Power network topology optimization method based on time series data analysis

Abstract

The invention discloses a power network topology optimization method based on time sequence data analysis, and relates to the technical field of power network topology optimization, and the method comprises the following steps: dividing a power grid into a plurality of sub-regions, and injecting disturbance signals into the sub-regions; obtaining time sequence disturbance response data, extracting oscillation characteristics, and identifying oscillation nodes; constructing an oscillation weakness evaluation model, and carrying out weakness evaluation on the oscillation nodes; correcting a phase difference matrix of the DTW based on an evaluation result, and screening a cross-regional risk propagation path; and power grid topology reconstruction is carried out according to a screening result, so that the problems of inaccurate weak node identification and low cross-regional high-risk path screening accuracy in a traditional network optimization method can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power network topology optimization, and more specifically, to a power network topology optimization method based on time series data analysis. Background Art

[0002] With the large-scale grid connection of new energy and the widespread access to power electronic equipment, modern power systems are facing more complex challenges. The access to new energy such as wind and solar energy has brought uncertainty and volatility to power output, which has put greater pressure on the stability of the power grid. At the same time, the popularization of power electronic equipment has improved the flexibility of the power grid, but it has also made the dynamic characteristics of the power grid more complex and increased the risk of oscillation. Especially under high load and new energy grid connection, the power system is susceptible to instantaneous current and voltage fluctuations, further exacerbating the complex oscillation problem. In addition, with the increase in grid interconnectivity and inter-regional power exchange, cross-regional risk propagation paths have become more hidden, and traditional grid stability analysis methods are often unable to effectively cope with these challenges. Therefore, how to improve the stability and reliability of the power grid, especially the real-time identification and control of complex oscillations and cross-regional risk propagation paths, has become a core issue facing modern power systems.

[0003] For example, the invention patent with announcement number CN117810996B discloses an active distribution network fault recovery method that considers island division and network reconstruction. By modifying the network constraints in the traditional network reconstruction problem, it can perform load shedding operations and generate islands, and can make the island operation and network reconstruction operations work together; then the nonlinear terms in the model are processed by second-order cone relaxation, and the original model is converted into a standard mixed integer second-order cone model; the output and load matching of the main power supply and distributed power supply are determined, and the improved Dijkstra algorithm is used to divide the islands, and then the network is reconstructed to confirm the load recovery amount; it is determined whether the distribution network system meets the flow constraints, and the multi-period fault recovery operation results are output. By reasonably separating the network, the fault spread is avoided, and while the power-off load is reduced, the energy transmission path is optimized by adjusting the power network topology to improve the reliability of the system.

[0004] For example, the invention patent with announcement number CN118539441B announces a search-sort-based power grid topology optimization method and system, including obtaining power grid topology data, and constructing an action space based on the power grid topology data; wherein the power grid topology data includes a node set, an edge set, and an attribute set; obtaining real-time power grid status data, and constructing an adaptive dual-tower model based on the real-time power grid status data and the action space, and calculating a candidate action set; based on the candidate action set, constructing a graph attention network and a time-series graph neural network to obtain a sorted candidate action list; based on the sorted candidate action list, performing multi-objective optimization and decision-making to obtain the optimal action. The present invention not only improves the overall effect of power grid topology optimization through innovative algorithm construction and the organic combination of multiple methods, but also enhances the adaptability and decision-making quality of the system, realizes the rapid optimization of large-scale power grid systems, and provides strong support for practical applications.

[0005] The above disclosed technical solutions have at least the following technical problems: In traditional power grid optimization methods, traditional power network optimization methods usually rely on preset power grid topology and simplified models. These methods often lack flexible adjustment capabilities when facing sudden failures. Especially in the screening of cross-regional risk propagation paths, traditional methods cannot respond to changes in power grid topology in real time, resulting in the inability to effectively control the spread of faults. In view of the above problems, the present invention proposes a solution. 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 power network topology optimization method based on time series data analysis, which identifies oscillation nodes and evaluates weaknesses based on sub-regional disturbance and time series data analysis, corrects the phase difference matrix to screen cross-regional paths, and dynamically reconstructs the power grid topology to solve the problems of inaccurate weak node identification and low accuracy in screening cross-regional high-risk paths in traditional network optimization methods.

[0007] To achieve the above object, the present invention provides the following technical solutions: The power network topology optimization method based on time series data analysis includes the following steps: dividing the power grid into several sub-areas and injecting disturbance signals into the sub-areas; acquiring time series disturbance response data and extracting oscillation characteristics to identify oscillation nodes; building an oscillation weakness assessment model to perform weakness assessment on oscillation nodes; correcting the DTW phase difference matrix based on the assessment results to screen cross-regional risk propagation paths; and reconstructing the power grid topology according to the screening results.

[0008] In a preferred embodiment, the power grid is divided into several sub-areas, and the disturbance signal is injected into the sub-area, specifically: the power grid is divided into several sub-areas, the topological data of the power grid nodes in the sub-areas are obtained, and the PSM matrix of the power grid nodes in the sub-areas is calculated; the power grid nodes are screened based on the PSM matrix of the power grid nodes in the sub-areas to obtain the screened nodes; and the disturbance signal is injected into the screened nodes.

[0009] In a preferred embodiment, the acquisition of timing disturbance response data and extraction of oscillation characteristics to identify oscillation nodes are specifically as follows: time domain and frequency domain feature extraction are performed on the timing disturbance response data to obtain power characteristic values ​​and communication characteristic values; the power characteristic values ​​and communication characteristic values ​​are feature-fused to obtain the oscillation characteristics of the node; the oscillation characteristics are judged using preset constraints to obtain the oscillation node of the node.

[0010] In a preferred embodiment, the construction of an oscillation weakness assessment model and the performance of a weakness assessment on the oscillation node are specifically as follows: the derivative of the energy of the weak point is calculated and input into a preset physical layer to obtain the physical constraint characteristics of the weak point; the physical constraint characteristics of the weak point are input into a preset machine learning model for training; the machine learning model is verified to obtain an oscillation weakness assessment model; the phase angle timing data and topological data of each oscillation node are obtained and the instantaneous kinetic energy component, damping ratio and maximum phase difference of the weak node are calculated; the instantaneous kinetic energy component, damping ratio and maximum phase difference of the oscillation node are input into the oscillation weakness assessment model to obtain the weakness value of each oscillation node; and based on the weakness value, the oscillation node is evaluated for weakness.

[0011] In a preferred embodiment, the phase difference matrix of DTW is corrected based on the evaluation results to screen the cross-regional risk propagation path, specifically: obtaining the phase angle sequence of the node within a preset time window; calculating the cumulative distance of the node pairs and constructing an initial matrix of cumulative distances; calculating the minimum cumulative distance of the phase angle sequence of each pair of node pairs based on a preset recursive formula; constructing a first phase difference matrix based on the minimum cumulative distance; correcting the first phase difference matrix based on the weakness value of the oscillating node, and screening the cross-regional risk propagation path.

[0012] In a preferred embodiment, the first phase difference matrix is ​​corrected based on the weakness value of the oscillation node, specifically: the average value and standard deviation of the weakness value of the oscillation node are calculated, and the ratio of the average value and the standard deviation of the weakness value is used as the correction weight; whether the nodes in the node pair are in the same sub-region is determined to obtain a cross-region matrix; based on the correction weight and the cross-region matrix, the first phase difference matrix is ​​corrected to obtain a second phase difference matrix.

[0013] In a preferred embodiment, the screening of cross-regional risk propagation paths is specifically as follows: sub-regions are used as graph nodes, topological relationships between sub-regions are used as edges, and elements of the second phase matrix are used as edge weights to construct a graph model; the Dijkstra algorithm is used to traverse the graph model to screen the cross-regional risk propagation paths.

[0014] In a preferred embodiment, the Dijkstra algorithm is used to traverse the graph model and screen the cross-regional risk propagation paths, specifically: initialize the priority queue, store the path and the path cumulative risk value; based on the cross-regional matrix, traverse the nodes in the graph model and update the priority queue to obtain a list of candidate paths; based on the path cumulative risk value of the candidate path, calculate the first risk value of the candidate path, and sort the first risk value of the candidate path in descending order; compare and analyze the first risk value with a preset threshold, update the candidate path list, and obtain a list of cross-regional high-risk paths.

[0015] Technical effects and advantages of the power network topology optimization method based on time series data analysis of the present invention: 1. The present invention can simulate multiple possible network states and fully capture the dynamic responses of different parts of the power grid by dividing the power grid into several sub-areas and injecting disturbance signals into the sub-areas. This refined local disturbance method not only helps to improve the accuracy of the data, but also can screen key nodes, discover potential oscillation nodes and weak links, and provide accurate data support for subsequent optimization.

[0016] Secondly, the method combines time domain and frequency domain feature extraction to obtain power and communication features, and performs feature fusion to effectively extract the oscillation characteristics of the node. Through the preset constraints, the oscillation nodes can be quickly identified, laying the foundation for further weakness assessment. The oscillation weakness assessment model provides a more accurate weak node assessment by combining physical layer constraint features with machine learning. It can dynamically evaluate the stability of each node in the power grid and identify possible risk points in a timely manner.

[0017] In addition, the correction of the DTW (dynamic time warping) phase difference matrix and the screening of cross-regional risk propagation paths further improve the response speed and accuracy of the system. By correcting the phase difference matrix and combining the weak value of the oscillating node, the cross-regional risk propagation path can be dynamically adjusted, effectively avoiding the potential risk spread in the network and ensuring the stability of the system. In particular, the use of the Dijkstra algorithm to screen cross-regional high-risk paths can identify potential high-risk paths in real time in the changing power grid topology, helping the power grid to adjust and optimize in time when facing emergencies, thereby improving the reliability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of the power network topology optimization method based on time series data analysis of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1, Figure 1 The present invention provides a method for optimizing power network topology based on time series data analysis, which includes the following steps: S1, divide the power grid into several sub-areas and inject disturbance signals into the sub-areas; In this example, the power grid is divided into several sub-areas, and disturbance signals are injected into the sub-areas, specifically: Divide the power grid into several sub-areas, obtain the topological data of the power grid nodes in the sub-areas, and calculate the PSM matrix of the power grid nodes in the sub-areas; Screening the power grid nodes based on the PSM matrix of the sub-region power grid nodes to obtain the screened nodes; Inject disturbance signals into the screened nodes.

[0021] It should be noted that the power grid is divided into several sub-areas, and disturbance signals are injected into the sub-areas, and a refined regional management strategy is adopted to improve the stability and responsiveness of the power system. The specific implementation steps include: first, the power grid is divided into multiple sub-areas, which are relatively independent in topological structure, which is conducive to the localized analysis of the dynamic response of the power grid. In each sub-area, the topological data of the power grid nodes in the area are obtained, and the corresponding PSM matrix is ​​calculated. This process is a quantification and characterization of the power grid structure and the relationship between nodes.

[0022] The PSM matrix is ​​constructed based on the phase difference and timing response characteristics between the grid nodes, reflecting the phase change characteristics of each node in the grid. By calculating the PSM matrix, the coupling relationship and dynamic behavior between the grid nodes can be accurately identified. Then, based on this PSM matrix, the grid nodes are screened to identify the key nodes that have a greater impact on the grid stability. This screening process is of great significance because it can help identify potential weak links or high-risk areas in the grid, providing a basis for subsequent optimization and adjustment.

[0023] Next, the disturbance signal is injected into the selected key nodes. The core of this step is to simulate the dynamic response of the power grid under disturbance, which can reflect the stability and anti-interference ability of each node in the face of external disturbances. By injecting disturbance signals and monitoring the system response, a large amount of time series data can be obtained to provide data support for subsequent oscillation feature extraction, weakness assessment and topology optimization. The advantage of this method is that by performing local disturbances in sub-areas, it can effectively avoid excessive impact of large-scale disturbances on the entire power grid, and can more finely analyze the stability of each node in the power grid.

[0024] In addition, the method of dividing the power grid into sub-areas and injecting local disturbances avoids the global disturbance of the entire power grid in traditional methods, reduces the risks brought by disturbances, and makes the analysis results more specific and actionable. In this way, power grid optimization not only relies on the analysis of global data, but can also perform dynamic testing and analysis in multiple local areas, so as to discover potential weak links and carry out targeted optimization.

[0025] S2, obtain the timing disturbance response data and extract the oscillation characteristics to identify the oscillation nodes; In this example, the timing disturbance response data is obtained and the oscillation characteristics are extracted to identify the oscillation nodes, specifically: Extract time domain and frequency domain features of the time series disturbance response data to obtain power characteristic values ​​and communication characteristic values; The power characteristic value and the communication characteristic value are integrated to obtain the oscillation characteristics of the node; The oscillation characteristics are judged using preset constraints to obtain the oscillation node of the node.

[0026] It should be noted that the time-domain and frequency-domain feature extraction of the time-series disturbance response data obtains the dynamic characteristics of the power system from the time and frequency levels respectively. In the time-domain analysis, the dynamic response characteristics, fluctuation amplitude and waveform changes of the system are used to reflect the stability of the grid nodes; while in the frequency-domain analysis, the main focus is on the frequency characteristics, harmonic components and other information of the system to help identify possible resonance phenomena or frequency fluctuations in the grid. Through these two feature extraction methods, the oscillation characteristics of different nodes in the power system can be fully captured, providing high-quality input data for subsequent analysis.

[0027] Then, the power characteristic values ​​and communication characteristic values ​​are fused to obtain comprehensive node oscillation characteristics. The power characteristic values ​​mainly reflect the electrical characteristics of the power grid nodes, such as voltage and power, while the communication characteristic values ​​focus on network-level information such as communication delay and transmission loss between nodes. By fusing these two types of features, the response behavior of power grid nodes under disturbances can be more comprehensively characterized. Especially in modern power systems, the stability of communication and information transmission plays a vital role in the overall stability of the power grid. After feature fusion, the oscillation characteristics are more accurate and can provide stronger support for the subsequent identification of oscillating nodes.

[0028] After obtaining the oscillation characteristics, the method judges the oscillation characteristics through preset constraints to identify the oscillating nodes in the power grid. This step determines which nodes are oscillating nodes based on the oscillation characteristics and response characteristics of the nodes, combined with the physical constraints of the system, such as voltage limits and power fluctuation ranges. These oscillating nodes are often the weakest links in the power grid that are most susceptible to disturbances or cause failures. By timely identification and targeted intervention, large-scale failures can be effectively avoided.

[0029] S3, build an oscillation weakness assessment model to conduct weakness assessment on oscillation nodes; In this example, an oscillation vulnerability assessment model is constructed to perform vulnerability assessment on oscillation nodes. Specifically: Calculate the derivative of the weak point energy and input it into the preset physical layer to obtain the physical constraint characteristics of the weak point; Input the physical constraint characteristics of the weak points into the preset machine learning model for training; The machine learning model was verified to obtain a shock vulnerability assessment model; Obtain the phase angle timing data and topological data of each oscillating node and calculate the instantaneous kinetic energy component, damping ratio and maximum phase difference of the weak node; The instantaneous kinetic energy component, damping ratio and maximum phase difference of the oscillation node are input into the oscillation weakness assessment model to obtain the weakness value of each oscillation node; Based on the weakness value, a weakness assessment is performed on the oscillating node.

[0030] It should be noted that by calculating the derivative of the energy of the weak point and inputting it into the preset physical layer, the physical constraint characteristics of the weak point are obtained. This step combines the physical laws of the power grid, such as current and voltage, and can accurately reflect the energy changes and physical characteristics of each node under disturbance. This process fully reveals the physical characteristics of the oscillating node, which helps to analyze which nodes show greater instability or susceptibility under external disturbances or load changes.

[0031] Next, these physical constraint features are input into the preset machine learning model for training. Through the learning of the machine learning model, the deep correlation between node oscillation and weakness can be found from historical data. The machine learning method is adaptive and efficient, and can automatically adjust the assessment model according to the actual operation of the power grid, thereby improving the accuracy and robustness of the weakness assessment. After the training is completed, a reliable oscillation weakness assessment model is obtained through model verification, which provides a theoretical basis for further weak node assessment.

[0032] Next, the method calculates the instantaneous kinetic energy component, damping ratio and maximum phase difference of each weak node by obtaining the phase angle time series data and topological data of each oscillating node. These dynamic characteristics can reveal the kinetic energy changes, oscillation intensity and phase differences of the power grid nodes under disturbance, thereby further quantifying the stability of the nodes. Based on these characteristics, they are input into the oscillation weakness assessment model for prediction to obtain the weakness value of each node. The larger the weakness value, the more susceptible the node is to disturbance in the power grid and the more likely it is to cause abnormal operation of the system.

[0033] By evaluating the weakness of the oscillating nodes based on the weakness value, the weak links in the power grid can be accurately identified, and targeted measures can be taken in time to optimize and adjust. This process can not only improve the stability of the power grid, but also provide early warning of potential failure risks, thereby reducing the occurrence of large-scale failure events and optimizing the safety and reliability of power grid operation.

[0034] In summary, this method based on the oscillation weakness assessment model effectively realizes the dynamic assessment of the weakness of power grid nodes by combining the feature analysis at the physical level with the intelligent processing of the machine learning model. Through this precise assessment method, the power system can achieve more efficient risk prediction and early warning, greatly improve the reliability and anti-interference ability of the power grid, and provide solid technical support for the intelligent management and optimized dispatching of modern power grids.

[0035] Among them, the instantaneous kinetic energy component, damping ratio and maximum phase difference of the oscillation node are input into the oscillation weakness assessment model to obtain the weakness value of each oscillation node. The specific calculation formula is as follows:

[0036] in, is the weakness value of weak node i at time t, is the instantaneous kinetic energy component of the weak node i, is the preset reference kinetic energy, is the damping ratio of weak node i, is the preset critical damping ratio threshold, is the maximum phase difference of weak node i.

[0037] S4, based on the evaluation results, the DTW phase difference matrix is ​​modified to screen the cross-regional risk propagation path; In this example, the DTW phase difference matrix is ​​modified based on the evaluation results to screen the cross-regional risk transmission path, specifically: Obtain the phase angle sequence of the node within the preset time window; Calculate the cumulative distance of node pairs and construct the initial cumulative distance matrix; The minimum cumulative distance of the phase angle sequence of each pair of nodes is calculated based on a preset recursive formula; Constructing a first phase difference matrix based on the minimum cumulative distance; The first phase difference matrix is ​​corrected based on the weak value of the oscillation node, and the cross-regional risk propagation path is screened.

[0038] It should be noted that by correcting the dynamic time warping (DTW) phase difference matrix based on the oscillation weakness assessment results and accurately screening the cross-regional risk propagation path, the stability analysis and risk prediction capabilities of the power system under complex disturbance conditions can be effectively improved. Specifically, the core of this method is based on the phase angle sequence of the grid nodes, combined with the DTW algorithm to analyze the phase difference between nodes, and then reveal the potential risk propagation paths between different regions in the power grid. The following are the detailed steps and advantages of this process.

[0039] First, the method obtains the phase angle sequence of the node within the preset time window. The phase angle sequence reflects the relative voltage changes of each node in the power grid, which is an important data for evaluating the dynamic response and stability of the power grid. This step can accurately track the response process of the power grid when disturbances occur by capturing the dynamic changes of nodes in the time series.

[0040] Next, the method calculates the cumulative distance of the node pairs and constructs the initial cumulative distance matrix. This process quantifies the degree of dynamic association between nodes by calculating the distance between phase angle sequences. The initial cumulative distance matrix provides the basis for the subsequent phase difference calculation. It can show the degree of phase angle fluctuation between nodes and lays a data foundation for further risk analysis.

[0041] Then, based on the preset recursive formula, the method calculates the minimum cumulative distance of the phase angle sequence between each pair of nodes. This process is the core step of the DTW algorithm. The minimum cumulative distance path is found through the recursive formula to ensure that the phase difference matrix can accurately reflect the phase change relationship between nodes. The minimum cumulative distance is an important basis for evaluating the risk propagation path between nodes in the power grid, because it can quantify the degree of linkage between nodes and the efficiency of disturbance transmission.

[0042] On this basis, the method constructs the first phase difference matrix based on the minimum cumulative distance, further revealing the phase relationship between nodes and their potential risk propagation path. The construction of the first phase difference matrix provides a reference for subsequent correction and optimization, so that the spatiotemporal correlation characteristics of each node in the power grid can be clearly presented.

[0043] Next, the method corrects the first phase difference matrix according to the weak value of the oscillating node. The key to this process is that the weak value can reflect the stability of the oscillating node. By correcting the phase difference matrix, the phase relationship of the high-risk area in the power grid can be dynamically adjusted, making the screening of risk propagation paths more accurate. Through this correction, the risk of misjudgment and missed judgment can be reduced, providing more accurate path data for subsequent cross-regional risk propagation path screening.

[0044] Finally, based on the corrected phase difference matrix, the method screens out the cross-regional risk propagation paths in the power grid. Through this screening process, the potential risk transmission paths in the power grid can be identified, especially the linkage effects between different regions, which helps decision makers to timely identify cross-regional risk propagation channels and take effective preventive measures. The screened high-risk paths will become the focus of power grid optimization scheduling and emergency management to avoid large-scale system failures and accidents.

[0045] The main advantages of this method are: First, it combines the dynamic matching ability of the DTW algorithm, which can effectively analyze the complex time series relationship between power grid nodes and improve the accuracy of cross-regional risk propagation path identification. Secondly, the correction process of weak nodes makes the phase difference matrix more in line with the actual operating status of the power grid, ensuring more accurate screening of risk propagation paths. Finally, this method can not only identify potential weak nodes in the power grid, but also conduct in-depth analysis of the cross-regional dynamic response of the power grid, thereby providing strong data support for the dynamic dispatch and emergency management of the power grid.

[0046] In this example, the first phase difference matrix is ​​corrected based on the weak value of the oscillation node, specifically: Calculate the mean and standard deviation of the weak values ​​of the oscillating nodes, and use the ratio of the mean and standard deviation of the weak values ​​as the correction weight; Determine whether the nodes in the node pair are in the same sub-region and obtain the cross-region matrix; The first phase difference matrix is ​​corrected based on the correction weight and the cross-region matrix to obtain a second phase difference matrix.

[0047] The first phase difference matrix is ​​corrected based on the correction weight and the cross-region matrix to obtain the second phase difference matrix. The specific calculation formula is as follows:

[0048] in, is the second phase difference matrix, is the first phase difference matrix, To correct the weight, is the cross-region matrix of node pairs (m,n), is the electrical distance between node m and node n.

[0049] It should be noted that, first of all, the method calculates the mean and standard deviation of the weak value of the oscillating node. The weak value of the oscillating node reflects the stability and anti-interference ability of the node in the power grid. The higher the weak value, the more susceptible the node is to disturbance or system failure. Calculating the mean and standard deviation of the weak value of the oscillating node helps to quantify the risk level of each oscillating node in the power grid and provide a basis for further correction of the phase difference matrix. By calculating the standard deviation of the weak value, the degree of stability difference between different nodes can be evaluated, thereby giving different correction weights to each node.

[0050] Next, the method uses the ratio of the mean value to the standard deviation of the weak value as the correction weight. This ratio can reflect the risk contribution of each node in the power grid. Nodes with larger weak values ​​and higher standard deviations will be given higher correction weights. This step can dynamically adjust the impact of weak nodes in the power grid on the overall stability, ensuring that when correcting the phase difference matrix, the risk of weak nodes can be appropriately amplified, while the impact of stable nodes is suppressed, thereby achieving more accurate risk assessment.

[0051] Then, the method obtains the cross-regional matrix by judging whether the nodes in the node pair are in the same sub-region. The power system is often composed of multiple regions, and there may be large dynamic differences between nodes in different regions. By analyzing whether the nodes are in the same sub-region, it can help clarify the coupling relationship between different regions, especially in the cross-regional risk propagation analysis, judging whether there is cross-regional propagation has become a crucial factor. The construction of the cross-regional matrix can effectively distinguish the risk propagation patterns within and between regions, thereby providing clear regional division information for subsequent risk assessment.

[0052] Based on the correction weights and cross-regional matrix, the method further corrects the first phase difference matrix to obtain the second phase difference matrix. By combining the weak value correction weights and the cross-regional matrix to correct the phase difference matrix, the phase difference relationship between nodes in the power grid can be dynamically adjusted, especially between nodes connected across regions, and potential risk propagation channels can be accurately captured. This correction process effectively avoids the overly balanced phase difference calculation in traditional methods, and can more finely identify those cross-regional propagation paths with higher risks and prone to large-scale failures.

[0053] The main advantages of this method are: first, by calculating the ratio of the weak value and standard deviation of the oscillating node as the correction weight, it can more accurately reflect the risk level of each node and dynamically adjust the stability influence between nodes in the phase difference matrix correction. Secondly, the introduction of the cross-regional matrix helps to clearly distinguish the mutual influence between different regions in the power grid, avoiding the misjudgment of large-scale cross-regional propagation paths. In addition, the phase difference matrix based on the weak value correction can more accurately screen out high-risk nodes and cross-regional risk propagation paths in the power grid, and improve the anti-interference ability and fault warning ability of the power grid.

[0054] In this example, the cross-regional risk transmission paths are screened, specifically: The graph model is constructed by taking the sub-regions as graph nodes, the topological relationships between the sub-regions as edges, and the elements of the second phase matrix as edge weights; The Dijkstra algorithm is used to traverse the graph model and screen the cross-regional risk transmission paths.

[0055] It should be noted that the power grid is first divided into multiple sub-regions, each sub-region is regarded as a node in the graph, and the topological relationship between sub-regions constitutes the edge of the graph. The elements of the second phase difference matrix are used as edge weights to reflect the risk propagation intensity between different sub-regions. The construction of this graph model can effectively represent the regional structure of the power grid and the dynamic coupling relationship between its nodes.

[0056] Next, the Dijkstra algorithm is used to traverse the constructed graph model and screen out cross-regional risk propagation paths. The Dijkstra algorithm is a classic algorithm widely used in graph optimization, which can effectively identify the optimal propagation path between nodes by calculating the shortest path. In this process, the weight of the edge (that is, the value in the phase difference matrix) determines the risk of the path, and the algorithm will automatically identify high-risk cross-regional paths. This step can accurately identify potential high-risk propagation channels in the power grid, ensuring that possible risk diffusion can be discovered and responded to in a timely manner during power grid operation.

[0057] In this example, the Dijkstra algorithm is used to traverse the graph model and screen the cross-regional risk transmission paths, specifically: Initialize the priority queue, store the path and the path cumulative risk value; Based on the cross-region matrix, the nodes in the graph model are traversed and the priority queue is updated to obtain a list of candidate paths; Based on the path cumulative risk values ​​of the candidate paths, first risk values ​​of the candidate paths are calculated, and the first risk values ​​of the candidate paths are sorted in descending order; The first risk value is compared and analyzed with a preset threshold, and the candidate path list is updated to obtain a cross-regional high-risk path list.

[0058] It should be noted that by initializing the priority queue, storing the paths and the cumulative risk values ​​of the paths, preparations are made for subsequent path screening. The priority queue is used to efficiently manage and update candidate paths so that the optimal path selection can be obtained in a timely manner during the traversal process. The cumulative risk value of the path is used to quantify the accumulated risk level on each path, which is directly related to the operational safety of the power grid. By introducing the priority queue, the path search process can be optimized and the efficiency of path screening can be improved.

[0059] Then, based on the cross-regional matrix, the method traverses the nodes in the graph model and updates the priority queue to obtain a list of candidate paths. The cross-regional matrix is ​​used to represent the risk coupling relationship between different sub-regions. The traversal of the nodes and the update of the priority queue ensure that the linkage risks between different regions can be fully reflected. In this way, the risk propagation channels between different regions of the power grid can be systematically analyzed, providing a wide range of candidate path information for subsequent path screening.

[0060] Then, based on the cumulative risk values ​​of the candidate paths, the first risk value of each candidate path is calculated, and the first risk values ​​of the candidate paths are sorted in descending order. The first risk value of the path is calculated based on the cumulative risk value, reflecting the total risk level of each path. By sorting the path risk values, it is possible to clearly identify which paths have higher risks, and then focus on those high-risk propagation channels that may cause large-scale power grid failures. Descending sorting can ensure that higher-risk paths are given priority, providing an important reference for subsequent decision-making.

[0061] Finally, the calculated first risk value is compared with the preset threshold, and the candidate path list is updated based on the threshold setting to obtain a list of cross-regional high-risk paths. The setting of this threshold is adjusted according to the fault tolerance, stability requirements and historical fault data of the power grid, which can ensure that the identification of high-risk paths is more in line with the actual needs of the power grid. Through this process, the cross-regional high-risk paths finally screened out will help the optimized scheduling and fault emergency response of the power grid.

[0062] The main advantage is that it can accurately identify high-risk transmission paths in the power grid through the Dijkstra algorithm combined with the cumulative risk value and threshold analysis of the path. This not only improves the accuracy of power grid risk assessment, but also effectively improves the real-time and predictability of risk management. Through the dynamic update of priority queues and path risk values, the method can quickly respond to changes in power grid operation and ensure that cross-regional risk transmission paths can be quickly and accurately screened in complex power grid environments. This process not only helps to improve the safety and stability of the power grid, but also provides a scientific basis for fault prevention and emergency management of the power grid, and can quickly take effective measures when emergencies occur to reduce the scope and impact of risk diffusion.

[0063] S5, reconstructing the power grid topology according to the screening results.

[0064] In this example, the power grid topology is reconstructed according to the screening results, specifically: According to the selected cross-regional high-risk transmission paths, the process of grid topology reconstruction is mainly to improve the stability and risk resistance of the grid by identifying high-risk areas and weak nodes and adjusting the connection mode of the grid. First, determine the high-risk areas in the grid, especially the weak nodes, which may become the key points of fault propagation due to excessive load, aging equipment or unreasonable structure. Then, take measures to optimize the grid connection mode, such as adding redundant paths to ensure that when a node fails, other paths can take over the load to avoid large-scale power outages; temporarily disconnect high-risk paths to prevent fault propagation; and reduce the pressure on weak nodes through reasonable load redistribution. Grid topology reconstruction can also be combined with real-time monitoring systems for dynamic adjustment. During the operation of the grid, the topology structure can be optimized in time according to real-time risk assessment data, thereby improving the fault tolerance and emergency response speed of the grid. In addition, by optimizing the grid topology structure, the operation efficiency of the grid can be improved, the system can avoid excessive dependence on a certain part, and the stability and reliability of the grid can be improved. Finally, the grid topology reconstruction not only improves the anti-disturbance ability of the grid and reduces the potential risk of fault propagation, but also enhances the emergency response capability of the grid to emergencies, ensuring the efficient and safe operation of the power system.

[0065] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0066] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0067] Those of ordinary skill 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 to be beyond the scope of this application.

[0068] 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.

[0069] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0070] 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 protection scope of the present invention.

Claims

1. A power network topology optimization method based on time series data analysis, characterized in that: The following steps are involved: The power grid is divided into several sub-areas, and disturbance signals are injected into the sub-areas; Obtain timing disturbance response data and extract oscillation features to identify oscillation nodes; Construct an oscillation weakness assessment model to conduct weakness assessment on oscillation nodes; Based on the evaluation results, the DTW phase difference matrix is ​​modified to screen the cross-regional risk transmission path; The grid topology is reconstructed according to the screening results.

2. The power network topology optimization method based on time series data analysis according to claim 1 is characterized in that: The power grid is divided into several sub-areas, and disturbance signals are injected into the sub-areas, specifically: Divide the power grid into several sub-areas, obtain the topological data of the power grid nodes in the sub-areas, and calculate the PSM matrix of the power grid nodes in the sub-areas; Screening the power grid nodes based on the PSM matrix of the sub-region power grid nodes to obtain the screened nodes; Inject disturbance signals into the screened nodes.

3. The power network topology optimization method based on time series data analysis according to claim 2 is characterized in that: The acquisition of the timing disturbance response data and the extraction of the oscillation characteristics to identify the oscillation nodes is specifically as follows: Extract time domain and frequency domain features of the time series disturbance response data to obtain power characteristic values ​​and communication characteristic values; The power characteristic value and the communication characteristic value are integrated to obtain the oscillation characteristics of the node; The oscillation characteristics are judged using preset constraints to obtain the oscillation node of the node.

4. The method for optimizing power network topology based on time series data analysis according to claim 3 is characterized in that: The construction of the oscillation weakness assessment model and the assessment of the weakness of the oscillation node are specifically as follows: Calculate the derivative of the weak point energy and input it into the preset physical layer to obtain the physical constraint characteristics of the weak point; Input the physical constraint characteristics of the weak points into the preset machine learning model for training; The machine learning model was verified to obtain a shock vulnerability assessment model; Obtain the phase angle timing data and topological data of each oscillating node and calculate the instantaneous kinetic energy component, damping ratio and maximum phase difference of the weak node; The instantaneous kinetic energy component, damping ratio and maximum phase difference of the oscillation node are input into the oscillation weakness assessment model to obtain the weakness value of each oscillation node; Based on the weakness value, a weakness assessment is performed on the oscillating node.

5. The method for optimizing power network topology based on time series data analysis according to claim 4 is characterized in that: The DTW phase difference matrix is ​​modified based on the evaluation results to screen the cross-regional risk transmission path, specifically: Obtain the phase angle sequence of the node within the preset time window; Calculate the cumulative distance of node pairs and construct the initial cumulative distance matrix; The minimum cumulative distance of the phase angle sequence of each pair of nodes is calculated based on a preset recursive formula; Constructing a first phase difference matrix based on the minimum cumulative distance; The first phase difference matrix is ​​corrected based on the weak value of the oscillation node, and the cross-regional risk propagation path is screened.

6. The method for optimizing power network topology based on time series data analysis according to claim 5, characterized in that: The first phase difference matrix is ​​corrected based on the weak value of the oscillation node, specifically: Calculate the mean and standard deviation of the weak values ​​of the oscillating nodes, and use the ratio of the mean and standard deviation of the weak values ​​as the correction weight; Determine whether the nodes in the node pair are in the same sub-region and obtain the cross-region matrix; The first phase difference matrix is ​​corrected based on the correction weight and the cross-region matrix to obtain a second phase difference matrix.

7. The method for optimizing power network topology based on time series data analysis according to claim 6, characterized in that: The screening of cross-regional risk transmission paths is specifically as follows: The sub-regions are used as graph nodes, the topological relationships between sub-regions are used as edges, and the elements of the second phase matrix are used as edge weights to construct a graph model; The Dijkstra algorithm is used to traverse the graph model and screen the cross-regional risk transmission paths.

8. The method for optimizing power network topology based on time series data analysis according to claim 7, characterized in that: The Dijkstra algorithm is used to traverse the graph model and screen the cross-regional risk transmission path, specifically: Initialize the priority queue, store the path and the path cumulative risk value; Based on the cross-region matrix, the nodes in the graph model are traversed and the priority queue is updated to obtain a list of candidate paths; Based on the path cumulative risk values ​​of the candidate paths, first risk values ​​of the candidate paths are calculated, and the first risk values ​​of the candidate paths are sorted in descending order; The first risk value is compared and analyzed with a preset threshold, and the candidate path list is updated to obtain a cross-regional high-risk path list.

9. The method for optimizing power network topology based on time series data analysis according to claim 8, characterized in that: The instantaneous kinetic energy component, damping ratio and maximum phase difference of the oscillation node are input into the oscillation weakness assessment model to obtain the weakness value of each oscillation node. The specific calculation formula is as follows: in, is the weakness value of weak node i at time t, is the instantaneous kinetic energy component of the weak node i, is the preset reference kinetic energy, is the damping ratio of weak node i, is the preset critical damping ratio threshold, is the maximum phase difference of weak node i.

10. The method for optimizing power network topology based on time series data analysis according to claim 9, characterized in that: The first phase difference matrix is ​​corrected based on the correction weight and the cross-region matrix to obtain the second phase difference matrix. The specific calculation formula is as follows: in, is the second phase difference matrix, is the first phase difference matrix, To correct the weight, is the cross-region matrix of node pairs (m,n), is the electrical distance between node m and node n.

Images