Forward supply decision-making method and system based on grid structure and load data

Abstract

The invention discloses a transfer decision-making method and system based on a grid structure and load data, and relates to the field of power system management, and the method comprises the steps: building an initial data set through collecting real-time and historical load data, power grid topology information, environment influence factors and the like, and carrying out the preprocessing of the initial data set; and then, identifying data closely related to load prediction by adopting a feature extraction technology, and predicting a future load by utilizing an LSTM (Long Short Term Memory) model. And based on the prediction result and the power grid structure, evaluating the power transfer potential between the nodes to form an evaluation report. And then, calculating the comprehensive weight of the edges between the nodes, and further finding out an optimal power transfer and supply path set. And finally, multiple groups of power transfer and supply strategies are formulated, an optimal scheme is selected for implementation through benefit evaluation, and strategy adjustment is performed according to an actual operation effect. According to the decision-making method provided by the invention, the operation efficiency of the power system is greatly improved, a powerful decision-making support tool is provided for a power operator, and the safety and the economical efficiency of the power system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of power system management, and in particular to a power supply transfer decision method and system based on grid structure and load data. Background Art

[0002] With the increasing complexity of power systems and the increasing proportion of renewable energy generation, the stable operation of power systems faces unprecedented challenges. Especially in terms of power supply and demand balance, how to effectively deal with load fluctuations and emergencies while ensuring the quality of power supply has become one of the key issues in power system management.

[0003] Although the existing LSTM-based load forecasting methods have achieved certain results in improving forecasting accuracy, there are still some limitations in practical applications. First, traditional load forecasting methods often ignore the information of the power grid topology, resulting in the prediction results failing to fully reflect the actual operating status of the power system. Second, the existing methods often rely on the knowledge of domain experts when selecting features and lack an automated feature selection mechanism, which limits the generalization ability and forecasting accuracy of the model. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a power supply transfer decision method and system based on grid structure and load data to solve the problems of inaccurate load forecasting, insufficient utilization of grid topology information, and insufficient optimization of power supply transfer strategies.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method and system for making a power transfer decision based on grid structure and load data, which includes collecting real-time load data, historical load data, grid topology information, and environmental influencing factors as an initial data set, preprocessing the initial data set, and extracting the most relevant features of the load from the preprocessed initial data set;

[0008] A real-time load forecasting model is established based on LSTM, the initial data set after feature extraction is input into the real-time load forecasting model, and the load forecasting results are output;

[0009] Based on the load forecast results, a grid topology model is established to obtain the grid information structure. Based on the grid structure information, the analysis results of the key interconnection paths are obtained. Combining the key interconnection path analysis results with the load forecast results, a node transfer potential assessment report is obtained.

[0010] The comprehensive weights of the edges between adjacent nodes are obtained by calculation, and a shortest path set is generated based on the power grid information structure and the node transfer potential assessment report. Based on the shortest path set, multiple groups of transfer power path solutions are obtained, from which the optimal transfer power strategy is selected;

[0011] Deploy and implement the optimal power supply transfer strategy, and decide whether to continue to implement the current strategy based on the feedback from the implementation results.

[0012] As a preferred solution of the power supply transfer decision method and system based on grid structure and load data described in the present invention, real-time load data, historical load data, power grid topology information, and environmental influencing factors are collected as initial data sets and preprocessed, and the preprocessing process is data cleaning and standardization;

[0013] The initial data set after preprocessing is defined as: F = [R t , H t , T g , E n ];

[0014] The feature extraction is performed on the preprocessed initial data set, and its expression is:

[0015]

[0016] Among them, X represents the final extracted features, H represents the normalization function, F represents the initial fusion function, τ represents the time variable, τ i represents the i-th time point, τ1 represents the start time of the time window, τ2 represents the end time of the time window, and N is the number of time points in the time window;

[0017] As a preferred solution of the power transfer decision method and system based on grid structure and load data described in the present invention, a real-time load prediction model is established based on LSTM, the initial data set after feature extraction is input into the real-time load prediction model for training, the real-time load data is input into the trained prediction model, the load prediction value is obtained and the load prediction result is output, and its expression is:

[0018]

[0019] Among them, Y^ represents the predicted load value, L represents the LSTM-based prediction model, and g represents the complex information filtering function;

[0020] As a preferred solution of the power transfer decision method and system based on grid structure and load data of the present invention, a grid topology model is established based on the load forecast result, and its expression is:

[0021]

[0022] Where M represents the power grid topology model, Y^ k represents the predicted load value of the kth node, Y^ l represents the predicted load value of the lth node, D k represents the electrical connection strength of the kth node, D0 represents the minimum electrical connection strength threshold, α represents the influence coefficient of the electrical connection strength, and β represents the influence coefficient of the load value;

[0023] In order to determine the critical connection path, the influence of the electrical connection strength of edge e on the weight is obtained, which is expressed as:

[0024]

[0025] Where W(e) is the weight of the edge, D l Represents the electrical connection strength of the lth node;

[0026] Find the path with the minimum total weight based on the weight of edge e, which is expressed as:

[0027]

[0028] Where W(s) represents the weight of the path, e represents an edge in the path s, and s represents the path;

[0029] After obtaining the weight W(s) of the key connection path, a set of key connection paths is defined, and its expression is:

[0030]

[0031] Among them, S represents the set of key connected paths, s represents a single path in the key connected paths, argmin represents selecting the value that minimizes the following expression, and e represents an edge in path s.

[0032] These paths are the key interconnection paths, V represents all nodes in the power grid, u represents the starting point of the path, v represents the end point of the path, and w(e) represents the weight function of edge e;

[0033] Combined with the key interconnection paths and load forecast values, the transfer potential of each node is evaluated, and a node transfer evaluation report is formed, which is expressed as follows:

[0034]

[0035] Where p represents the node transfer assessment report, Y^ start (s) represents the predicted load value at the starting point of path s, max u∈ V Y^u represents the maximum value of the predicted load among all nodes, max s′∈SW(s′) represents the maximum value of weights among all key connected paths;

[0036] As a preferred solution of the power transfer decision method and system based on grid structure and load data of the present invention, wherein: by calculating the comprehensive weight of the edges between adjacent nodes, and according to the load prediction value and the power transfer potential evaluation report result, the shortest path set is obtained;

[0037] Calculate the comprehensive weight of the edge between adjacent nodes, the expression is:

[0038]

[0039] Among them, W e represents the comprehensive weight of the edge between adjacent nodes, Y^ k represents the load forecast value of the kth node, Y^ l represents the load forecast value of the lth node, Y^ u represents the load forecast value of the u-th node, P k represents the transfer potential evaluation value of the kth node, P l represents the transfer potential evaluation value of the lth node, P avg (s′) represents the average transfer potential evaluation value of all nodes on the path, s′ is the path;

[0040] The shortest path set is obtained by the comprehensive weight of the edges between adjacent nodes, and its expression is:

[0041]

[0042] Among them, S * Represents a set of shortest paths.

[0043] As a preferred solution of the power transfer decision method and system based on grid structure and load data described in the present invention, wherein: a comprehensive benefit function is obtained, multiple groups of power transfer path plans are formulated, the benefit of each path is evaluated through the comprehensive benefit function, and the optimal power transfer strategy is obtained;

[0044] Get the comprehensive benefit function, which is expressed as:

[0045]

[0046] Among them, B(s) represents the comprehensive benefit, maxY* start (e) represents the maximum predicted load value of the starting node of edge e, maxY* end (e) represents the maximum predicted load value of the end node of edge e, P start (e) represents the transfer potential of the starting node of edge e, P end(e) The transfer potential of the end node of edge e, maxPavg represents the maximum value of the average transfer potential among all paths;

[0047] By adjusting the sum of the maximum predicted load values ​​of each node on the path, the total weight, the weight ratio, and the power ratio, B(s) is obtained. The one with the largest B(s) value is the optimal power supply path solution.

[0048] Formulate multiple groups of power transfer path plans, compare the benefits of each path through the B(s) value, and screen out the optimal power transfer strategy, which is expressed as:

[0049]

[0050] Among them, F(S*,k) represents the optimal power supply path solution, s i represents the i-th group of optimal power transfer paths, and k represents the number of optimal power transfer path solutions.

[0051] As a preferred solution of the power supply transfer decision method and system based on grid structure and load data described in the present invention, wherein: deploying and implementing the optimal power supply transfer strategy, continuously monitoring key performance indicators during the implementation process, collecting data during the implementation period, and comparing with the expected goals;

[0052] If the evaluation results show that the strategy is effective and meets all objectives, then the current strategy can continue to be executed. If the evaluation shows that the strategy does not achieve the expected results, a new optimal power supply strategy is generated. The new strategy needs to go through the deployment and evaluation process again until a solution that meets all requirements is found.

[0053] In a second aspect, the present invention provides a power transfer decision system based on grid structure and load data, including a data acquisition module, which is responsible for collecting real-time load data, historical load data, grid topology information and environmental influencing factor data;

[0054] A data preprocessing module, which performs cleaning and normalization preprocessing operations on the collected first data set for subsequent processing;

[0055] Feature extraction module, which is used to extract the most relevant features for load forecasting from the preprocessed data set;

[0056] The real-time load forecasting model building module uses the long short-term memory network (LSTM) to build a real-time load forecasting model, and inputs the feature-extracted data into the model to obtain the load forecasting results;

[0057] The power grid topology modeling module establishes a power grid topology model based on load forecasting results and power grid topology information;

[0058] The node transfer potential assessment module assesses the transfer potential of each node in the power grid and forms a node transfer potential assessment report;

[0059] The power transfer path optimization module calculates the shortest path set based on the power grid topology model and the node power transfer potential assessment report, thereby obtaining multiple sets of power transfer path solutions and evaluating the optimal power transfer strategy;

[0060] The strategy implementation and feedback module is responsible for deploying and implementing the optimal power supply strategy, and providing feedback based on the implementation results to determine whether it is necessary to continue to execute the current strategy or regenerate the strategy.

[0061] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the power transfer decision method and system based on grid structure and load data as described in the first aspect of the present invention is implemented.

[0062] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the power transfer decision method and system based on grid structure and load data as described in the first aspect of the present invention is implemented.

[0063] The beneficial effects of the present invention are as follows: by preprocessing the initial data sets such as real-time and historical load data, the data quality is improved, ensuring the accuracy of subsequent analysis and the generalization ability of the model. Secondly, the use of the LSTM model for real-time load forecasting not only improves the prediction accuracy, but also enhances the timeliness of decision-making and the effective allocation of resources. Furthermore, based on the prediction results, a power grid topology model is constructed, combined with key interconnection path analysis, and the transfer potential of each node is evaluated, which not only improves the security of the power grid, but also realizes intelligent scheduling. Finally, by calculating the comprehensive weight and evaluating the comprehensive benefits, the optimal power transfer strategy is screened and implemented, which effectively reduces the operating cost and improves the flexibility and adaptability of the system. In general, the decision-making method provided by the present invention greatly improves the operating efficiency of the power system, provides a powerful decision-making support tool for power operators, and significantly improves the safety and economy of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0065] Figure 1This is a flow chart of the power transfer decision method and system based on grid structure and load data in Example 1.

[0066] Figure 2 This is a decision diagram for determining whether the power transfer strategy is the optimal strategy after implementation in Example 1. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0068] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0069] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0070] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a power transfer decision method and system based on grid structure and load data, including the following steps:

[0071] S1, collect real-time load data, historical load data, power grid topology information, and environmental influencing factors as the initial data set, and perform preprocessing. The preprocessing process is data cleaning and standardization;

[0072] The process of data cleaning is as follows: outlier detection and processing, identifying outliers through statistical analysis or visualization methods, and deciding whether to remove or correct these outliers according to the specific situation; missing value filling, using interpolation, mean method, and median method to fill missing data to ensure data integrity; duplicate data removal, identifying and removing duplicate data records by setting unique identifiers or using data deduplication tools; consistency check to ensure that the data format is unified;

[0073] The process of data standardization is: normalization, scaling the data to between 0 and 1, or a fixed range; regularization, in some cases, the data also needs to be regularized to reduce overfitting during model training.

[0074] The initial data set after preprocessing is defined as: F = [R t , Ht , T g , E n ];

[0075] The feature extraction is performed on the preprocessed initial data set, and its expression is:

[0076]

[0077] Among them, X represents the final extracted features, H represents the normalization function, F represents the initial fusion function, τ represents the time variable, τ i represents the i-th time point, τ1 represents the start time of the time window, τ2 represents the end time of the time window, and N is the number of time points in the time window;

[0078] S2. Establish a real-time load forecasting model based on LSTM. Input the initial data set after feature extraction into the real-time load forecasting model for training. During the training process, the model will continuously adjust its internal parameters to minimize the difference between the predicted results and the actual load data. Adjust the model's hyperparameters, such as learning rate and batch size, according to the performance of the validation set to optimize the model performance. Select a suitable loss function, such as mean square error or mean absolute error, to evaluate the gap between the model's predicted results and the actual values.

[0079] Use real-time load data to input the trained prediction model, obtain the load prediction value and output the load prediction result. The expression is:

[0080]

[0081] Among them, Y^ represents the predicted load value, L represents the LSTM-based prediction model, and g represents the complex information filtering function;

[0082] After training, the model can receive new feature vectors as input and output predicted load values ​​Y^. These prediction results can be used for subsequent grid topology modeling and power supply strategy formulation.

[0083] S3. Establishing a grid topology model is an important step in power system management and dispatching. It is crucial for the operation, maintenance and optimization of the power system. By establishing a grid topology model, we can have a clearer understanding of the connection mode of the grid and the location of key nodes. The topology model can help power companies better understand the direction and path of power flow.

[0084] The grid topology model is established based on the load forecast results, and its expression is:

[0085]

[0086] Where M represents the power grid topology model, Y^ k represents the predicted load value of the kth node, Y^ l represents the predicted load value of the lth node, D k represents the electrical connection strength of the kth node, D0 represents the minimum electrical connection strength threshold, α represents the influence coefficient of the electrical connection strength, and β represents the influence coefficient of the load value;

[0087] In order to determine the key interconnection path, we must first obtain the impact of the electrical connection strength of edge e on the weight. This step is of great significance for determining the key interconnection path, such as quantifying the electrical connection strength. The electrical connection strength reflects the degree of connection between two nodes in the power grid. By converting the electrical connection strength into a weight, the degree of connection can be quantified; the path selection can also be optimized. By assigning weights to the edges, the path selection can be optimized based on the electrical connection strength. Paths with lower weights (i.e., higher electrical connection strengths) are more likely to be selected as key interconnection paths, which means that when transferring power, paths with high electrical connection strengths are preferred because these paths are more stable and reliable; obtaining the impact of the electrical connection strength of edge e on the weight can also improve the efficiency of power transfer. When determining the key interconnection path, taking into account the weight of the electrical connection strength can improve the efficiency and success rate of power transfer. Selecting a path with high electrical connection strength can reduce the loss during power transmission, thereby improving the overall efficiency of the power system. The impact of the electrical connection strength of edge e on the weight is expressed as:

[0088]

[0089] Where W(e) is the weight of the edge, D l Represents the electrical connection strength of the lth node;

[0090] After obtaining the influence of the electrical connection strength of edge e on the weight, it is also necessary to obtain the weight of path S, which comprehensively considers factors such as the electrical connection strength of each edge in the path and is used to measure the importance or priority of the path.

[0091] Find the path with the minimum total weight based on the weight of edge e, which is expressed as:

[0092]

[0093] Where W(s) represents the weight of the path, e represents an edge in the path s, and s represents the path;

[0094] After obtaining the weight W(s) of the key connection path, a set of key connection paths is defined, and its expression is:

[0095]

[0096] Among them, S represents the set of key connected paths, s represents a single path in the key connected paths, argmin represents selecting the value that minimizes the following expression, and e represents an edge in path s.

[0097] These paths are the key interconnection paths, V represents all nodes in the power grid, u represents the starting point of the path, v represents the end point of the path, and w(e) represents the weight function of edge e;

[0098] Critical interconnection paths are one of the most important paths in the power grid. They usually have higher electrical connection strength and more stable transmission capacity. By identifying these paths, they can be given priority when transferring power, thereby improving the efficiency of power transmission and reducing power loss. And the identification of critical interconnection paths helps to enhance the security of the power grid. These paths are usually more stable and can withstand higher loads, thus reducing the possibility of failure.

[0099] Combined with the key interconnection paths and load forecast values, the transfer potential of each node is evaluated, and a node transfer evaluation report is formed, which is expressed as follows:

[0100]

[0101] Where p represents the node transfer assessment report, Y^ start (s) represents the predicted load value at the starting point of path s, max u∈ V Y^u represents the maximum value of the predicted load among all nodes, max s′∈S W(s′) represents the maximum value of weights among all key connected paths;

[0102] The value range of P is [0,1]. The closer the value of P is to 1, the higher the node transfer potential is. The closer the value of P is to 0, the lower the node transfer potential is.

[0103] The node transfer assessment report evaluates the transfer potential of each node in the power grid by comprehensively considering various factors, such as load forecast results, grid topology, electrical connection strength, etc. Through the assessment report, it can be identified which nodes are more suitable as source nodes or target nodes for power transfer, which helps power companies to formulate more efficient power transfer strategies and improve the efficiency and reliability of power transmission. The assessment report provides power companies with information about which nodes in the power grid have high transfer potential, which is very important for long-term planning.

[0104] Based on this information, power companies can predict future load growth trends and make grid expansion or transformation plans accordingly to ensure the sustainable development of the power system.

[0105] S4. By calculating the comprehensive weights of the edges between adjacent nodes and according to the load forecast value and the results of the transfer potential assessment report, the shortest path set is obtained;

[0106] The comprehensive weight takes into account multiple factors such as electrical connection strength, load forecast value, and transfer potential assessment value. Edges with lower comprehensive weights usually represent edges with higher electrical connection strength, lower load forecast value, and higher transfer potential assessment value. The comprehensive weight of edges between adjacent nodes is calculated as follows:

[0107]

[0108] Among them, W e represents the comprehensive weight of the edge between adjacent nodes, Y^ k represents the load forecast value of the kth node, Y^ l represents the load forecast value of the lth node, Y^ u represents the load forecast value of the u-th node, P k represents the transfer potential evaluation value of the kth node, P l represents the transfer potential evaluation value of the lth node, P avg (s′) represents the average transfer potential evaluation value of all nodes on the path, s′ is the path;

[0109] Selecting a path from the shortest path set can develop a more efficient power supply strategy, improve the efficiency of power transmission, make more effective use of grid resources, and help reduce unnecessary resource waste. The shortest path set is obtained by the comprehensive weight of the edges between adjacent nodes, and its expression is:

[0110]

[0111] Among them, S * Represents a set of shortest paths.

[0112] It not only helps optimize power transfer strategies, improve power transfer efficiency, and enhance grid stability, but also supports more effective decision-making, optimizes resource allocation, and improves safety.

[0113] S5. Obtain a comprehensive benefit function, formulate multiple groups of power transfer path plans, evaluate the benefits of each path through the comprehensive benefit function, and obtain the optimal power transfer strategy;

[0114] The comprehensive benefit function plays an important role in determining the optimal power supply strategy. It comprehensively considers the maximum predicted load value of each node on the path, the total weight of the path, the weight ratio, the power ratio and other factors, and provides a comprehensive benefit evaluation for each path. Selecting the path with the largest comprehensive benefit value as the optimal path can ensure the efficiency and reliability of power transmission and obtain the comprehensive benefit function, which is expressed as follows:

[0115]

[0116] Among them, B(s) represents the comprehensive benefit, maxY* start (e) represents the maximum predicted load value of the starting node of edge e, maxY* end (e) represents the maximum predicted load value of the end node of edge e, P start (e) represents the transfer potential of the starting node of edge e, P end (e) The transfer potential of the end node of edge e, maxPavg represents the maximum value of the average transfer potential among all paths;

[0117] By adjusting the sum of the maximum predicted load values ​​of each node on the path, the total weight, the weight ratio, and the power ratio, B(s) is obtained. The one with the largest B(s) value is the optimal power supply path solution.

[0118] Formulate multiple groups of power transfer path plans, compare the benefits of each path through the B(s) value, and screen out the optimal power transfer strategy, which is expressed as:

[0119]

[0120] Among them, F(S*,k) represents the optimal power supply path solution, s i represents the i-th group of optimal power transfer paths, and k represents the number of optimal power transfer path solutions.

[0121] To further illustrate, the comprehensive benefit of each path is calculated, multiple groups of optimal power transfer path solutions are generated, and finally the optimal power transfer path solution is obtained from the multiple groups of solutions.

[0122] S6. Obtain the optimal power supply path plan through comprehensive benefits, deploy and implement the optimal power supply strategy, continuously monitor key performance indicators during implementation, such as grid load balance, power quality, and transmission loss rate, collect data during implementation, and compare with expected targets to determine whether actual performance meets expectations;

[0123] The evaluation results show that the strategy is effective and meets all objectives. It analyzes whether the predetermined benefit standards and performance indicators have been achieved. If the current strategy can continue to be implemented, if the evaluation shows that the strategy has not achieved the expected results, a new optimal power supply strategy is generated. The new strategy needs to go through the deployment and evaluation process again until a solution that meets all requirements is found.

[0124] This is an iterative optimization process that aims to improve the effectiveness of the power transfer strategy through continuous testing, monitoring and adjustment. Each cycle aims to gradually improve the power transfer plan to ensure that the power system can operate efficiently and reliably. This approach is particularly suitable for dynamically changing environments because power demand and grid conditions change over time and seasons.

[0125] This embodiment also provides a power transfer decision system based on grid structure and load data, including:

[0126] Data acquisition module, which is responsible for collecting real-time load data, historical load data, power grid topology information and environmental influencing factor data;

[0127] A data preprocessing module, which performs cleaning and normalization preprocessing operations on the collected first data set for subsequent processing;

[0128] Feature extraction module, which is used to extract the most relevant features for load forecasting from the preprocessed data set;

[0129] The real-time load forecasting model building module uses the long short-term memory network (LSTM) to build a real-time load forecasting model, and inputs the feature-extracted data into the model to obtain the load forecasting results;

[0130] The power grid topology modeling module establishes a power grid topology model based on load forecasting results and power grid topology information;

[0131] The node transfer potential assessment module assesses the transfer potential of each node in the power grid and forms a node transfer potential assessment report;

[0132] The power transfer path optimization module calculates the shortest path set based on the power grid topology model and the node power transfer potential assessment report, thereby obtaining multiple sets of power transfer path solutions and evaluating the optimal power transfer strategy;

[0133] The strategy implementation and feedback module is responsible for deploying and implementing the optimal power supply strategy, and providing feedback based on the implementation results to determine whether it is necessary to continue to execute the current strategy or regenerate the strategy.

[0134] This embodiment also provides a computer device, which is suitable for the case of a power transfer decision method and system based on grid structure and load data, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the power transfer decision method and system based on grid structure and load data as proposed in the above embodiment.

[0135] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. 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 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 achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0136] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method and system for implementing a power supply decision-making method based on grid structure and load data as proposed in the above embodiment are implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0137] In summary, the present invention realizes the monitoring and understanding of user behavior through the analysis of user file operation behavior, can accurately capture the user's operation habits and behavior patterns, provide basic data for the subsequent generation of encryption strategies, and also help the system to detect and prevent abnormal behaviors; predict the user's future operations according to the user's behavior habits, so as to formulate encryption strategies more intelligently; more accurately protect user privacy, reduce the risk of data leakage, and improve the data security and confidentiality of the system; the present invention better adapts to the user's operation habits and needs, improves the intelligence level of the encryption algorithm and user experience, and enhances the flexibility and adaptability of the system.

[0138] Example 2 is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of a power transfer decision method and system based on grid structure and load data are provided.

[0139] In order to verify the effectiveness of the power transfer decision method based on grid structure and load data, the following examples were carried out. First, an experimental environment was constructed by simulating a medium-sized regional power grid system. The power grid system contains 30 nodes, including power stations, substations and user nodes. In addition, historical load data and real-time load data for the past year were collected, as well as the topological information of the power grid and environmental influencing factor data. Based on these data, the following steps were carried out:

[0140] Data collection and preprocessing:

[0141] Real-time load data, historical load data, grid topology information and environmental influencing factors data were collected every hour throughout 2023.

[0142] The data were cleaned and standardized to remove outliers and missing values ​​and to normalize all data to the same dimension.

[0143] Feature extraction:

[0144] Applying Expressions

[0145]

[0146] Feature extraction is performed on the preprocessed data set, where τ represents the time variable and N is the number of data points in the time window.

[0147] Real-time load forecasting model construction:

[0148] A real-time load forecasting model was established based on LSTM, and the data after feature extraction was input into the model for training.

[0149] Use real-time load data to input the trained prediction model to obtain the load prediction value Y^.

[0150] Grid topology modeling and node transfer potential assessment:

[0151] A power grid topology model is established based on load forecasting results and power grid topology information.

[0152] Calculate the transfer potential of each node and form a node transfer potential assessment report.

[0153] Power supply path optimization:

[0154] By calculating the comprehensive weights of the edges between adjacent nodes, the shortest path set is generated based on the power grid information structure and the node transfer potential assessment report.

[0155] Based on the shortest path set, multiple groups of power supply path solutions are obtained, and the optimal power supply strategy is screened out.

[0156] Strategy implementation and feedback:

[0157] Deploy and implement the optimal power supply transfer strategy, and decide whether to continue to execute the current strategy or regenerate the strategy based on the feedback of the implementation results.

[0158] In order to further quantify the effect of the above process, an experiment was designed to compare the performance of the prior art and the method of the present invention. The experiment set up two control groups (prior art A and B) and two experimental groups (inventive method C and D).

[0159] The details are shown in the following table:

[0160]

[0161] It can be seen from the above table that the inventive methods C and D show significant advantages in many aspects compared with the prior arts A and B.

[0162] Real-time prediction error:

[0163] The real-time prediction errors of the inventive methods C and D are 3.2% and 2.9% respectively, which are much lower than 7.5% and 6.8% of the prior art A and B. This shows that the inventive method can predict the load more accurately and help improve the accuracy of power dispatching.

[0164] Power supply path efficiency:

[0165] The power transfer efficiency of the invention methods C and D is 1.8 kWh / km and 1.7 kWh / km respectively, while that of the prior art methods A and B is 2.3 kWh / km and 2.2 kWh / km respectively. Lower power transfer efficiency means less energy loss and higher transmission efficiency.

[0166] Reduction of power supply cost:

[0167] Inventive methods C and D achieved cost reductions of 20% and 25% respectively, while prior art methods A and B did not achieve cost reductions. This means that the adoption of the inventive method can significantly reduce the operating costs of power companies.

[0168] Comprehensive benefit function B(s):

[0169] The comprehensive benefit functions B(s) of the inventive methods C and D are 1.20 and 1.25, respectively, which are higher than 0.75 and 0.80 of the prior art A and B. This indicates that the inventive methods can provide better overall benefits, including but not limited to energy efficiency and cost savings.

[0170] In summary, it can be seen from the experimental data that the inventive methods C and D not only improve the accuracy of load forecasting, but also perform well in terms of power transfer path efficiency and cost savings. This proves that the inventive method has significant technical advantages and practical value compared to the prior art, especially for modern power grids that require efficient energy management.

[0171] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power transfer decision method based on grid structure and load data, characterized in that: include: Collect real-time load data, historical load data, power grid topology information, and environmental influencing factors as the initial data set, preprocess the initial data set, and extract the most relevant features of the load from the preprocessed initial data set; A real-time load forecasting model is established based on LSTM, the initial data set after feature extraction is input into the real-time load forecasting model, and the load forecasting results are output; Based on the load forecast results, a grid topology model is established to obtain the grid information structure. Based on the grid structure information, the analysis results of the key interconnection paths are obtained. Combining the key interconnection path analysis results with the load forecast results, a node transfer potential assessment report is obtained. The comprehensive weights of the edges between adjacent nodes are obtained by calculation, and a shortest path set is generated based on the power grid information structure and the node transfer potential assessment report. Based on the shortest path set, multiple groups of transfer power path solutions are obtained, from which the optimal transfer power strategy is selected; Deploy and implement the optimal power supply transfer strategy, and decide whether to continue to implement the current strategy based on the feedback from the implementation results.

2. The power transfer decision method based on grid structure and load data according to claim 1, characterized in that: Collect real-time load data, historical load data, power grid topology information, and environmental factors as the initial data set and perform preprocessing. The preprocessing process includes data cleaning and standardization. The initial data set after preprocessing is defined as: F = [R t , H t , T g , E n ]; The feature extraction is performed on the preprocessed initial data set, and its expression is: Among them, X represents the final extracted features, H represents the normalization function, F represents the initial fusion function, τ represents the time variable, τ i represents the i-th time point, τ1 represents the start time of the time window, τ2 represents the end time of the time window, and N is the number of time points in the time window.

3. The power transfer decision method based on grid structure and load data according to claim 2, characterized in that: A real-time load forecasting model is established based on LSTM. The initial data set after feature extraction is input into the real-time load forecasting model for training. The real-time load data is input into the trained forecasting model to obtain the load forecast value and output the load forecast result. The expression is: Among them, Y^ represents the predicted load value, L represents the LSTM-based prediction model, and g represents the complex information filtering function.

4. The power transfer decision method based on grid structure and load data according to claim 3, characterized in that: The grid topology model is established based on the load forecast results, and its expression is: Where M represents the power grid topology model, Y^ k represents the predicted load value of the kth node, Y^ l represents the predicted load value of the lth node, D k represents the electrical connection strength of the kth node, D0 represents the minimum electrical connection strength threshold, α represents the influence coefficient of the electrical connection strength, and β represents the influence coefficient of the load value; In order to determine the critical connection path, the influence of the electrical connection strength of edge e on the weight is obtained, which is expressed as: Where W(e) is the weight of the edge, D l Represents the electrical connection strength of the lth node; Find the path with the minimum total weight based on the weight of edge e, which is expressed as: Where W(s) represents the weight of the path, e represents an edge in the path s, and s represents the path; After obtaining the weight W(s) of the key connection path, a set of key connection paths is defined, and its expression is: Among them, S represents the set of key connected paths, s represents a single path in the key connected paths, argmin represents selecting the value that minimizes the following expression, and e represents an edge in path s. These paths are the key interconnection paths, V represents all nodes in the power grid, u represents the starting point of the path, v represents the end point of the path, and w(e) represents the weight function of edge e; Combined with the key interconnection paths and load forecast values, the transfer potential of each node is evaluated, and a node transfer evaluation report is formed, which is expressed as follows: Where p represents the node transfer assessment report, Y^ start (s) represents the predicted load value at the starting point of path s, max u∈V Y^u represents the maximum value of the predicted load among all nodes, max s′∈S W(s′) represents the maximum value of weights among all key connection paths.

5. The power transfer decision method based on grid structure and load data according to claim 4, characterized in that: By calculating the comprehensive weights of the edges between adjacent nodes and based on the load forecast value and the transfer potential assessment report results, the shortest path set is obtained; Calculate the comprehensive weight of the edge between adjacent nodes, the expression is: Among them, W e represents the comprehensive weight of the edge between adjacent nodes, Y^ k represents the load forecast value of the kth node, Y^ l represents the load forecast value of the lth node, Y^ u represents the load forecast value of the u-th node, P k represents the transfer potential evaluation value of the kth node, P l represents the transfer potential evaluation value of the lth node, P avg (s′) represents the average transfer potential evaluation value of all nodes on the path, s′ is the path; The shortest path set is obtained by the comprehensive weight of the edges between adjacent nodes, and its expression is: Among them, S * Represents a set of shortest paths.

6. The power transfer decision method based on grid structure and load data according to claim 5, characterized in that: Obtain a comprehensive benefit function, formulate multiple groups of power transfer path plans, evaluate the benefits of each path through the comprehensive benefit function, and obtain the optimal power transfer strategy; Get the comprehensive benefit function, which is expressed as: Among them, B(s) represents the comprehensive benefit, maxY* start (e) represents the maximum predicted load value of the starting node of edge e, maxY* end (e) represents the maximum predicted load value of the end node of edge e, P start (e) represents the transfer potential of the starting node of edge e, P end (e) The transfer potential of the end node of edge e, maxPavg represents the maximum value of the average transfer potential among all paths; By adjusting the sum of the maximum predicted load values ​​of each node on the path, the total weight, the weight ratio, and the power ratio, B(s) is obtained. The one with the largest B(s) value is the optimal power supply path solution. Formulate multiple groups of power transfer path plans, compare the benefits of each path through the B(s) value, and screen out the optimal power transfer strategy, which is expressed as: Among them, F(S*,k) represents the optimal power supply path solution, s i represents the i-th group of optimal power transfer paths, and k represents the number of optimal power transfer path solutions.

7. The power transfer decision method based on grid structure and load data according to claim 6, characterized in that: Deploy and implement the optimal power supply transfer strategy, continuously monitor key performance indicators during implementation, collect data during implementation, and compare with expected goals; If the evaluation results show that the strategy is effective and meets all objectives, then the current strategy can continue to be executed. If the evaluation shows that the strategy does not achieve the expected results, a new optimal power supply strategy is generated. The new strategy needs to go through the deployment and evaluation process again until a solution that meets all requirements is found.

8. A power transfer decision system based on grid structure and load data, based on the power transfer decision method and system based on grid structure and load data according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, which is responsible for collecting real-time load data, historical load data, power grid topology information and environmental influencing factor data; A data preprocessing module, which performs cleaning and normalization preprocessing operations on the collected first data set for subsequent processing; Feature extraction module, which is used to extract the most relevant features for load forecasting from the preprocessed data set; The real-time load forecasting model building module uses the long short-term memory network (LSTM) to build a real-time load forecasting model, and inputs the feature-extracted data into the model to obtain the load forecasting results; The power grid topology modeling module establishes a power grid topology model based on load forecasting results and power grid topology information; The node transfer potential assessment module assesses the transfer potential of each node in the power grid and forms a node transfer potential assessment report; The power transfer path optimization module calculates the shortest path set based on the power grid topology model and the node power transfer potential assessment report, thereby obtaining multiple sets of power transfer path solutions and evaluating the optimal power transfer strategy; The strategy implementation and feedback module is responsible for deploying and implementing the optimal power supply strategy, and providing feedback based on the implementation results to determine whether it is necessary to continue to execute the current strategy or regenerate the strategy.

9. 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 power transfer decision method and system based on grid structure and load data are implemented as described in any one of claims 1 to 7.

10. 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 power transfer decision method and system based on grid structure and load data described in any one of claims 1 to 7 are implemented.

Images