Data analysis method and system for optimizing regional power resource supply

By comprehensively considering the operation characteristics of substations and energy storage stations, and using multi-objective optimization and neural network technology, the problems of unreasonable load allocation and high cost in power resource scheduling are solved, and the overall optimal configuration of power resources and the efficient system are achieved. , reliable and economical.

CN118917598AActive Publication Date: 2024-11-08STATE GRID HUBEI ELECTRIC POWER INFORMATION & TELECOMMUNICATION COMPANY

Patent Information

Application Number
CN202410970595.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-08
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

The existing regional power resource scheduling system fails to effectively comprehensively consider the energy storage station, resulting in unreasonable load distribution, poor power supply reliability and high operating costs.

Method used

By obtaining the operation timing data of substations and energy storage stations, using multi-objective optimization model, timing prediction model, graph neural network and reinforcement learning layer, comprehensive scheduling optimization, target load balancing and charging and discharging operation measures, and using data preprocessing, Feature fusion and graph structure extract global features to optimize power resource configuration.

Benefits of technology

It significantly improves the load scheduling capacity and overall optimization effect of the power system, reduces operating costs, ensures the reliability and economicality of power supply, and adapts to load and environmental changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917598A_ABST
    Figure CN118917598A_ABST
Patent Text Reader

Abstract

The invention provides a data analysis method and system for optimizing regional power resource supply, and relates to the technical field of industrial data mining analysis, and the method comprises the steps: obtaining transformer substation operation time sequence data and energy storage station operation time sequence data of a to-be-analyzed target regional node corresponding to a historical first time period; determining an initial load balancing measure corresponding to a future second time period based on the substation dispatching optimization model; determining an initial charging and discharging operation measure corresponding to a second time period based on the energy storage station scheduling optimization model; and determining a target load balancing measure and a target charging and discharging operation measure corresponding to the second time period based on a measure comprehensive optimization model, wherein the measure comprehensive optimization model comprises a data preprocessing layer, a graph neural network layer, a feature fusion layer and a reinforcement learning layer. Therefore, the transformer substation and the energy storage station are comprehensively dispatched and analyzed, and the dispatching requirement of a modern electric power system is met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of industrial data mining and analysis, and in particular to a data analysis method and system for optimizing regional power resource supply. Background Art

[0002] With the continuous growth of electricity demand and the development of new energy technologies, the efficient supply and management of regional power resources have become particularly important. At the same time, with the rapid development of energy storage technology, some regions have configured energy storage stations, especially hot spots where there are even multiple energy storage stations. Energy storage systems are gradually being used in power systems to smooth load fluctuations, improve the utilization rate of renewable energy, and so on.

[0003] In the existing regional power resource dispatching system, the focus is often on the dispatching and management of substations, while ignoring the potential value of energy storage stations in power dispatching. With the development of new energy technologies, the configuration of energy storage stations has gradually increased, especially in some hot spots. The existence of multiple energy storage stations makes the solution of dispatching substations alone unable to meet the needs of modern power systems.

[0004] In addition, in the process of power resource dispatching, cost control is an important but difficult to achieve accurately. Traditional dispatching methods usually find it difficult to optimize the balance between cost and benefit while ensuring the security of power supply. For example, when performing charging and discharging operations, energy storage stations need to consider factors such as fluctuations in electricity market prices, battery life, and maintenance costs, but existing technologies lack accurate cost assessment and optimization methods, resulting in high operating costs and unsatisfactory benefits. Similarly, when dispatching loads, substations often find it difficult to take into account both the reliability and economy of power supply, resulting in unreasonable load distribution and high operating costs.

[0005] Therefore, how to comprehensively dispatch substations and energy storage stations to achieve the optimal allocation of power resources has become a difficult problem that needs to be solved urgently in the industry. Summary of the invention

[0006] The present application provides a data analysis method, system, storage medium, computer program product and electronic device for optimizing regional power resource supply, which is used to at least solve the problem that the current power resource scheduling does not comprehensively consider energy storage stations, resulting in unreasonable load distribution, poor power supply reliability and high operating costs.

[0007] In a first aspect, an embodiment of the present application provides a data analysis method for optimizing regional power resource supply, including: obtaining substation operation timing data and energy storage station operation timing data corresponding to a first historical time period of a target regional node to be analyzed; the data type of the substation operation timing data includes: load records, peak and valley loads, operating costs, equipment status data and historical maintenance records; the data type of the energy storage station operation timing data includes: charging and discharging records, equipment status, remaining capacity, operating costs, electricity market prices and weather data; the substation operation timing data is input into a substation scheduling optimization model to determine preliminary load balancing measures corresponding to a second time period in the future; the substation scheduling optimization model adopts a multi-objective optimization model; the energy storage station operation timing data and the weather forecast information corresponding to the second time period are input into the energy storage station scheduling optimization model to determine preliminary charging and discharging operation measures corresponding to the second time period; the energy storage station scheduling optimization model adopts a time series prediction model; the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures are input into a comprehensive optimization model to determine The target load balancing measures and target charging and discharging operation measures corresponding to the second time period are determined; the comprehensive optimization model of the measures includes a data preprocessing layer, a graph neural network layer, a feature fusion layer and a reinforcement learning layer; the data preprocessing layer is used to preprocess the substation operation time series data, the energy storage station operation time series data, the preliminary load balancing measures and the preliminary charging and discharging operation measures to obtain the corresponding first time series features, second time series features, first measure features and second measure features; the first time series features and the second time series features are input into the graph neural network layer to obtain the corresponding substation dependency features and energy storage station dependency features respectively, specifically including: based on the first time series features and the second time series features, a graph structure is constructed; the graph structure includes a plurality of graph nodes and edges; each of the graph nodes is defined by the time series features of the corresponding substation or energy storage station, and each of the edges is defined by the substation and energy storage station with a power connection relationship; based on the graph neural network layer, the feature vectors of each graph node are iteratively updated to gradually fuse the information of neighboring nodes to extract global features, thereby obtaining the substation dependency features and energy storage station dependency features corresponding to each graph node:

[0008] Initialize the feature vector of each graph node i x i Represents the time series characteristics of the substation or energy storage station corresponding to the graph node i;

[0009] At each layer l, each graph node i receives information from its neighbor nodes N(i) and aggregates:

[0010]

[0011] In the formula, is the message of graph node i at layer l+1, w ij represents the edge weight corresponding to the edge connecting graph node i and graph node j, is the feature vector of graph node i at layer l+1, W (l) and b (l) is the weight and bias of the lth layer, σ is the activation function;

[0012] Iterative updates are performed through multi-layer graph neural network layers, gradually integrating global information to obtain the final node feature vector:

[0013]

[0014] Where L is the number of graph neural network layers, H i is the final feature vector of graph node i, which is used to determine the corresponding substation dependency feature or energy storage station dependency feature;

[0015] The feature fusion layer is used to fuse the substation dependency feature, the energy storage station dependency feature, the first measure feature, and the second measure feature to obtain a comprehensive feature representation:

[0016] H fusion =Concat(H GNN-substation ,H GNN-storage ,F substation ,F storage )

[0017] In the formula, H fusion represents the comprehensive feature vector, H GNN-substation represents the substation dependent characteristics, H GNN-storage represents the energy storage station dependency characteristics, F substation represents the first measure feature, F storage represents the second measure characteristic;

[0018] Processing the comprehensive feature representation based on the reinforcement learning layer to determine corresponding target load balancing measures and target charging and discharging operation measures specifically includes:

[0019] Each state in the state space of the reinforcement learning layer is defined by the following formula:

[0020] s=H fusi on

[0021] Where s represents the state of the reinforcement learning layer, which is defined by the corresponding comprehensive feature representation;

[0022] The strategy update formula is:

[0023] π(a|s)=softmax(Wπ ·s+b π )

[0024] Where π(a|s) represents the strategy of the reinforcement learning layer, which indicates the probability of selecting action a in state s; a is defined by the corresponding load adjustment amplitude and charge / discharge operation amplitude; W π and b π Represent the strategy weight matrix and strategy bias vector respectively;

[0025] The reward function is:

[0026]

[0027] In the formula, R represents the reward value, P profit represents the overall benefit of the power system, P cost Represents the operating cost of the power system; L balanced represents the regional power load after load balancing adjustment, L total Represents the total load of the power system, E loss represents energy loss; 1 ,λ 2 ,λ 3 They represent the weight coefficients used to measure the system economic benefits, system stability and system efficiency respectively;

[0028] According to the action with the largest corresponding reward value, the target load balancing measure and the target charging and discharging operation measure are determined.

[0029] In a second aspect, an embodiment of the present application provides a data analysis system for optimizing regional power resource supply, which is used to implement the steps of a data analysis method for optimizing regional power resource supply as in any embodiment of the present application.

[0030] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the data analysis method for optimizing regional power resource supply of any embodiment of the present application.

[0031] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, the steps of the data analysis method for optimizing regional power resource supply of any embodiment of the present application are implemented.

[0032] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the data analysis method for optimizing regional power resource supply of any embodiment of the present application.

[0033] The data analysis method for optimizing regional power resource supply provided by this application can produce at least the following technical effects:

[0034] (1) By inputting the operation sequence data of the substation and the energy storage station into the substation dispatch optimization model and the energy storage station dispatch optimization model respectively, the respective operation characteristics and constraints can be comprehensively considered to formulate preliminary load balancing and charging and discharging operation measures. Through these preliminary measures, the load dispatching capacity of the substation or the energy storage station can be significantly improved, and the load balancing capacity can be better supported to smooth load fluctuations. Then, the dispatching measures of the substation and the energy storage station are comprehensively optimized by using the comprehensive optimization model of measures, and the global features are extracted and fused by using the graph neural network layer. By iteratively updating the information of neighbor nodes, the dependency relationship between the substation and the energy storage station can be accurately captured, and the complementary characteristics of the substation and the energy storage station can be fully utilized to achieve the overall optimal configuration of power resources and improve the global optimization effect of the entire power system.

[0035] (2) In this technical solution, the comprehensive optimization model of measures comprehensively considers the time series characteristics and preliminary dispatching measures of substations and energy storage stations, and obtains comprehensive feature representation through the feature fusion layer, ensuring the comprehensiveness and scientificity of the dispatching decision. Furthermore, the reinforcement learning layer selects the optimal load balancing measures and charging and discharging operation measures through strategy updating based on the overall economic benefits, stability and efficiency of the power system, which not only ensures the reliability of power supply, but also maximizes economic benefits and significantly reduces operating costs.

[0036] (3) The time series prediction model is used to predict the charging and discharging operations of the energy storage station, and combined with weather forecast information, the charging and discharging plan of the energy storage station is flexibly adjusted, so that the system can better adapt to changes in load and external environment, and provide flexibility and adaptability of the preliminary charging and discharging operation measures predicted by the system. The substation dispatch optimization model adopts a multi-objective optimization model, which outputs preliminary load balancing measures by considering multiple objectives at the same time, which can effectively avoid unreasonable load balancing measures.

[0037] Through this technical solution, substations and energy storage stations are comprehensively dispatched and analyzed, and technical means such as multi-objective optimization, time series prediction, graph neural network and reinforcement learning are used to significantly improve the efficiency, reliability and economy of power system resource supply. It also has strong flexibility and adaptability, meeting the dispatch needs of modern power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. 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.

[0039] Figure 1 A flowchart showing an example of a data analysis method for optimizing regional power resource supply according to an embodiment of the present application is shown;

[0040] Figure 2 A schematic diagram of structural connection of an example of a comprehensive optimization model of measures according to an embodiment of the present application is shown;

[0041] Figure 3 An operation flow chart of an example of processing time series features using a graph neural network layer according to an embodiment of the present application is shown;

[0042] Figure 4 A schematic diagram of structural connection of an example of an energy storage station scheduling optimization model according to an embodiment of the present application is shown;

[0043] Figure 5 A structural block diagram of an example of a data analysis system for optimizing regional power resource supply according to an embodiment of the present application is shown;

[0044] Figure 6 It is a schematic structural diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved shall comply with the provisions of relevant laws and regulations and shall not violate public order and good morals.

[0047] Figure 1 A flowchart of an example of a data analysis method for optimizing regional power resource supply according to an embodiment of the present application is shown.

[0048] Regarding the executor of the method of the embodiment of the present application, it can be any controller or processor with computing or processing capabilities. Through multi-level and multi-model optimization means, comprehensive scheduling of substations and energy storage stations is achieved, the efficiency and accuracy of power resource supply and management are improved, the operating costs are significantly reduced, and the stability of the system and energy utilization efficiency are improved.

[0049] In some examples, it can be a data analysis platform and can be integrated and configured in an electronic device or terminal through software, hardware, or a combination of software and hardware, and the type of terminal or electronic device can be diverse, such as a mobile phone, tablet computer, or desktop computer, etc.

[0050] like Figure 1 As shown, in step S110, the substation operation timing data and the energy storage station operation timing data of the first historical time period corresponding to the target area node to be analyzed are obtained.

[0051] In some embodiments, the data analysis platform can call the system log and query the system log according to a preset time period of past time length (for example, one day or one week) to determine the corresponding substation operation timing data and energy storage station operation timing data.

[0052] For example, substation operation time series data may include load records (daily, hourly or finer-grained load data), peak and valley loads (recording daily or hourly load peaks and valleys), operating costs (operation and maintenance costs of substations in different time periods), equipment status data (health status of substation equipment, fault records, etc.) and historical maintenance records (maintenance time, maintenance content, equipment replacement records, etc.). In addition, energy storage station operation time series data may include charging and discharging records (daily, hourly or finer-grained charging and discharging data), equipment status (health status of energy storage equipment, fault records, etc.), remaining capacity (current remaining power of energy storage equipment), operating costs (operation and maintenance costs of energy storage stations in different time periods), electricity market prices (time series data of market electricity prices) and weather data (meteorological data related to electricity demand, such as temperature, humidity, etc.).

[0053] Therefore, by acquiring multiple types of data, the operating conditions of substations and energy storage stations can be fully reflected, and the accuracy and reliability of the data can be improved. The rich data types provide a solid foundation for subsequent scheduling optimization and prediction, ensuring that the model can make accurate decisions even in complex situations.

[0054] In step S120 , the substation operation timing data is input into the substation dispatch optimization model to determine preliminary load balancing measures corresponding to a future second time period.

[0055] Here, the substation dispatch optimization model adopts a multi-objective optimization model, for example, it comprehensively considers multiple objectives such as load balance, operating cost, equipment status and maintenance record, and sets constraints such as maximum equipment load, maintenance interval time, etc. It is solved by using appropriate optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) to obtain preliminary load balancing measures.

[0056] It should be noted that load balancing measures refer to ensuring the balance of power supply and demand by adjusting the load distribution of each substation in the power system, so as to optimize the operational stability and reliability of the power system. For example, load balancing measures can include various load distribution operations, such as transferring non-critical loads, absorbing increased loads, and encouraging users to use electricity.

[0057] In this embodiment, a multi-objective optimization model is used to comprehensively consider multiple objectives to ensure the rationality of the output preliminary load balancing measures.

[0058] In step S130, the energy storage station operation timing data and the weather forecast information corresponding to the second time period are input into the energy storage station scheduling optimization model to determine preliminary charging and discharging operation measures corresponding to the second time period.

[0059] Here, by adopting a time series prediction model and using a time series analysis method to predict, corresponding charging and discharging measures are obtained, aiming to maximize the utilization of energy storage equipment, reduce energy loss, and improve economic benefits. It should be noted that the energy storage station scheduling optimization model can use ARIMA, LSTM or other types of time series prediction models to predict the charging and discharging needs of the energy storage station.

[0060] It should be noted that the charging and discharging operation measures refer to the balance of power supply and demand of energy storage stations and the optimization of system operation efficiency and economic benefits by scheduling the charging and discharging operations of energy storage stations in the power system. In some examples, the charging and discharging operation measures may include charging operations and corresponding recommended charging powers, discharging operations and corresponding recommended discharging powers, so as to dynamically adjust the charging and discharging operations of energy storage stations.

[0061] In this embodiment, the energy storage station scheduling optimization model comprehensively considers the historical operation data of the energy storage station and weather forecast information, and uses this to predict the charging and discharging operation measures. Therefore, combined with the weather forecast information, the energy storage operation is adjusted in advance to reduce the impact of renewable energy fluctuations on regional power supply and distribution.

[0062] In step S140, the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures are input into the comprehensive optimization model to determine the target load balancing measures and the target charging and discharging operation measures corresponding to the second time period.

[0063] In some implementations, the comprehensive optimization model of measures may adopt an integrated learning model, which can formulate optimal load balancing and charging and discharging operation measures by comprehensively learning substation operation data, energy storage station operation data, and the relationship between substations and energy storage stations, thereby improving the overall dispatching effect of the power system.

[0064] Figure 2 A schematic diagram of structural connections of an example of a measure comprehensive optimization model according to an embodiment of the present application is shown.

[0065] like Figure 2 As shown, the comprehensive optimization model 200 includes a data preprocessing layer 210, a graph neural network layer 220, a feature fusion layer 230 and a reinforcement learning layer 240.

[0066] The data preprocessing layer 210 is used to preprocess the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures to obtain the corresponding first timing characteristics, second timing characteristics, first measure characteristics and second measure characteristics.

[0067] In some embodiments, the data preprocessing layer 210 is used to scale the data to a uniform range to facilitate model processing, and then key features such as average load, peak load, etc. are extracted from the time series data.

[0068] The first time series feature and the second time series feature are input into the Graph Neural Network (GNN) layer 220 to obtain corresponding substation dependency features and energy storage station dependency features, respectively.

[0069] It should be noted that GNN is suitable for processing network data with complex relationships. In the power system, there are complex dependencies between substations and energy storage stations. GNN can capture these relationships, such as the dependencies between different substations and the charging and discharging relationship between energy storage stations and substations, thereby increasing the amount of information extracted.

[0070] Figure 3 An operational flowchart of an example of processing time series features using a graph neural network layer according to an embodiment of the present application is shown.

[0071] like Figure 3 As shown, in step S310, a graph structure is constructed based on the first time series feature and the second time series feature.

[0072] Here, the graph structure includes multiple graph nodes and edges, each graph node is defined by the timing characteristics of the corresponding substation or energy storage station, and each edge is defined by the substation and energy storage station with power connection relationship.

[0073] In some embodiments, the graph nodes represent substations and energy storage stations in the power system, and their specific node characteristics are defined by corresponding operating sequence characteristics, such as load, voltage, operating status, etc. In addition, the edge can be a physical or logical connection between a substation and an energy storage station. For example, in the same substation area, a substation can be connected to one or more energy storage stations. In addition, each edge is also provided with a corresponding edge weight w ij , which can be defined by the strength of the relationship between the connected nodes.

[0074] In step S320, the feature vector of each graph node is iteratively updated based on the graph neural network layer to gradually integrate the information of neighboring nodes to achieve the extraction of global features, thereby finally obtaining the substation dependency features and energy storage station dependency features corresponding to each graph node.

[0075] Here, the feature vector of the node is updated through GNN iteration, and the information of neighboring nodes is gradually integrated to realize the extraction of global features. Specifically, the feature vector of each graph node i is initialized x i Represents the time series characteristics of the substation or energy storage station corresponding to the graph node i.

[0076] Next, at each layer l, each graph node i receives information from its neighbor nodes N(i) and aggregates them.

[0077] The message passing formula is:

[0078]

[0079] The aggregation formula is:

[0080]

[0081] In the formula, is the message of graph node i at layer l+1, is the feature vector of graph node i at layer l+1, W (l) and b (l) are the weights and biases of the lth layer, and σ is the activation function.

[0082] Iterative updates are performed through multi-layer graph neural network layers, gradually integrating global information to obtain the final node feature vector:

[0083]

[0084] Where L is the number of graph neural network layers, H i is the final feature vector of graph node i, which is used to determine the corresponding substation dependency feature or energy storage station dependency feature.

[0085] Through the above-mentioned graph structure construction process and GNN feature extraction process, the complex relationship between substations and energy storage stations can be effectively captured, enriching the information content of the extracted features. Therefore, the GNN layer can effectively capture the complex relationship between substations and energy storage stations, improve the quality of feature extraction, and provide more accurate data support for subsequent strategy optimization.

[0086] The feature fusion layer 230 is used to fuse the substation-dependent feature, the energy storage station-dependent feature, the first measure feature, and the second measure feature to obtain a comprehensive feature representation:

[0087] H fusion =Concat(H GNN-substation ,H GNN-storage ,F substation ,F storage ), Formula (4)

[0088] In the formula, H fusion represents the comprehensive feature vector, H GNN-substation represents the substation dependent characteristics, H GNN-storage represents the energy storage station dependency characteristics, F substation represents the first measure feature, F storage Indicates the second measure feature.

[0089] Here, the features extracted by GNN are fused with the features of the preliminary measures to form a comprehensive feature vector for subsequent comprehensive optimization of measures. In this embodiment, by fusing data features from different sources, the model can simultaneously consider the operating status and preliminary strategies of the substation and energy storage station, thereby improving the effect of comprehensive optimization.

[0090] The reinforcement learning layer 240 is used to process the comprehensive feature representation to determine the corresponding target load balancing measures and target charging and discharging operation measures.

[0091] Here, the reinforcement learning algorithm is used to process the comprehensive feature vector. Since reinforcement learning is suitable for decision-making optimization in dynamic and complex environments, it can dynamically adjust strategies and maximize the operating cost, stability and economic benefits of the power system by continuously adjusting the initial measures, and output target load balancing measures and target charging and discharging operation measures.

[0092] Specifically, each state in the state space of the reinforcement learning layer 240 is defined by the following formulas:

[0093] s=H fusi on , Formula (5)

[0094] Where s represents the state of the reinforcement learning layer, which is defined by the corresponding comprehensive feature representation.

[0095] The strategy update formula is:

[0096] π(a|s)=softmax(W π ·s+b π ), Formula (6)

[0097] Where π(a|s) represents the strategy of the reinforcement learning layer, which indicates the probability of selecting action a in state s; a is defined by the corresponding load adjustment amplitude and charge / discharge operation amplitude; W π and b π They represent the policy weight matrix and policy bias vector respectively.

[0098] The reward function is:

[0099]

[0100] In the formula, R represents the reward value, P profit represents the overall benefit of the power system, P cost Represents the operating cost of the power system; L balanced represents the regional power load after load balancing adjustment, L total Represents the total load of the power system, E loss represents energy loss; 1 ,λ 2 ,λ 3 They respectively represent the weight coefficients used to measure system economic benefits, system stability and system efficiency.

[0101] Here, by including economic benefits as an important component in the reward function, the model is able to prioritize the costs and benefits of the power system in the decision-making process. profit -P cost It directly reflects the economic benefits of the power system and prompts the model to maximize benefits and minimize costs when selecting load balancing measures and charging and discharging operation recommendations.

[0102] By introducing an indicator of operational stability into the reward function The model is able to balance the power load and avoid overload or underload situations, which encourages the model to be more cautious in the selection of load balancing measures, ensure the balance of power supply and demand, and improve the stability of the system.

[0103] Through the system efficiency index E in the reward function loss It reflects the energy loss situation and prompts the model to consider the efficiency issues in the energy conversion and transmission process when selecting charging and discharging operation measures, thereby improving the overall system efficiency.

[0104] According to the action with the largest corresponding reward value, the target load balancing measure and the target charging and discharging operation measure are determined.

[0105] By comprehensively considering the reward function of economic benefits, operational stability and system efficiency, the reinforcement learning layer can make optimization decisions under multi-objective constraints during the process of updating strategy actions, ensuring that the optimal load balancing measures and charging and discharging operation measures can be output in different scenarios.

[0106] In the embodiment of the present application, the comprehensive optimization model combines various data and preliminary strategies of the substation and energy storage station, and can flexibly adjust the scheduling optimization strategy while comprehensively considering multiple factors. By comprehensively considering the operating status of the substation and energy storage station, the market economic environment and the external weather environment, the global optimization of load balancing measures and charging and discharging measures can ensure the balance of power supply and demand, reduce the fluctuation of the power system, and avoid overcharging or discharging of the energy storage station, thereby improving the stability of the system and enhancing the safety of the system.

[0107] In some examples of the embodiments of the present application, the substation scheduling optimization model adopts an enhanced particle swarm optimization (PSO) algorithm.

[0108] More specifically, K subpopulations are initialized, each subpopulation contains multiple particles, the dimension of each particle is D, and the initial position of each particle is randomly initialized. and initial velocity The position of the particle is defined by the load distribution value of the substation, and the speed of the particle represents the speed and direction of the particle in the search space. Here, the update of the speed determines how the particle moves from the current position to the new position, thereby updating its load distribution measures, and then obtaining the optimal load distribution strategy based on the optimal particle position obtained by the PSO optimization calculation.

[0109] The following will describe the details of the specific PSO optimization calculation process. First, set the maximum number of iterations T max and the frequency of information exchange between subgroups T exchange , and perform independent PSO search for each sub-population to update the velocity and position of each particle in the sub-population.

[0110] In this embodiment, the particle swarm is divided into multiple sub-groups, each sub-group searches independently in different search spaces, and by regularly exchanging information between sub-groups, the search space can be explored more comprehensively to avoid falling into a local optimal solution.

[0111] More specifically, the particle velocity update formula used in the global search phase is:

[0112] v i,j (t+1)=ω·v i,j (t)+η·(p i,j (t)-x i,j(t))+μ·(x rand,j (t)-x i,j (t)), formula (8)

[0113]

[0114] Where ω is the inertia weight, w max and w min is the initial and minimum inertia weight, t is the current iteration number, T max is the maximum number of iterations; v i,j (t) represents the velocity of the i-th particle in the j-th dimension at time t, v i,j (t+1) represents the updated value of the velocity of the i-th particle in the j-th dimension at time t+1; η represents the first variation factor, which is used to increase the diversity of particles and help escape from the local optimum; p i,j (t) is the value of the historical optimal position of the i-th particle in the j-th dimension; x i,j (t) represents the value of the current position of the i-th particle in the j-th dimension at time t; μ represents the second variation factor, which is used to introduce random components to further increase the diversity of particles; x rand,j (t) represents the value of the randomly selected particle position at time t in the jth dimension.

[0115] Here, according to the search stage and performance of the particles, the inertia weight and other parameters are dynamically adjusted, so that the algorithm can adapt to different search environments and optimization requirements, improving the robustness and adaptability of the algorithm so that the algorithm can perform more global exploration in the early stages of the search and more local searches in the later stages. Therefore, in the face of sudden load changes and uncertain factors, the algorithm can quickly adjust the load distribution strategy to ensure the stable operation and optimization effect of the system.

[0116] The particle velocity update formula used in the local search phase is:

[0117] v i,j (t+1)=α·v i,j (t)+β·(p i,j (t)-x i,j (t))+γ·(g j (t)-x i,j (t)), Formula (10)

[0118] In the formula, α, β, and γ are convergence factors, which control the ratio of inertia weight, individual cognition, and social cognition respectively; in the formula, α represents the first convergence factor, which is used to control the inertia weight and affect the ratio of particle velocity maintenance; β represents the second convergence factor, which is used to control the ratio of individual cognition and affect the role of the particle's own historical optimal position; γ represents the third convergence factor, which is used to control the ratio of social cognition and affect the role of the particle group's historical optimal position; g j (t) represents the value of the global optimal position in the subgroup at time t in the jth dimension. Here, the individual cognition and social cognition parameters control the degree to which the particle is affected by its own optimal position and the group's optimal position when updating the speed. These parameters can be set in advance.

[0119] In this way, in the global search phase, the randomness and diversity of particles are increased through the mutation speed update mechanism, ensuring that a better solution is found in a wide search space. In the local search phase, the convergence speed update mechanism is used to reduce the search space, focus on fine search near the optimal solution, and improve optimization accuracy.

[0120] In this embodiment, multiple speed update mechanisms are used, and a mutation speed update formula and a convergence speed update formula are introduced, which are used in the global search stage and the local search stage respectively. The diversity of particles is increased by mutation speed update to ensure global search capability, and the search accuracy of particles is improved by convergence speed update to ensure local optimization effect. For example, in substation scheduling, through accurate load distribution strategies, the power supply and demand relationship can be better balanced, peak load pressure can be reduced, and the reliability and stability of the system can be improved.

[0121] Regularly exchange optimal information between subgroups, every T exchange Perform one swap per iteration;

[0122] Share the optimal solutions of each subgroup and update the global optimal position of each subgroup;

[0123]

[0124] In the formula, G j (t) represents the value of the global optimal position of all sub-populations in the jth dimension at time t; k represents the index of the sub-population, ranging from 1 to K, where K is the total number of sub-populations; It represents the value of the global optimal position in the kth subpopulation at time t in the jth dimension; f is the fitness function, which is used to evaluate the quality of particles.

[0125] The global optimal position is updated within each sub-group, and the global optimal position is updated after information exchange, and a preliminary load balancing measure is determined based on the updated global optimal position.

[0126] In this embodiment, multiple subgroups are initialized, each subgroup searches independently, and information is exchanged between subgroups regularly to ensure that each subgroup can use the optimal solution of other subgroups, thereby improving the global search capability and optimization efficiency. Therefore, in substation scheduling optimization, multi-group collaborative search can ensure that the global optimal load distribution strategy is found in different time periods, avoiding resource waste and low operating efficiency caused by local optimal solutions.

[0127] Through the embodiments of the present application, an enhanced PSO algorithm using multi-group collaborative search and multiple speed update mechanisms can significantly improve the global search capability and optimization efficiency of the substation scheduling optimization model, enhance the accuracy and reliability of the load distribution strategy, improve the robustness and adaptability of the algorithm, and optimize the economic benefits and operating efficiency of the power system.

[0128] Figure 4 A schematic diagram of the structural connection of an example of an energy storage station scheduling optimization model according to an embodiment of the present application is shown.

[0129] like Figure 4 As shown, the energy storage station scheduling optimization model 400 includes a cascaded input layer 410, a convolutional layer 420, an LSTM layer 430, an attention layer 440 and an output layer 450.

[0130] The input layer 410 is used to receive the energy storage station operation sequence data and weather forecast information.

[0131] The convolution layer 420 uses a multi-scale convolution kernel to perform a convolution operation on the input time series data to extract corresponding multi-scale convolution features.

[0132]

[0133] In the formula, H conv Represents the multi-scale convolution features output by the convolution layer, and They represent the weight matrix and bias term of the convolution kernel with scale s respectively; S represents the convolution kernel scale set; X represents the input data matrix determined based on the energy storage station operation timing data and weather forecast information.

[0134] The multi-scale convolutional layer extracts local features of time series data and captures features of different time windows, improving the model's ability to understand and predict complex time series data. In addition, the model can be more efficient in extracting features, reducing the computational burden of the LSTM layer.

[0135] The LSTM layer 430 is used to process the multi-scale convolutional features to obtain the corresponding time series modeling convolutional features:

[0136] H LSTM =LSTM(Hconv ), Formula (13)

[0137] In the formula, H LSTM Represents the temporal modeling convolutional features output by the LSTM layer;

[0138] The features of the convolutional layer output are processed through the LSTM layer to perform time series modeling, effectively capturing the time dependency and nonlinear characteristics in the data.

[0139] The attention layer 440 is used to process the temporal modeling convolutional features using a multi-head attention mechanism to obtain a corresponding attention context vector;

[0140] e t =Concat(head 1 ,...,head h ), Formula (14)

[0141]

[0142] In the formula, e t represents the attention score at time t, and Represent the weight matrix and bias term of the i-th attention head respectively; α t represents the attention weight at time t, and c represents the attention context vector.

[0143] Through the multi-head attention mechanism, the attention layer can dynamically adjust the focus, capture important time points and patterns in the time series data, improve the ability to capture important features in the time series data, and further improve the accuracy of the prediction results. In addition, through the multi-head attention mechanism, the parallel computing capability of the model is improved, the impact of long sequence dependencies on computing efficiency is reduced, and the real-time and efficiency of strategy optimization are improved.

[0144] The output layer 450 is used to predict the initial charging and discharging operation measures corresponding to the second time period according to the attention context vector:

[0145]

[0146] In the formula, Indicates the charge and discharge decision value; if Then perform charging operation; if Then the discharge operation is performed; W decision and b decision Represent the weight matrix and bias term of the decision fully connected layer respectively; Indicates the charge and discharge strategy value, W strategy represents the strategy value conversion slope, and b strategy represents the strategy value transformation intercept.

[0147] Based on the above design of the output layer 450, the charge and discharge strategy value not only determines whether the energy storage station performs charging or discharging operations, but also accurately controls the power of charging and discharging, which directly corresponds to the depth of charging and discharging, making the charge and discharge control measures for the energy storage station clearer and easier to implement to meet actual needs. In addition, through precise charging and discharging operations, the operating costs and benefits of the energy storage station can be optimized to maximize economic benefits.

[0148] Through the embodiments of the present application, in actual energy storage station scheduling, based on real-time input data and context information, the model can dynamically adjust the charging and discharging strategy to ensure the accuracy and adaptability of the operation, accurately adjust the charging and discharging power in each time period, avoid overcharging or discharging, and improve the life and economic benefits of the energy storage equipment.

[0149] In some examples of the embodiments of the present application, the loss function L of the energy storage station scheduling optimization model is:

[0150] L=λ 1 ·L economic +λ 2 ·L stability +λ 3 ·L efficiency , Formula (20)

[0151] Where, L economic Represents the economic benefit loss term, L stability represents the operational stability loss term, L efficiency represents the system efficiency loss term; λ 1 ,λ 2 ,λ 3 Represent the corresponding weight coefficients respectively.

[0152]

[0153] In the formula, N represents the number of samples in the data sample set, D profit,i represents the power supply revenue of the energy storage station corresponding to the i-th sample, D cost,i Represents the power supply and distribution operation cost of the energy storage station corresponding to the i-th sample.

[0154]

[0155] Where, L balanced,i represents the regional power load after load balancing corresponding to the i-th sample, L lim,i Indicates the regional power load extreme value corresponding to the i-th sample.

[0156]

[0157] In the formula, E loss,i Indicates the regional power supply energy loss value corresponding to the i-th sample.

[0158] Based on the above loss function design of the embodiment of the present application, by maximizing revenue and minimizing cost, the model can optimize the charging and discharging strategy of the energy storage station under different electricity price conditions, effectively control operating costs, select the best charging and discharging time and strategy, and reduce electricity procurement costs. For example, the energy storage station discharges during peak electricity price periods and charges during low electricity price periods, thereby maximizing revenue. By balancing the power load, avoiding regional power overload or underload, and improving the stability and reliability of regional power supply and distribution, for example, by sharing the load of the substation in the region or the connected substation through the energy storage station, to prevent regional power supply and distribution overload. By reducing energy loss items, the energy storage equipment operates in the optimal state and improves the charging and discharging efficiency, such as efficient charging under sufficient lighting conditions.

[0159] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of actions combined, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0160] Figure 5 A structural block diagram of an example of a data analysis system for optimizing regional power resource supply according to an embodiment of the present application is shown.

[0161] like Figure 5 As shown, the data analysis system 500 for optimizing regional power resource supply includes a data acquisition unit 510 , a first measure determination unit 520 , a second measure determination unit 530 and a comprehensive measure optimization unit 540 .

[0162] The data acquisition unit 510 is used to obtain the substation operation timing data and the energy storage station operation timing data of the first historical time period corresponding to the target area node to be analyzed; the data type of the substation operation timing data includes: load records, peak and valley loads, operating costs, equipment status data and historical maintenance records; the data type of the energy storage station operation timing data includes: charging and discharging records, equipment status, remaining capacity, operating costs, electricity market prices and weather data.

[0163] The first measure determination unit 520 is used to input the substation operation timing data into the substation dispatch optimization model to determine the preliminary load balancing measures corresponding to the second time period in the future; the substation dispatch optimization model adopts a multi-objective optimization model;

[0164] The second measure determination unit 530 is used to input the energy storage station operation time series data and the weather forecast information corresponding to the second time period into the energy storage station scheduling optimization model to determine the preliminary charging and discharging operation measures corresponding to the second time period; the energy storage station scheduling optimization model adopts a time series prediction model.

[0165] The comprehensive measures optimization unit 540 is used to input the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures into the comprehensive measures optimization model to determine the target load balancing measures and target charging and discharging operation measures corresponding to the second time period.

[0166] The comprehensive optimization model of the measures includes a data preprocessing layer, a graph neural network layer, a feature fusion layer and a reinforcement learning layer;

[0167] The data preprocessing layer is used to preprocess the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures to obtain corresponding first timing characteristics, second timing characteristics, first measure characteristics and second measure characteristics;

[0168] The first time series feature and the second time series feature are input into the graph neural network layer to obtain corresponding substation dependency features and energy storage station dependency features, respectively, including:

[0169] Based on the first time series feature and the second time series feature, a graph structure is constructed; the graph structure includes a plurality of graph nodes and edges; each of the graph nodes is defined by the operation data of the corresponding substation or energy storage station, and each of the edges is defined by the substation and energy storage station having a power connection relationship;

[0170] Based on the graph neural network layer, the feature vector of each graph node is iteratively updated to gradually integrate the information of neighboring nodes and extract global features, thereby obtaining the substation dependency features and energy storage station dependency features corresponding to each graph node:

[0171] Initialize the feature vector h of each graph node i i (0) =x i ;x i Represents the time series characteristics of the substation or energy storage station corresponding to the graph node i;

[0172] At each layer l, each graph node i receives information from its neighbor nodes N(i) and aggregates:

[0173]

[0174] In the formula, is the message of graph node i at layer l+1, w ij represents the edge weight corresponding to the edge connecting graph node i and graph node j, is the feature vector of graph node i at layer l+1, W (l) and b (l) is the weight and bias of the lth layer, σ is the activation function;

[0175] Iterative updates are performed through multi-layer graph neural network layers, gradually integrating global information to obtain the final node feature vector:

[0176]

[0177] Where L is the number of graph neural network layers, H i is the final feature vector of graph node i, which is used to determine the corresponding substation dependency feature or energy storage station dependency feature;

[0178] The feature fusion layer is used to fuse the substation dependency feature, the energy storage station dependency feature, the first measure feature, and the second measure feature to obtain a comprehensive feature representation:

[0179] H fusion =Concat(H GNN-substation ,H GNN-storage ,F substation ,F storage )

[0180] In the formula, H fusion represents the comprehensive feature vector, H GNN-substation represents the substation dependency characteristics, H GNN-storage represents the energy storage station dependency characteristics, F substation represents the first measure feature, F storage represents the second measure characteristic;

[0181] Processing the comprehensive feature representation based on the reinforcement learning layer to determine corresponding target load balancing measures and target charging and discharging operation measures specifically includes:

[0182] Each state in the state space of the reinforcement learning layer is defined by the following formula:

[0183] s=H fusion

[0184] Where s represents the state of the reinforcement learning layer, which is defined by the corresponding comprehensive feature representation;

[0185] The strategy update formula is:

[0186] π(a|s)=softmax(W π ·s+bπ )

[0187] Where π(a|s) represents the strategy of the reinforcement learning layer, which indicates the probability of selecting action a in state s; a is defined by the corresponding load adjustment amplitude and charge / discharge operation amplitude; W π and b π Represent the strategy weight matrix and strategy bias vector respectively;

[0188] The reward function is:

[0189]

[0190] In the formula, R represents the reward value, P profit represents the overall benefit of the power system, P cost Represents the operating cost of the power system; L balanced represents the regional power load after load balancing adjustment, L total Represents the total load of the power system, E loss represents energy loss; 1 ,λ 2 ,λ 3 They represent the weight coefficients used to measure the system economic benefits, system stability and system efficiency respectively;

[0191] According to the action with the largest corresponding reward value, the target load balancing measure and the target charging and discharging operation measure are determined.

[0192] In some embodiments, an embodiment of the present application provides a non-volatile computer-readable storage medium, in which one or more programs including execution instructions are stored, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute the steps of any of the above-mentioned data analysis methods for optimizing regional power resource supply in the present application.

[0193] In some embodiments, the embodiments of the present application also provide a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer performs any step of the above-mentioned data analysis method for optimizing regional power resource supply.

[0194] In some embodiments, the embodiments of the present application also provide an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of a data analysis method for optimizing regional power resource supply.

[0195] Figure 6 is a hardware structure diagram of an electronic device for executing a data analysis method for optimizing regional power resource supply provided by another embodiment of the present application, such as Figure 6 As shown, the device includes:

[0196] One or more processors 610 and memory 620, Figure 6 A processor 610 is taken as an example.

[0197] The device for executing the data analysis method for optimizing regional power resource supply may further include: an input device 630 and an output device 640 .

[0198] The processor 610, the memory 620, the input device 630 and the output device 640 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0199] The memory 620, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the data analysis method for optimizing regional power resource supply in the embodiment of the present application. The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 620, that is, implements the data analysis method for optimizing regional power resource supply in the above method embodiment.

[0200] The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 620 may optionally include a memory remotely arranged relative to the processor 610, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0201] The input device 630 can receive input digital or character information and generate signals related to user settings and function control of the electronic device. The output device 640 can include a display device such as a display screen.

[0202] The one or more modules are stored in the memory 620, and when executed by the one or more processors 610, perform the data analysis method for optimizing regional power resource supply in any of the above method embodiments.

[0203] The above-mentioned product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of the present application.

[0204] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0205] (1) Mobile communication equipment: This type of equipment is characterized by having mobile communication functions and its main purpose is to provide voice and data communications. This type of terminal includes: smart phones, multimedia phones, functional phones, and low-end phones.

[0206] (2) Ultra-mobile personal computer devices: These devices belong to the category of personal computers, have computing and processing functions, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, etc.

[0207] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players, handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0208] (4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.

[0209] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0210] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0211] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data analysis method for optimizing regional power resource supply, include: Obtaining substation operation timing data and energy storage station operation timing data corresponding to the first historical time period of the target area node to be analyzed; The data types of the substation operation time series data include: load records, peak and valley loads, operation costs, equipment status data and historical maintenance records; the data types of the energy storage station operation time series data include: charge and discharge records, equipment status, remaining capacity, operation costs, electricity market prices and weather data; Inputting the substation operation timing data into a substation dispatch optimization model to determine preliminary load balancing measures corresponding to a second time period in the future; the substation dispatch optimization model adopts a multi-objective optimization model; Inputting the energy storage station operation timing data and the weather forecast information corresponding to the second time period into the energy storage station scheduling optimization model to determine preliminary charging and discharging operation measures corresponding to the second time period; The energy storage station scheduling optimization model adopts a time series prediction model; Inputting the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charge-discharge operation measures into a comprehensive optimization model to determine a target load balancing measure and a target charge-discharge operation measure corresponding to the second time period; The comprehensive optimization model of the measures includes a data preprocessing layer, a graph neural network layer, a feature fusion layer and a reinforcement learning layer; The data preprocessing layer is used to preprocess the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures to obtain corresponding first timing characteristics, second timing characteristics, first measure characteristics and second measure characteristics; The first time series feature and the second time series feature are input into the graph neural network layer to obtain corresponding substation dependency features and energy storage station dependency features, respectively, including: Based on the first time series feature and the second time series feature, a graph structure is constructed; the graph structure includes a plurality of graph nodes and edges; each of the graph nodes is defined by the time series feature of the corresponding substation or energy storage station, and each of the edges is defined by the substation and energy storage station having a power connection relationship; Based on the graph neural network layer, the feature vector of each graph node is iteratively updated to gradually integrate the information of neighboring nodes and extract global features, thereby obtaining the substation dependency features and energy storage station dependency features corresponding to each graph node: Initialize the feature vector of each graph node i x i Represents the time series characteristics of the substation or energy storage station corresponding to the graph node i; At each layer l, each graph node i receives information from its neighbor nodes N(i) and aggregates: In the formula, is the message of graph node i at layer l+1, w ij represents the edge weight corresponding to the edge connecting graph node i and graph node j, is the feature vector of graph node i at layer l+1, W (l) and b (l) is the weight and bias of the lth layer, σ is the activation function; Iterative updates are performed through multi-layer graph neural network layers, gradually integrating global information to obtain the final node feature vector: Where L is the number of graph neural network layers, H i is the final feature vector of graph node i, which is used to determine the corresponding substation dependency feature or energy storage station dependency feature; The feature fusion layer is used to fuse the substation dependency feature, the energy storage station dependency feature, the first measure feature, and the second measure feature to obtain a comprehensive feature representation: H fusion =Concat(H GNN-substation ,H GNN-storage ,F substation ,F storage ) In the formula, H fusion represents the comprehensive feature vector, H GNN-substation represents the substation dependency characteristics, H GNN-storage represents the energy storage station dependency characteristics, F substation represents the first measure feature, F storage represents the second measure characteristic; Processing the comprehensive feature representation based on the reinforcement learning layer to determine corresponding target load balancing measures and target charging and discharging operation measures specifically includes: Each state in the state space of the reinforcement learning layer is defined by the following formula: s=H fusion Where s represents the state of the reinforcement learning layer, which is defined by the corresponding comprehensive feature representation; The strategy update formula is: π(a|s)=softmax(W π ·s+b π ) Where π(a|s) represents the strategy of the reinforcement learning layer, which indicates the probability of selecting action a in state s; a is defined by the corresponding load adjustment amplitude and charge / discharge operation amplitude; W π and b π Represent the strategy weight matrix and strategy bias vector respectively; The reward function is: In the formula, R represents the reward value, P profit represents the overall benefit of the power system, P cost Represents the operating cost of the power system; L balanced represents the regional power load after load balancing adjustment, L total Represents the total load of the power system, E loss represents energy loss; 1 ,λ 2 ,λ 3 They represent the weight coefficients used to measure the system economic benefits, system stability and system efficiency respectively; According to the action with the largest corresponding reward value, the target load balancing measure and the target charging and discharging operation measure are determined.

2. The method according to claim 1, in, The substation dispatch optimization model adopts the enhanced particle swarm optimization PSO algorithm and is used to determine the load balancing measures in the following ways: Initialize K sub-populations, each of which contains multiple particles, the dimension of each particle is D, and randomly initialize the initial position of each particle and initial velocity The position of the particle is defined by the load distribution value of the substation, and the velocity of the particle represents the moving speed and direction of the particle in the search space; Set the maximum number of iterations T max and the frequency of information exchange between subgroups T exchange , and perform independent PSO searches for each sub-population to update the velocities and positions of each particle in the sub-population: The particle velocity update formula used in the global search phase is: v i,j (t+1)=ω·v i,j (t)+η·(p i,j (t)-x i,j (t))+μ·(x rand,j (t)-x i,j (t)) Where ω is the inertia weight, w max and w min is the initial and minimum inertia weight, t is the current iteration number, T max is the maximum number of iterations; v i,j (t) represents the velocity of the i-th particle in the j-th dimension at time t, v i,j (t+1) represents the updated value of the velocity of the i-th particle in the j-th dimension at time t+1; η represents the first variation factor, which is used to increase the diversity of particles and help escape from the local optimum; p i,j (t) is the value of the historical optimal position of the i-th particle in the j-th dimension; x i,j (t) represents the value of the current position of the i-th particle in the j-th dimension at time t; μ represents the second variation factor, which is used to introduce random components to further increase the diversity of particles; x rand,j (t) represents the value of the randomly selected particle position at time t in the jth dimension; The particle velocity update formula used in the local search phase is: v i,j (t+1)=α·v i,j (t)+β·(p i,j (t)-x i,j (t))+γ·(g j (t)-x i,j (t)) In the formula, α, β, and γ are convergence factors, which control the ratio of inertia weight, individual cognition, and social cognition respectively; in the formula, α represents the first convergence factor, which is used to control the inertia weight and affect the ratio of particle velocity maintenance; β represents the second convergence factor, which is used to control the ratio of individual cognition and affect the role of the particle's own historical optimal position; γ represents the third convergence factor, which is used to control the ratio of social cognition and affect the role of the particle group's historical optimal position; g j (t) represents the value of the global optimal position in the sub-population at time t in the jth dimension; Regularly exchange optimal information between subgroups, every T exchange Perform one swap per iteration; Share the optimal solutions of each subgroup and update the global optimal position of each subgroup; In the formula, G j (t) represents the value of the global optimal position of all sub-populations in the jth dimension at time t; k represents the index of the sub-population, ranging from 1 to K, where K is the total number of sub-populations; represents the value of the global optimal position in the kth subpopulation at time t in the jth dimension; f is the fitness function, which is used to evaluate the quality of particles; The global optimal position is updated within each sub-group, and the global optimal position is updated after information exchange, and a preliminary load balancing measure is determined based on the updated global optimal position.

3. The method according to claim 1, in, The energy storage station scheduling optimization model includes a cascaded input layer, a convolutional layer, an LSTM layer, an attention layer and an output layer; The input layer is used to receive the energy storage station operation timing data and the weather forecast information; The convolution layer uses a multi-scale convolution kernel to perform a convolution operation on the input time series data and extract the corresponding multi-scale convolution features: In the formula, H conv Represents the multi-scale convolution features output by the convolution layer, and They respectively represent the weight matrix and bias term of the convolution kernel with a scale of s; S represents the convolution kernel scale set; X represents the input data matrix determined based on the operating time data of the energy storage station and the weather forecast information; The LSTM layer is used to process the multi-scale convolutional features to obtain corresponding time series modeling convolutional features: H LSTM =LSTM(H conv ) In the formula, H LSTM Represents the temporal modeling convolutional features output by the LSTM layer; The attention layer is used to process the temporal modeling convolutional features using a multi-head attention mechanism to obtain a corresponding attention context vector; e t =Concat(head 1 ,...,head h ) In the formula, e t represents the attention score at time t, and Respectively represent the weight matrix and bias term of the i-th attention head; α t represents the attention weight at time t, and c represents the attention context vector; The output layer is used to predict the initial charging and discharging operation measures corresponding to the second time period according to the attention context vector: In the formula, Indicates the charge and discharge decision value; if Then the charging operation is performed; if Then the discharge operation is performed; W decision and b decision Represent the weight matrix and bias term of the decision fully connected layer respectively; Indicates the charge and discharge strategy value, W strategy represents the strategy value conversion slope, and b strategy represents the strategy value transformation intercept.

4. The method according to claim 3, in, The loss function L of the energy storage station scheduling optimization model is: L=λ 1 ·L economic +λ 2 ·L stability +λ 3 ·L efficiency Where, L economic Represents the economic benefit loss term, L stability represents the operational stability loss term, L efficiency represents the system efficiency loss term; λ 1 ,λ 2 ,λ 3 Respectively represent the corresponding weight coefficients; In the formula, N represents the number of samples in the data sample set, D profit,i represents the power supply revenue of the energy storage station corresponding to the i-th sample, D cost,i represents the power supply and distribution operation cost of the energy storage station corresponding to the i-th sample; Where, L balanced,i represents the regional power load after load balancing corresponding to the i-th sample, L lim,i represents the regional power load extreme value corresponding to the i-th sample; In the formula, E loss,i Indicates the regional power supply energy loss value corresponding to the i-th sample.

5. A data analysis system for optimizing regional power resource supply, include: A data acquisition unit, used to acquire substation operation time sequence data and energy storage station operation time sequence data corresponding to a first time period of the history of the target area node to be analyzed; The data types of the substation operation time series data include: load records, peak and valley loads, operation costs, equipment status data and historical maintenance records; the data types of the energy storage station operation time series data include: charge and discharge records, equipment status, remaining capacity, operation costs, electricity market prices and weather data; A first measure determination unit, configured to input the substation operation timing data into a substation dispatch optimization model to determine a preliminary load balancing measure corresponding to a future second time period; The substation dispatch optimization model adopts a multi-objective optimization model; A second measure determination unit, configured to input the energy storage station operation timing data and the weather forecast information corresponding to the second time period into the energy storage station scheduling optimization model to determine preliminary charging and discharging operation measures corresponding to the second time period; The energy storage station scheduling optimization model adopts a time series prediction model; A comprehensive measures optimization unit, used for inputting the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charge-discharge operation measures into a comprehensive measures optimization model to determine a target load balancing measure and a target charge-discharge operation measure corresponding to the second time period; The comprehensive optimization model of the measures includes a data preprocessing layer, a graph neural network layer, a feature fusion layer and a reinforcement learning layer; The data preprocessing layer is used to preprocess the substation operation timing data, the energy storage station operation timing data, the preliminary load balancing measures and the preliminary charging and discharging operation measures to obtain corresponding first timing characteristics, second timing characteristics, first measure characteristics and second measure characteristics; The first time series feature and the second time series feature are input into the graph neural network layer to obtain corresponding substation dependency features and energy storage station dependency features, respectively, including: Based on the first time series feature and the second time series feature, a graph structure is constructed; the graph structure includes a plurality of graph nodes and edges; each of the graph nodes is defined by the operation data of the corresponding substation or energy storage station, and each of the edges is defined by the substation and energy storage station having a power connection relationship; Based on the graph neural network layer, the feature vector of each graph node is iteratively updated to gradually integrate the information of neighboring nodes and extract global features, thereby obtaining the substation dependency features and energy storage station dependency features corresponding to each graph node: Initialize the feature vector of each graph node i x i Represents the time series characteristics of the substation or energy storage station corresponding to the graph node i; At each layer l, each graph node i receives information from its neighbor nodes N(i) and aggregates: In the formula, is the message of graph node i at layer l+1, w ij represents the edge weight corresponding to the edge connecting graph node i and graph node j, is the feature vector of graph node i at layer l+1, W (l) and b (l) is the weight and bias of the lth layer, σ is the activation function; Iterative updates are performed through multi-layer graph neural network layers, gradually integrating global information to obtain the final node feature vector: Where L is the number of graph neural network layers, H i is the final feature vector of graph node i, which is used to determine the corresponding substation dependency feature or energy storage station dependency feature; The feature fusion layer is used to fuse the substation dependency feature, the energy storage station dependency feature, the first measure feature, and the second measure feature to obtain a comprehensive feature representation: H fusion =Concat(H GNN-substation ,H GNN-storage ,F substation ,F storage ) In the formula, H fusion represents the comprehensive feature vector, H GNN-substation represents the substation dependency characteristics, H GNN-storage represents the energy storage station dependency characteristics, F substation represents the first measure feature, F storage represents the second measure characteristic; Processing the comprehensive feature representation based on the reinforcement learning layer to determine corresponding target load balancing measures and target charging and discharging operation measures specifically includes: Each state in the state space of the reinforcement learning layer is defined by the following formula: s=H fusion Where s represents the state of the reinforcement learning layer, which is defined by the corresponding comprehensive feature representation; The strategy update formula is: π(a|s)=softmax(W π ·s+b π ) Where π(a|s) represents the strategy of the reinforcement learning layer, which indicates the probability of selecting action a in state s; a is defined by the corresponding load adjustment amplitude and charge / discharge operation amplitude; W π and b π Represent the strategy weight matrix and strategy bias vector respectively; The reward function is: In the formula, R represents the reward value, P profit represents the overall benefit of the power system, P cost Represents the operating cost of the power system; L balanced represents the regional power load after load balancing adjustment, L total Represents the total load of the power system, E loss represents energy loss; 1 ,λ 2 ,λ 3 They represent the weight coefficients used to measure the system economic benefits, system stability and system efficiency respectively; According to the action with the largest corresponding reward value, the target load balancing measure and the target charging and discharging operation measure are determined.

Citation Information

Patent Citations

  • Method, system and device for economic dispatching decision-making of electric power system and medium

    CN114358520A

  • Characterization network and deep reinforcement learning-based power distribution network voltage control method

    CN116722555A

  • Urban water network area river and lake water quality improvement and water safety guarantee method and system

    CN117236199A

Cited By

  • Industrial park multi-target collaborative optimization scheduling system and method based on artificial intelligence

    CN120146482A

  • Flexible resource scheduling decision adaptability adjusting method based on reinforcement learning

    CN120258425A