Power system flexible resource scheduling control method and system based on graph database

Abstract

The invention discloses a power system flexible resource scheduling control method and system based on a graph database, and relates to the technical field of resource scheduling control, and the method comprises the following steps: constructing a power system topological graph model based on the graph database, and dividing an initial section boundary region through a shortest path algorithm; constructing a dynamic boundary model, and recognizing an abnormal section area in combination with a preset power flow equation; obtaining a candidate capacity boundary set; under a plurality of preset disturbance scales, filtering disturbance is carried out on the candidate capacity boundary set to obtain a plurality of capacity response values, and an optimal credible capacity boundary is determined; and updating the optimal credible capacity boundary to the graph database, and generating a core flexible resource scheduling instruction for resource scheduling. The problem that a closed loop mechanism from capacity boundary analysis to graph database updating and scheduling instruction generation is not established in traditional scheduling, so that capacity boundary information cannot effectively guide scheduling decisions is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource scheduling and control, and more specifically, to a method and system for flexible resource scheduling and control of a power system based on a graph database. Background Art

[0002] Flexible resource dispatch in the power system, a key component in ensuring the safe and stable operation of the power grid, undertakes the core tasks of coordinating power generation and load, maintaining grid power balance, and improving system responsiveness and stability. With the large-scale integration of renewable energy sources such as wind power and photovoltaics, the grid operating environment has become increasingly complex and volatile, significantly increasing system volatility and uncertainty. Furthermore, the diversification of modern power load structures, such as the integration of electric vehicle charging, large-scale energy storage facilities, and distributed power sources, has further exacerbated the operational complexity and dispatching difficulties of the power system.

[0003] Traditional dispatching methods mainly rely on static models and empirical rules, and use linear programming or heuristic algorithms to make capacity allocation and dispatching decisions. However, these methods usually ignore the dynamic changes in the power system topology and the time-varying characteristics of abnormal section areas, making it difficult to fully reflect the actual operating conditions of the system, resulting in insufficient robustness and accuracy of the dispatching scheme.

[0004] For example, the invention patent announcement with the publication number CN115514014B discloses a novel power system flexibility resource supply and demand game optimization scheduling method containing a high proportion of wind power, including establishing a two-layer game architecture for flexibility regulation resource supply and demand based on master-slave game; establishing a quantitative model for flexibility regulation resource demand of wind power operators based on the quantitative index of wind power volatility; establishing an incentive price optimization decision model for upper-layer wind power operators to lower-layer energy storage operators, thermal power operators, and demand response aggregators; establishing a flexibility regulation resource supply decision model for lower-layer energy storage operators, thermal power operators, and demand response aggregators; combining the established incentive price optimization decision model with the established flexibility regulation resource supply decision model to jointly constitute a novel power system flexibility regulation resource supply and demand optimization model containing a high proportion of wind power, and solving the model. The present invention can effectively improve the enthusiasm of the source-load-storage multi-party flexibility regulation resources to participate in regulation, and promote the grid-connection and consumption of high-proportion wind power.

[0005] The above disclosed technical solutions have at least the following technical problems: Traditional power system flexible resource dispatch and control methods lack a closed-loop mechanism from capacity boundary analysis to graph database updates and dispatch instruction generation. This results in capacity boundary information being unable to effectively guide dispatch decisions, reducing dispatch accuracy and the system's adaptability. This present invention proposes a solution to this problem. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a flexible resource scheduling control method and system for a power system based on a graph database. A dynamic topology model is constructed through a graph database, and the initial section is divided in combination with an improved shortest path algorithm. The robust capacity boundary is determined through multi-objective optimization and disturbance testing, and finally an adaptive scheduling instruction is generated to solve the problem that a closed-loop mechanism from capacity boundary analysis to graph database update and scheduling instruction generation is not established in traditional scheduling, resulting in the inability of capacity boundary information to effectively guide scheduling decisions.

[0007] To achieve the above object, the present invention provides the following technical solutions: A method and system for controlling flexible resource dispatching of a power system based on a graph database includes the following steps: A power system topology model is constructed based on a graph database, and the initial section boundary area is divided using the shortest path algorithm. A dynamic boundary model is constructed based on the initial section boundary area, and the abnormal section area is identified in combination with the preset power flow equation. A multi-objective optimization function is constructed for the abnormal section area and solved using a non-dominated sorting genetic algorithm to obtain a candidate capacity boundary set. Under several preset disturbance scales, the candidate capacity boundary set is subjected to filtered disturbance to obtain several capacity response values, and a credibility evaluation function is constructed based on the matching degree between the capacity response values ​​and the preset system normal capacity threshold to determine the optimal credible capacity boundary. The optimal credible capacity boundary is updated to the graph database and a core flexible resource scheduling instruction is generated for resource scheduling.

[0008] In a preferred embodiment, the power system topology graph model is constructed based on the graph database, and the initial section boundary area is divided by the shortest path algorithm, specifically: the equipment attribute data of all nodes in the power system are obtained, and the equipment attribute data include generator capacity, load power, line impedance and node voltage level; the nodes are mapped to vertices in the graph database, the connection relationship is mapped to edges, and the vertices are hierarchically marked based on the node voltage level to construct the power system topology graph model; the Dijkstra algorithm is used to traverse the shortest path in the power system topology graph model to obtain several first shortest paths; the path feature sequence of the first shortest path is obtained based on the equipment attribute data to obtain several path feature sequences; the DTW algorithm is used to perform path screening on several path feature sequences to obtain several second shortest paths; cluster analysis is performed on several second shortest paths to divide the initial section boundary area.

[0009] In a preferred embodiment, the clustering analysis is performed on several second shortest paths to divide the initial section boundary area, specifically: the node and device attribute data in each second shortest path are constructed as a first path feature vector; based on the first path feature vector, a clustering algorithm is used to cluster several second shortest paths to obtain several path clusters; within each path cluster, a node frequency vector and an edge frequency matrix are constructed; based on the node frequency vector and the edge frequency matrix, whether each edge endpoint crosses the cluster is determined, and the number of times the endpoint appears in the path cluster is counted. If it exceeds a preset frequency threshold, it is marked as a section boundary edge; the endpoints of all section boundary edges constitute the initial section boundary area.

[0010] In a preferred embodiment, the dynamic boundary model is constructed based on the initial section boundary area, and the abnormal section area is identified in combination with the preset power flow equation, specifically: the initial section boundary area is constructed as a local response graph model, and a node power disturbance model is constructed based on the preset power flow equation; the disturbance response value of each node in the local response graph model is calculated based on the node power disturbance model to obtain the disturbance propagation matrix of each node; the power of each node is predicted using a preset neural network model to obtain a power prediction value; the residual calculation is performed on the real-time power data of each node and the power prediction value to obtain the power residual value of each node; a first power disturbance vector is constructed based on the power residual value of each node and input into the disturbance propagation matrix to obtain the response value vector of the local response graph model; data analysis is performed on the response value vector of the local response graph model to identify the abnormal section area.

[0011] In a preferred embodiment, a multi-objective optimization function is constructed for the abnormal section area and solved by a non-dominated sorting genetic algorithm to obtain a candidate capacity boundary set, specifically: based on the abnormal section area, the unit capacity compensation efficiency of the preset control node for the abnormal section area is calculated in combination with the power residual value of the node, and a regional capacity response matrix is ​​constructed; based on the regional capacity response matrix, the nodes are screened to obtain the screened nodes, and the preset maximum allowable regulation capacity of the screened nodes is used as the capacity boundary upper limit to obtain a capacity boundary variable set and optimize the capacity boundary variable set.

[0012] In a preferred embodiment, the capacity boundary variable set is optimized by constructing a multi-objective optimization function with the optimization objectives of power balance restoration in the abnormal section area, maximizing branch capacity utilization, and minimizing regulation cost; and optimizing the capacity boundary variable set using a non-dominated sorting strategy based on the multi-objective optimization function to obtain a candidate capacity boundary set, wherein the non-dominated sorting strategy includes variable initialization.

[0013] In a preferred embodiment, the candidate capacity boundary set is filtered and disturbed under several preset disturbance scales to obtain several capacity response values, specifically: historical fault data is obtained and a disturbance type set is defined, where the disturbance type set includes load surge, generator disconnection and line disconnection; the disturbance scale level of each disturbance type is set to build a disturbance scenario library; for each disturbance scenario in the disturbance scenario library, a disturbance source node is randomly selected and injected into each candidate capacity boundary in the candidate capacity boundary set to obtain several disturbance capacity boundaries; and the several disturbance capacity boundaries are based on a preset power flow response model to obtain several capacity response values.

[0014] In a preferred embodiment, the method of constructing a credibility evaluation function based on the degree of matching between the capacity response value and a preset system normal capacity threshold to determine the optimal credible capacity boundary comprises the following steps: constructing a capacity response vector for each capacity response value, performing cluster analysis on the capacity response vector using a clustering algorithm, and constructing a multi-scale response topology clustering map; constructing a credibility density function based on the multi-scale response topology clustering map using a distribution fitting algorithm; calculating the expected value of each disturbance capacity boundary based on the credibility density function, and selecting the disturbance capacity boundary with the largest expected value as the optimal credible capacity boundary.

[0015] In a preferred embodiment, the optimal trusted capacity boundary is updated to the graph database and core flexible resource scheduling instructions are generated for resource scheduling, specifically: the optimal trusted capacity boundary is parsed, and the parsed parameters are mapped to the vertex attributes of the graph database to obtain an updated graph database; based on the updated graph database, a resource scheduling instruction generation model is constructed, and the dependencies and priorities between nodes in the model are extracted through a graph neural network; a scheduling instruction sequence is generated according to the dependencies and priorities, the scheduling instructions are sent to the power system control terminal, the instruction execution effect is monitored in real time, and the capacity boundary parameters in the graph database are dynamically adjusted according to the feedback data.

[0016] The technical effects and advantages of the graph database-based power system flexible resource scheduling control method and system of the present invention are as follows: 1. This invention effectively depicts the dynamic changes in the system's operating structure by constructing a power system topology model in a graph database, combining shortest path partitioning with dynamic boundary modeling. On this basis, it introduces power flow disturbance analysis and residual calculation to identify abnormal cross-section areas and achieve precise anomaly location. Subsequently, a multi-objective optimization algorithm is used to construct an optimal scheduling model covering power balance, capacity utilization, and cost control, obtaining a set of candidate capacity boundaries. This model then filters responses under multiple disturbance scenarios, constructs a credibility evaluation function, and ultimately determines the optimal credible capacity boundary. This capacity boundary not only has high dynamic adaptability and response stability, but is also updated in real time to the graph database. Node dependencies are extracted through a graph neural network model, generating core scheduling instructions including power generation, load, and line regulation, completing a closed-loop process from analysis to control. This method overcomes the drawback of traditional scheduling methods where capacity boundary analysis results cannot be fed back to actual scheduling control, significantly improving the scientific nature, real-time nature, and robustness of scheduling decisions, and meeting the higher requirements of new power systems for flexibility, efficiency, and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of the flexible resource dispatching and control method of the power system based on the graph database of the present invention.

[0018] Figure 2 This is a structural diagram of the flexible resource dispatching and control system of the power system based on the graph database of the present invention. DETAILED DESCRIPTION

[0019] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] Example 1, Figure 1 The present invention provides a flexible resource dispatching control method for a power system based on a graph database, which includes the following steps: S1, builds a power system topology model based on the graph database and divides the initial section boundary area using the shortest path algorithm; In this example, a power system topology model is constructed based on a graph database, and the initial section boundary area is divided using the shortest path algorithm. Specifically: Acquiring device attribute data of all nodes in the power system, wherein the device attribute data includes generator capacity, load power, line impedance, and node voltage level; Nodes are mapped as vertices in a graph database, connections are mapped as edges, and vertices are hierarchically labeled based on node voltage levels to construct a power system topology model. The Dijkstra algorithm is used to traverse the shortest paths in the power system topology model and obtain several first shortest paths; Obtaining a path feature sequence of the first shortest path based on the device attribute data to obtain a plurality of path feature sequences; The DTW algorithm is used to screen several path feature sequences and obtain several second shortest paths; Cluster analysis is performed on several second shortest paths to divide the initial section boundary area.

[0021] It should be noted that the following grid node device attributes are obtained by extracting system operation data from the grid management system (such as EMS): Generator capacity (MW): For example, G1 node is 300MW, G2 is 500MW; Load power (MW): For example, load node L1 is 120MW and L2 is 80M; Node voltage level (kV): For example, N1 is 220kV, N2 is 110kV, and N3 is 35kV.

[0022] Based on the above data, the following modeling process is performed in the Neo4j graph database: Nodes are mapped to vertices: All nodes such as generators, loads, and substations are mapped to the Vertex of the graph; Connection relationships are mapped as edges: if a line connects N1 and N2, a directed edge from N1 to N2 is created in the graph; Voltage level hierarchical labeling: Add level labels to vertex attribute fields, using 220kV, 110kV, and so on as levels to facilitate hierarchical processing. At this point, a power topology model containing device characteristics and connection relationships is formed in the graph database.

[0023] Furthermore, the Dijkstra shortest path algorithm built into the graph database is used to traverse the paths between any power generation node and load node, obtaining several first shortest paths. The path feature sequences of these first shortest paths are then derived based on the device attribute data, resulting in several path feature sequences. The DTW (Dynamic Time Warping) algorithm is then used to compare the similarity between all path feature sequences, filtering out distorted paths and retaining a set of paths with high similarity as the second shortest path set.

[0024] In this example, cluster analysis is performed on several second shortest paths to divide the initial section boundary area, specifically: constructing the node and device attribute data in each second shortest path into a first path feature vector; Based on the first path feature vector, a clustering algorithm is used to cluster several second shortest paths to obtain several path clusters; Within each path cluster, construct the node frequency vector and edge frequency matrix; The node frequency vector and edge frequency matrix are used to determine whether each edge endpoint crosses clusters and count the number of times the endpoint appears in the path cluster. If the number exceeds the preset frequency threshold, it is marked as a cross-section boundary edge. The endpoints of all section boundary edges constitute the initial section boundary area.

[0025] It should be noted that each second shortest path is constructed as a path feature vector. The feature dimensions include: voltage level of each node; node type (generation / load / relay); impedance and flow direction of adjacent edges. The path feature vector is clustered using K-means or DBSCAN clustering algorithms to divide the path into several clusters. In each cluster, the following statistics are collected: Node frequency vector: the number of times each node appears in the cluster; Edge frequency matrix: the number of times each edge appears in the path.

[0026] Identify whether the two endpoints of each edge belong to different clusters. If the two endpoints of an edge span different clusters and their frequency of occurrence in the path cluster exceeds a set threshold (e.g., 30%), the edge is marked as a "section boundary edge." Ultimately, the endpoint nodes of all section boundary edges are combined to form the initial section boundary region, which serves as the basis for subsequent dynamic modeling and optimized scheduling.

[0027] S2, constructing a dynamic boundary model based on the initial section boundary area and identifying abnormal section areas in combination with the preset tidal flow equation; In this example, a dynamic boundary model is constructed based on the initial cross-section boundary area, and the abnormal cross-section area is identified in combination with the preset tidal flow equation. Specifically: The initial section boundary area is constructed as a local response diagram model, and a node power disturbance model is constructed based on the preset power flow equation; Based on the node power disturbance model, the disturbance response value of each node in the local response graph model is calculated to obtain the disturbance propagation matrix of each node; Use the preset neural network model to predict the power of each node and obtain the power prediction value; Calculate the residual between the real-time power data of each node and the power prediction value to obtain the power residual value of each node; A first power disturbance vector is constructed based on the power residual value of each node and input into the disturbance propagation matrix to obtain a response value vector of the local response graph model; Perform data analysis on the response value vector of the local response map model to identify abnormal cross-section areas.

[0028] It should be noted that the initial section boundary area is constructed as a local response graph model. First, all nodes and their connection relationships in the area are extracted from the graph database to form a local subgraph, while retaining the node's power information, voltage level, equipment type and other attributes. Then, a node power disturbance model based on the power flow equation is introduced into this subgraph. By injecting a certain disturbance (such as power change) into each node, its impact on adjacent nodes is calculated to form a disturbance propagation matrix. Subsequently, a neural network (such as LSTM) is used to predict the power value of each node under normal conditions. The predicted value is then compared with the actual real-time power data for residual analysis to obtain the power residual vector of each node. This residual vector is input into the disturbance propagation matrix to deduce the response value vector of each node in the entire local response graph. Finally, statistical analysis methods (such as PCA dimensionality reduction and cluster analysis) are used to determine which nodes' response values ​​deviate significantly under the influence of the disturbance. If multiple high-response value nodes are concentrated in a certain area, the area can be identified as an abnormal section area, indicating that it has potential power flow imbalance or power anomaly propagation risk.

[0029] S3, construct a multi-objective optimization function for the abnormal section area and solve it using a non-dominated sorting genetic algorithm to obtain a candidate capacity boundary set; In this example, a multi-objective optimization function is constructed for the abnormal section area and solved by a non-dominated sorting genetic algorithm to obtain a candidate capacity boundary set, which is as follows: Based on the abnormal section area, the unit capacity compensation efficiency of the preset control node for the abnormal section area is calculated in combination with the power residual value of the node, and the regional capacity response matrix is ​​constructed; Nodes are screened based on the regional capacity response matrix to obtain screened nodes, and the preset maximum allowable adjustment capacity of the screened nodes is used as the capacity boundary upper limit to obtain a capacity boundary variable set; A multi-objective optimization function is constructed with the optimization objectives of restoring power balance in abnormal section areas, maximizing branch capacity utilization, and minimizing regulation costs. Set the population size and number of iterations of the genetic algorithm, and initialize the decision variables including generator output adjustment, load transfer, and energy storage scheduling; Based on the multi-objective optimization function, a multi-objective optimization function is adopted to obtain a candidate capacity boundary set.

[0030] It should be noted that a control node refers to a key node with regulation capabilities that can be used to restore system power balance and alleviate load pressure in abnormal areas. It usually includes generators, controllable loads, energy storage devices, etc., which participate in scheduling as potential intervention means in the optimization process; unit capacity compensation efficiency is an indicator to measure the effect of unit capacity adjustment of a certain control node on power restoration in the abnormal section area. It is usually calculated by analyzing the regional response degree caused by the unit output change of the node in the disturbance propagation matrix, reflecting its marginal benefit in alleviating local anomalies; based on these control nodes and their unit capacity compensation efficiency, the constructed multi-objective optimization function comprehensively considers multiple optimization objectives, including power balance restoration in the abnormal area (i.e., minimizing the total residual), maximizing branch capacity utilization (minimizing idle or overloaded lines), and minimizing regulation costs (economic constraints of control nodes). By establishing a trade-off relationship between these objectives, a non-dominated sorting strategy is used in multi-objective solution methods such as genetic algorithms to generate a Pareto optimal solution set, ultimately providing the system with a variety of scheduling strategy candidate schemes.

[0031] S4, filtering and perturbing the candidate capacity boundary set under several preset perturbation scales to obtain several capacity response values, and constructing a credibility evaluation function based on the matching degree between the capacity response values ​​and a preset system normal capacity threshold to determine the optimal credible capacity boundary; In this example, under several preset disturbance scales, the candidate capacity boundary set is filtered and disturbed to obtain several capacity response values, specifically: Acquire historical fault data and define a disturbance type set, wherein the disturbance type set includes load surge, generator disconnection, and line disconnection; Set the disturbance scale level for each disturbance type and build a disturbance scenario library; For each disturbance scenario in the disturbance scenario library, a disturbance source node is randomly selected and injected into each candidate capacity boundary in the candidate capacity boundary set to obtain several disturbance capacity boundaries; A number of disturbance capacity boundaries are based on a preset power flow response model to obtain a number of capacity response values.

[0032] It should be noted that in order to comprehensively evaluate the reliability and robustness of the candidate capacity boundaries in actual operation, historical fault data are first collected and organized, and various disturbance types including load surge, generator disconnection and line breakage are defined to build a disturbance scenario library covering different disturbance scales and scenarios; for each disturbance type, multiple disturbance scale levels are set to reflect the different disturbance intensities, thereby simulating the response of the power grid under various abnormal conditions; in the simulation process, the disturbance source node is randomly selected and the disturbance is injected into each capacity boundary scheme in the candidate capacity boundary set to generate a series of disturbance capacity boundaries; then, based on the preset power flow response model, the power flow changes of each disturbance capacity boundary in the power grid are calculated to obtain the corresponding capacity response values. These response values ​​reflect the operating performance of the power grid under different disturbances, thereby providing key data support for credibility evaluation and screening of the optimal capacity boundary.

[0033] In this example, a credibility evaluation function is constructed based on the matching degree between the capacity response value and the preset system normal capacity threshold to determine the optimal credible capacity boundary. Specifically, it is: A volume response vector is constructed for each volume response value, and a clustering algorithm is used to perform cluster analysis on the volume response vector to construct a multi-scale response topology clustering map; Based on the multi-scale response topology clustering map, a distribution fitting algorithm is used to construct the credibility density function; The expected value of each disturbance capacity boundary is calculated based on the credibility density function, and the disturbance capacity boundary with the largest expected value is selected as the optimal credibility capacity boundary.

[0034] It should be noted that for the multiple capacity response values ​​obtained under different disturbance scenarios, each response value is first constructed into a capacity response vector, and these vectors are analyzed using a clustering algorithm to form a multi-scale response topology clustering map, thereby revealing the distribution characteristics and internal correlations of the capacity response under different disturbance conditions; based on this clustering map, a distribution fitting algorithm is further used to establish a credibility density function to quantify the probability that each capacity response scheme meets the system normal capacity threshold in actual operation; by calculating the expected value of the credibility density function corresponding to each disturbance capacity boundary, its overall performance and stability are evaluated, and finally the disturbance capacity boundary with the highest expected value is selected as the optimal credibility capacity boundary, thereby ensuring that the flexible resource scheduling scheme has high reliability and adaptability under various disturbance conditions.

[0035] S5, updates the optimal trusted capacity boundary to the graph database and generates core flexible resource scheduling instructions for resource scheduling.

[0036] In this example, the optimal trusted capacity boundary is updated to the graph database and a core flexible resource scheduling instruction is generated for resource scheduling. Specifically: Analyze the generator output adjustment value, load distribution strategy and line switching plan within the optimal credible capacity boundary; Map the parsed parameters to the vertex attributes of the graph database, and update the node capacity, edge transmission limit, and topological connection status; Based on the updated graph database, a resource scheduling instruction generation model is built. The model extracts the dependencies and priorities between nodes through a graph neural network. Generate dispatch instruction sequences based on dependencies and priorities, including generator output instructions, load shedding instructions, and standby line switching instructions; The dispatch instructions are sent to the power system control terminal, the execution effect of the instructions is monitored in real time, and the capacity boundary parameters in the graph database are dynamically adjusted based on the feedback data.

[0037] It should be noted that the key dispatching parameters in the optimal credible capacity boundary - including generator output adjustment values, load distribution strategies, and backup line switching plans - are parsed, and then these parameters are mapped and updated to the attributes of the corresponding nodes and edges in the graph database, such as node capacity, line transmission limits, and topological connection status, thereby realizing dynamic adjustment of the power system model; based on the updated graph database, a resource dispatching instruction generation model using graph neural networks (GNNs) is constructed. GNNs intelligently generate dispatching sequences including generator output instructions, load switching instructions, and backup line switching instructions by capturing the complex dependencies and priorities between nodes; finally, these dispatching instructions are sent to the control terminal of the power system to realize accurate dispatch and real-time management of flexible resources. At the same time, the system continuously monitors the execution effect of the instructions and dynamically adjusts the capacity boundary parameters in the graph database based on feedback data to ensure the effectiveness of the dispatching strategy and the stability of the system operation.

[0038] Example 2, Figure 2 The present invention provides a flexible resource dispatching and control system for a power system based on a graph database, which includes a boundary division module, an anomaly screening module, an optimization solution module, a disturbance assessment module, and a dispatching control module: Boundary division module, used to build a power system topology model based on the graph database and divide the initial section boundary area using the shortest path algorithm; Anomaly screening module, used to build a dynamic boundary model based on the initial section boundary area and identify abnormal section areas in combination with the preset tidal flow equation; The optimization solution module is used to construct a multi-objective optimization function for the abnormal section area and solve it using a non-dominated sorting genetic algorithm to obtain a candidate capacity boundary set; A disturbance assessment module is used to filter and perturb the candidate capacity boundary set under several preset disturbance scales to obtain several capacity response values, and to construct a credibility evaluation function based on the matching degree between the capacity response values ​​and the preset system normal capacity threshold to determine the optimal credible capacity boundary; The scheduling control module is used to update the optimal trusted capacity boundary to the graph database and generate core flexible resource scheduling instructions for resource scheduling.

[0039] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0040] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0041] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0042] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0043] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0044] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A flexible resource dispatching and control method for power systems based on a graph database, characterized in that: The following steps are involved: Build a power system topology model based on a graph database and divide the initial section boundary area using the shortest path algorithm; A dynamic boundary model is constructed based on the initial section boundary area, and the abnormal section area is identified in combination with the preset tidal flow equation; A multi-objective optimization function is constructed for the abnormal section area and solved by non-dominated sorting genetic algorithm to obtain the candidate capacity boundary set; Under several preset disturbance scales, the candidate capacity boundary set is filtered and disturbed to obtain several capacity response values. Based on the matching degree between the capacity response values ​​and the preset system normal capacity threshold, a credibility evaluation function is constructed to determine the optimal credible capacity boundary. The optimal trusted capacity boundary is updated to the graph database and core flexible resource scheduling instructions are generated for resource scheduling.

2. The method for controlling flexible resource dispatching of a power system based on a graph database according to claim 1, characterized in that: The power system topology model is constructed based on the graph database, and the initial section boundary area is divided by the shortest path algorithm, specifically: Acquiring device attribute data of all nodes in the power system, wherein the device attribute data includes generator capacity, load power, line impedance, and node voltage level; Nodes are mapped as vertices in a graph database, connections are mapped as edges, and vertices are hierarchically labeled based on node voltage levels to construct a power system topology model. The Dijkstra algorithm is used to traverse the shortest paths in the power system topology model and obtain several first shortest paths; Obtaining a path feature sequence of the first shortest path based on the device attribute data to obtain a plurality of path feature sequences; The DTW algorithm is used to screen several path feature sequences and obtain several second shortest paths; Cluster analysis is performed on several second shortest paths to divide the initial section boundary area.

3. The method for controlling flexible resource dispatching of a power system based on a graph database according to claim 2, characterized in that: The cluster analysis of the plurality of second shortest paths is performed to divide the initial section boundary area, specifically: constructing the node and device attribute data in each second shortest path into a first path feature vector; Based on the first path feature vector, a clustering algorithm is used to cluster several second shortest paths to obtain several path clusters; Within each path cluster, construct the node frequency vector and edge frequency matrix; Based on the node frequency vector and edge frequency matrix, determine whether each edge endpoint crosses clusters, and count the number of times the endpoint appears in the path cluster. If it exceeds the preset frequency threshold, it is marked as a section boundary edge; The endpoints of all section boundary edges constitute the initial section boundary area.

4. The method for controlling flexible resource dispatching of a power system based on a graph database according to claim 3, characterized in that: The dynamic boundary model is constructed based on the initial section boundary area, and the abnormal section area is identified in combination with the preset tidal flow equation, specifically: The initial section boundary area is constructed as a local response diagram model, and a node power disturbance model is constructed based on the preset power flow equation; Based on the node power disturbance model, the disturbance response value of each node in the local response graph model is calculated to obtain the disturbance propagation matrix of each node; Use the preset neural network model to predict the power of each node and obtain the power prediction value; Calculate the residual between the real-time power data of each node and the power prediction value to obtain the power residual value of each node; A first power disturbance vector is constructed based on the power residual value of each node and input into the disturbance propagation matrix to obtain a response value vector of the local response graph model; Perform data analysis on the response value vector of the local response map model to identify abnormal cross-section areas.

5. The graph database-based flexible resource dispatch control method for power systems according to claim 4, characterized in that: The multi-objective optimization function is constructed for the abnormal section area and solved by non-dominated sorting genetic algorithm to obtain the candidate capacity boundary set, which is specifically: Based on the abnormal section area, the unit capacity compensation efficiency of the preset control node for the abnormal section area is calculated in combination with the power residual value of the node, and the regional capacity response matrix is ​​constructed; Nodes are screened based on the regional capacity response matrix to obtain screened nodes, and the preset maximum allowable adjustment capacity of the screened nodes is used as the capacity boundary upper limit to obtain a capacity boundary variable set and optimize the capacity boundary variable set.

6. The graph database-based flexible resource dispatch control method for power systems according to claim 5, characterized in that: The optimization of the capacity boundary variable set is specifically as follows: A multi-objective optimization function is constructed with the optimization objectives of restoring power balance in abnormal section areas, maximizing branch capacity utilization, and minimizing regulation costs. Based on a multi-objective optimization function, a non-dominated sorting strategy is adopted to optimize the capacity boundary variable set to obtain a candidate capacity boundary set, wherein the non-dominated sorting strategy includes variable initialization.

7. The method for controlling flexible resource dispatching of a power system based on a graph database according to claim 6, characterized in that: The candidate capacity boundary set is filtered and disturbed under several preset disturbance scales to obtain several capacity response values, specifically: Acquire historical fault data and define a disturbance type set, wherein the disturbance type set includes load surge, generator disconnection, and line disconnection; Set the disturbance scale level for each disturbance type and build a disturbance scenario library; For each disturbance scenario in the disturbance scenario library, a disturbance source node is randomly selected and injected into each candidate capacity boundary in the candidate capacity boundary set to obtain several disturbance capacity boundaries; A number of disturbance capacity boundaries are based on a preset power flow response model to obtain a number of capacity response values.

8. The graph database-based flexible resource dispatching control method for a power system according to claim 7, characterized in that: The credibility evaluation function is constructed based on the matching degree between the capacity response value and the preset system normal capacity threshold to determine the optimal credible capacity boundary, specifically: A volume response vector is constructed for each volume response value, and a clustering algorithm is used to perform cluster analysis on the volume response vector to construct a multi-scale response topology clustering map; Based on the multi-scale response topology clustering map, a distribution fitting algorithm is used to construct the credibility density function; The expected value of each disturbance capacity boundary is calculated based on the credibility density function, and the disturbance capacity boundary with the largest expected value is selected as the optimal credibility capacity boundary.

9. The graph database-based flexible resource dispatch control method for a power system according to claim 8, characterized in that: The updating of the optimal trusted capacity boundary to the graph database and the generation of core flexible resource scheduling instructions for resource scheduling are specifically as follows: Analyze the optimal trusted capacity boundary and map the analyzed parameters to the vertex attributes of the graph database to obtain the updated graph database. Based on the updated graph database, a resource scheduling instruction generation model is built, and the dependencies and priorities between nodes in the model are extracted through a graph neural network. Generate a dispatch instruction sequence based on dependencies and priorities, send the dispatch instructions to the power system control terminal, monitor the instruction execution effect in real time, and dynamically adjust the capacity boundary parameters in the graph database based on feedback data.

10. A graph database-based flexible resource dispatching and control system for a power system, applied to a graph database-based flexible resource dispatching and control method for a power system as claimed in any one of claims 1 to 9, characterized in that: It includes boundary division module, anomaly screening module, optimization solution module, disturbance assessment module and scheduling control module: Boundary division module, used to build a power system topology model based on the graph database and divide the initial section boundary area using the shortest path algorithm; Anomaly screening module, used to build a dynamic boundary model based on the initial section boundary area and identify abnormal section areas in combination with the preset tidal flow equation; The optimization solution module is used to construct a multi-objective optimization function for the abnormal section area and solve it using a non-dominated sorting genetic algorithm to obtain a candidate capacity boundary set; A disturbance assessment module is used to filter and perturb the candidate capacity boundary set under several preset disturbance scales to obtain several capacity response values, and to construct a credibility evaluation function based on the matching degree between the capacity response values ​​and the preset system normal capacity threshold to determine the optimal credible capacity boundary; The scheduling control module is used to update the optimal trusted capacity boundary to the graph database and generate core flexible resource scheduling instructions for resource scheduling.

Images