in the target power station. These devices may be of the same type, such as transformers and circuit breakers, or of different types, such as mutual inductors and line switches. Clarify the data types to be collected, including voltage, current, power and temperature. According to the different types of power-consuming devices, the collected numerical rules are sorted to generate the original operation data table of each device. During the cleaning process, duplicate, abnormal or erroneous data must be removed, and the consistency and accuracy of each type of data must be ensured. Standardize or normalize the original data to convert non-numeric data into computable numerical data. According to the type of equipment and related parameters, provide a unified basis for subsequent model construction and optimization. Then, based on domain knowledge and correlation analysis, the user selects characteristic indicators related to the power demand of the target power station, such as population, GDP and climate, from economic indicators, historical power data and other external factors to improve the prediction accuracy of the association model. The user selects a suitable machine learning or statistical model, such as linear regression, random forest, and support vector machine, based on the selected feature indicators and the nature of the data. The model's hyperparameters are adjusted initially to prepare for model training. The terminal divides the data set into a training set and a validation set, and uses the training set to train the model, adjust the model parameters, and improve its predictive ability. The performance of the model is evaluated through the validation set to ensure that it has sufficient generalization ability. The prediction performance of the model is evaluated using indicators such as accuracy, mean square error, F1 score, and recall rate to ensure that the model can effectively predict future electricity demand under different circumstances. At the same time, the evaluation results are compared with the actual electricity consumption pattern to ensure that the model has high prediction accuracy.

[0109] In this embodiment, by utilizing a pre-trained electricity demand information prediction model, an accurate predicted electricity demand is first obtained; then an operation plan is predicted based on the predicted electricity demand, and then a load transfer plan is generated and executed in combination with real-time monitoring and dynamic adjustment mechanisms. This can greatly improve the operating efficiency and reliability of the power grid, quickly respond to emergencies in the power grid, ensure stable and continuous power supply, significantly improve the intelligence level and adaptability of power grid operation, and meet the needs of efficient and stable operation of modern power grids.

[0110] In an exemplary embodiment, Figure 3 As shown, the present application provides a power grid operation and supply transfer system based on genetic algorithm, which includes a data module 301, a model module 302, an optimization module 303, a decision module 304 and a user interface module 305.

[0111] The data module 301 is responsible for real-time collection and storage of data such as load, power consumption patterns and power of power stations and power-consuming equipment, as well as other relevant economic indicators, environmental information and other external factors, providing a comprehensive data basis for model construction and optimization.

[0112] The model module 302 constructs a power demand information prediction model based on historical data and characteristic indicators to predict the future power demand information of the target power station.

[0113] The optimization module 303 generates the optimal grid operation plan and load transfer plan based on current and future power demand information using optimization methods such as genetic algorithms.

[0114] The decision module 304 converts the load transfer scheme into intuitive scheme information, and screens and determines the load transfer scheme to be executed according to preset rules or in response to user selection.

[0115] The user interface module 305 provides an intuitive interface for operation and maintenance personnel, including a graphical display of forecast data and a comparative display of different power transfer plans.

[0116] In terms of the data flow of the system, each module interacts closely through the data flow. The data module 301 passes the collected power plant operation data to the model module 302 to build a power demand information prediction model. The prediction results are passed to the optimization module 303 and the decision module 304 through the data flow. Based on the data output by the model, the optimization module 303 generates a power grid operation plan and a load transfer plan in combination with system rules, and interacts with the decision module 304 to form a visual strategy output. The user interface module 305 displays the prediction data and prediction plan in an intuitive graphical way, and returns the user's feedback to the decision module 304 for further optimization or execution of the plan.

[0117] In this embodiment, the system ensures that the power load of the target power station can be reasonably distributed through the interaction between the data module, optimization module, model module and decision module, provides users with intuitive and accurate decision-making basis, and ensures that the entire distribution network can operate stably and efficiently.

[0118] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiment of the present application also provides a genetic algorithm-based power grid operation transfer device for implementing the genetic algorithm-based power grid operation transfer method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the genetic algorithm-based power grid operation transfer device provided below can refer to the limitations of the genetic algorithm-based power grid operation transfer method above, and will not be repeated here.

[0120] In an exemplary embodiment, Figure 4 As shown, a power grid operation and supply transfer device based on a genetic algorithm is provided, comprising: an information acquisition module 401, a demand prediction module 402, an operation prediction module 403, an operation monitoring module 404 and a supply transfer prediction module 405, wherein:

[0121] The information acquisition module 401 is used to acquire preset characteristic information of the power grid to be predicted, and to acquire a pre-trained power demand information prediction model;

[0122] The demand prediction module 402 is used to input the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted;

[0123] The operation prediction module 403 is used to generate a prediction operation plan of the power grid to be predicted based on the genetic algorithm model and the predicted power demand information;

[0124] Operation monitoring module 404, used to execute the forecast operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time;

[0125] The load transfer prediction module 405 is used to generate a load transfer plan for the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and execute the load transfer plan when the supply and demand status information is abnormal.

[0126] In one of the embodiments, the above-mentioned operation prediction module 403 is also used to determine the penalty term of the individual fitness function in the genetic algorithm based on the predicted power demand information; determine the objective function term of the individual fitness function in the genetic algorithm based on the scheme evaluation information of each operation scheme; and generate a predicted operation plan for the power grid to be predicted through the genetic algorithm model based on the individual fitness function in the genetic algorithm.

[0127] In one of the embodiments, the above-mentioned operation prediction module 403 is also used to randomly generate multiple operation plans according to the range of values ​​of the operation parameters of the power grid to be predicted; use the multiple operation plans as the corresponding number of initial genetic individuals, and form an initial genetic population based on the corresponding number of initial genetic individuals; on the basis of the initial genetic population, determine the optimal genetic individual through a genetic algorithm model; the optimal genetic individual is the individual with the best individual fitness; and determine the predicted operation plan of the power grid to be predicted based on the optimal genetic individual.

[0128] In one of the embodiments, the above-mentioned genetic algorithm-based power grid operation and power transfer device also includes an anomaly detection module, which is used to determine the load state of the power supply equipment in the power grid to be predicted based on the supply and demand status information; when the load state is greater than or equal to the preset warning threshold of the power supply equipment, it is determined that the supply and demand status information is abnormal.

[0129] In one of the embodiments, the above-mentioned transfer prediction module 405 is also used to randomly generate multiple candidate transfer plans based on supply and demand status information and power grid topology information; based on the multiple candidate transfer plans, the optimal transfer plan is determined through a preset load transfer prediction model as the load transfer plan for the power grid to be predicted.

[0130] In one of the embodiments, the above-mentioned power transfer prediction module 405 is also used to determine the objective function value of each of the multiple candidate power transfer schemes according to the supply and demand status information and the power grid topology information; generate multiple new candidate power transfer schemes according to the objective function value and the multiple candidate power transfer schemes, and jump to the step of determining the objective function value of each of the multiple candidate power transfer schemes according to the supply and demand status information and the power grid topology information, until the preset iteration conditions are met, and the final multiple candidate power transfer schemes are obtained; and the optimal power transfer scheme is determined from the final multiple candidate power transfer schemes.

[0131] Each module in the above-mentioned genetic algorithm-based power grid operation and supply transfer device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0132] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a power grid operation transfer method based on a genetic algorithm is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0133] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0134] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0135] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0136] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0137] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0138] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0139] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0140] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A power grid operation and supply transfer method based on genetic algorithm, characterized in that: The method comprises: Obtaining preset characteristic information of the power grid to be predicted, and obtaining a pre-trained power demand information prediction model; Inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted; Based on the genetic algorithm model, generating a forecast operation plan for the power grid to be forecasted according to the forecast power demand information; Execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time; When the supply and demand status information is abnormal, a load transfer plan for the power grid to be predicted is generated based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and the load transfer plan is executed.

2. The method according to claim 1, characterized in that The method of generating a forecast operation plan of the power grid to be forecasted based on the genetic algorithm model and the forecast power demand information includes: Determining a penalty term of an individual fitness function in a genetic algorithm according to the predicted power demand information; Determining the objective function term of the individual fitness function in the genetic algorithm according to the scheme evaluation information of each operation scheme; According to the individual fitness function in the genetic algorithm, a prediction operation plan of the power grid to be predicted is generated through a genetic algorithm model.

3. The method according to claim 2, characterized in that The method of generating a prediction operation plan of the power grid to be predicted by using a genetic algorithm model according to the individual fitness function in the genetic algorithm includes: Randomly generate multiple operation plans according to the value range of the operation parameters of the power grid to be predicted; Taking the multiple operation schemes as the corresponding number of initial genetic individuals, and constructing an initial genetic population based on the corresponding number of initial genetic individuals; Based on the initial genetic population, determining the optimal genetic individual through the genetic algorithm model; the optimal genetic individual is the individual with the best individual fitness; A forecast operation plan of the power grid to be forecasted is determined according to the optimal genetic individual.

4. The method according to claim 1, characterized in that: After real-time monitoring of the supply and demand status information of the power grid to be predicted, the method further includes: Determining the load status of the power supply equipment in the power grid to be predicted according to the supply and demand status information; When the load status is greater than or equal to a preset warning threshold of the power supply device, it is determined that the supply and demand status information is abnormal.

5. The method according to claim 1, characterized in that The step of generating a load transfer scheme for the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted comprises: Randomly generate a plurality of candidate power transfer schemes according to the supply and demand status information and the power grid topology information; On the basis of the multiple candidate transfer schemes, an optimal transfer scheme is determined through a preset load transfer prediction model as the load transfer scheme of the power grid to be predicted.

6. The method according to claim 5, characterized in that The method of determining the optimal load transfer scheme based on the plurality of candidate load transfer schemes by using a preset load transfer prediction model includes: Determining objective function values ​​of the plurality of candidate power transfer schemes respectively according to the supply and demand state information and the power grid topology information; Generate multiple new candidate power transfer schemes according to the objective function value and the multiple candidate power transfer schemes, and jump to the step of determining the objective function values ​​of the multiple candidate power transfer schemes according to the supply and demand state information and the power grid topology information, until the preset iteration conditions are met, and the final multiple candidate power transfer schemes are obtained; The optimal supply transfer plan is determined from the final multiple candidate supply transfer plans.

7. A power grid operation and supply transfer device based on genetic algorithm, characterized in that: The device comprises: An information acquisition module is used to obtain preset characteristic information of the power grid to be predicted and to obtain a pre-trained power demand information prediction model; A demand prediction module, used for inputting the preset characteristic information into the pre-trained power demand information prediction model to obtain the predicted power demand information of the power grid to be predicted; An operation prediction module is used to generate a prediction operation plan of the power grid to be predicted based on a genetic algorithm model and according to the predicted power demand information; An operation monitoring module, used to execute the forecasting operation plan and monitor the supply and demand status information of the power grid to be forecasted in real time; The load transfer prediction module is used to generate a load transfer plan for the power grid to be predicted based on the supply and demand status information and the power grid topology information of the power grid to be predicted, and execute the load transfer plan when the supply and demand status information is abnormal.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Transfer scheme generation method, model training method, device, equipment and medium

    CN119362452A

  • Load transfer scheme intelligent recommendation method and device based on machine learning, and medium

    CN120073746A

  • Power distribution network load transfer strategy generation method, device and equipment and readable storage medium

    CN120914797A

  • Power distribution network load transfer strategy generation method, device and equipment and readable storage medium

    CN120914797B