Power grid optimization control method, system, equipment and medium based on disaster awareness

Abstract

The present invention application provides a power grid optimization control method, system, equipment and medium based on disaster awareness, which obtains the impact caused by disaster events from multiple dimensions such as equipment damage, communication status and meteorology, and realizes the integration of multi-source data by constructing an initial disaster impact matrix; tracks time series data to analyze the diffusion trend of disaster events, and extracts key node features, and then constructs a power grid dynamic response mechanism to obtain a preliminary recovery path planning scheme. During the self-healing recovery process of the power grid, it continuously tracks the recovery progress. When the progress threshold corresponding to the same time is not reached, the key load protection scheme and resource scheduling scheme are corrected to obtain an optimized recovery path planning scheme and thus realize optimized control of the target power grid. Compared with the existing control scheme that relies on static plans, the present invention application can intervene in time to achieve optimized control, avoiding problems such as load distribution imbalance and control rigidity.

Description

Technical Field

[0001] The present invention relates to the field of power grid control, and in particular to a power grid optimization control method, system, equipment and medium based on disaster awareness. Background Art

[0002] During the actual operation of a power grid, its stable operation may be affected by a number of external factors, including severe disasters, which pose challenges to the stability and reliability of grid operations. During post-disaster recovery, the grid often requires real-time analysis of its current operating status, losses caused by the disaster, and the impact of the fault. Currently, grid restoration relies primarily on static emergency plans, which are primarily determined before or in the early stages of a fault. This plan-based approach to grid restoration is inherently rigid, making it difficult to adapt to the actual grid status in real time during the restoration process. This can lead to problems such as unbalanced load distribution, impacting the stability and reliability of grid operation during the recovery process. Summary of the Invention

[0003] The present invention provides a disaster-aware power grid optimization control method, system, device and medium to solve the technical problem of how to improve the matching degree between fault recovery and the actual state of the power grid.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a power grid optimization control method based on disaster awareness, comprising:

[0005] Obtain multi-dimensional impact data caused by the disaster event from the target power grid's equipment operation logs, meteorological warning information, and communication network status, and construct an initial disaster impact matrix based on the multi-dimensional impact data;

[0006] Based on the initial disaster impact matrix, obtaining the diffusion trend data of the disaster event by tracking time series data analysis;

[0007] Extracting key node features of the target power grid during the self-healing process according to the diffusion trend;

[0008] According to the characteristics of the key nodes, a dynamic response mechanism of the power grid is constructed; according to the dynamic response mechanism of the power grid, a preliminary restoration path planning scheme is obtained; the preliminary restoration path planning scheme includes a key load protection scheme and a resource scheduling scheme;

[0009] The operating status data of the target power grid is acquired in real time, and the recovery progress is continuously tracked based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection plan and the resource scheduling plan are revised to obtain an optimized recovery path planning plan, and the target power grid is optimized and controlled based on the optimized recovery path planning plan.

[0010] As a preferred solution, the optimizing control of the target power grid based on the optimized restoration path planning solution includes:

[0011] monitoring abnormal fluctuations of the target power grid according to the operating status data;

[0012] Based on the optimized recovery path planning scheme, combined with the preset system redundancy mechanism and the grid dynamic response mechanism, recovery control is performed on the local area of ​​the grid corresponding to the abnormal fluctuation, and local recovery feedback information is obtained;

[0013] Based on the operating status data, a comprehensive analysis is performed on the post-disaster recovery efficiency, disaster resistance, and post-disaster adaptive adjustment capability of the target power grid to determine the load distribution; based on the load distribution, a relative relationship between the recovery efficiency of the local area of ​​the power grid and the target power grid is analyzed;

[0014] Based on the local recovery feedback information and the relative relationship, an optimization direction of dynamic resource allocation is determined, thereby achieving optimized control of the target power grid.

[0015] As a preferred solution, extracting key node features of the target power grid during the self-healing process based on the diffusion trend data includes:

[0016] Analyzing the diffusion trend data to obtain a fault diffusion speed;

[0017] When the fault diffusion speed exceeds a preset speed threshold, segmenting the diffusion trend data according to time points, determining the fault isolation speed data at each time point, and obtaining a fault isolation speed data set;

[0018] Based on the fault isolation speed dataset and the preset key node protection strategy, the node protection priority is sorted by a preset random forest model to obtain a key node protection sequence;

[0019] Through the key node protection sequence and the fault isolation speed data set, the impact of key node state changes on the fault diffusion trend is analyzed, and then the key node characteristics are obtained.

[0020] As a preferred solution, obtaining a preliminary restoration path planning solution according to the dynamic response mechanism of the power grid includes:

[0021] Dividing the target power grid into a plurality of partitions;

[0022] Determining resource allocation for each of the partitions according to a preset resource distribution ratio; determining a partition response mechanism for each of the partitions according to the power grid dynamic response mechanism;

[0023] Determining a partition control order according to resource allocation of each partition and a response mechanism of each partition;

[0024] Obtain a multi-stage emergency plan; optimize the multi-stage emergency plan according to the partition control sequence to obtain a preliminary recovery path planning scheme.

[0025] As a preferred solution, the operating status data includes operating status information of each partition; and continuously tracking the recovery progress based on the operating status data includes:

[0026] Monitor the operating status of each partition and obtain the distribution of abnormal fluctuation areas;

[0027] Obtaining path restoration information for each partition based on the distribution of abnormal fluctuation areas, and then determining the restoration coverage status;

[0028] The restoration progress is determined according to the restoration coverage condition.

[0029] As a preferred solution, the multi-dimensional impact data caused by the disaster event is obtained from the equipment operation logs, meteorological warning information and communication network status of the target power grid, including:

[0030] Obtaining an original log record from the equipment operation log, wherein the original log record includes a field associated with the equipment damage condition; obtaining extreme weather event data from the weather warning information;

[0031] Performing data fusion processing on the original log records and the extreme weather event data in chronological order to obtain a fused data set;

[0032] Based on the fused data set and combined with the communication network status, communication interruption distribution characteristics are obtained, thereby obtaining the multi-dimensional impact data.

[0033] As a preferred solution, the construction of an initial disaster impact matrix based on the multi-dimensional impact data includes:

[0034] The multi-dimensional impact data is screened by using a pre-built support vector machine model to obtain a risk data set;

[0035] The risk dataset is converted into an initial disaster impact matrix.

[0036] Accordingly, the present invention also provides a power grid optimization control system based on disaster awareness, including a matrix construction module, an analysis module, a feature extraction module, a program planning module and an optimization control module; wherein,

[0037] The matrix construction module is used to obtain multi-dimensional impact data caused by the disaster event from the equipment operation logs, meteorological warning information and communication network status of the target power grid, and to construct an initial disaster impact matrix based on the multi-dimensional impact data;

[0038] The analysis module is configured to obtain the diffusion trend data of the disaster event by tracking time series data analysis based on the initial disaster impact matrix;

[0039] The feature extraction module is used to extract key node features of the target power grid during the self-healing process based on the diffusion trend data;

[0040] The program planning module is used to construct a power grid dynamic response mechanism based on the characteristics of the key nodes; obtain a preliminary restoration path planning scheme based on the power grid dynamic response mechanism; the preliminary restoration path planning scheme includes a key load protection scheme and a resource scheduling scheme;

[0041] The optimization control module is used to obtain the operating status data of the target power grid in real time; and continuously track the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection plan and resource scheduling plan are revised to obtain an optimized recovery path planning plan, and the target power grid is optimized and controlled based on the optimized recovery path planning plan.

[0042] As a preferred solution, the optimization control module performs optimization control on the target power grid based on the optimization restoration path planning solution, including:

[0043] The optimization control module monitors abnormal fluctuations of the target power grid according to the operating status data;

[0044] Based on the optimized recovery path planning scheme, combined with the preset system redundancy mechanism and the grid dynamic response mechanism, recovery control is performed on the local area of ​​the grid corresponding to the abnormal fluctuation, and local recovery feedback information is obtained;

[0045] Based on the operating status data, a comprehensive analysis is performed on the post-disaster recovery efficiency, disaster resistance, and post-disaster adaptive adjustment capability of the target power grid to determine the load distribution; based on the load distribution, a relative relationship between the recovery efficiency of the local area of ​​the power grid and the target power grid is analyzed;

[0046] Based on the local recovery feedback information and the relative relationship, an optimization direction of dynamic resource allocation is determined, thereby achieving optimized control of the target power grid.

[0047] As a preferred solution, the feature extraction module extracts key node features of the target power grid during the self-healing process based on the diffusion trend data, including:

[0048] The feature extraction module analyzes the diffusion trend data to obtain the fault diffusion speed;

[0049] When the fault diffusion speed exceeds a preset speed threshold, segmenting the diffusion trend data according to time points, determining the fault isolation speed data at each time point, and obtaining a fault isolation speed data set;

[0050] Based on the fault isolation speed dataset and the preset key node protection strategy, the node protection priority is sorted by a preset random forest model to obtain a key node protection sequence;

[0051] Through the key node protection sequence and the fault isolation speed data set, the impact of key node state changes on the fault diffusion trend is analyzed, and then the key node characteristics are obtained.

[0052] As a preferred solution, the solution planning module obtains a preliminary restoration path planning solution according to the dynamic response mechanism of the power grid, including:

[0053] The program planning module divides the target power grid into a plurality of partitions;

[0054] Determining resource allocation for each of the partitions according to a preset resource distribution ratio; determining a partition response mechanism for each of the partitions according to the power grid dynamic response mechanism;

[0055] Determining a partition control order according to resource allocation of each partition and a response mechanism of each partition;

[0056] Obtain a multi-stage emergency plan; optimize the multi-stage emergency plan according to the partition control sequence to obtain a preliminary recovery path planning scheme.

[0057] As a preferred solution, the operating status data includes operating status information of each partition; the optimization control module continuously tracks the recovery progress based on the operating status data, including:

[0058] The optimization control module monitors the operating status information of each partition and obtains the distribution of abnormal fluctuation areas;

[0059] Obtaining path restoration information for each partition based on the distribution of abnormal fluctuation areas, and then determining the restoration coverage status;

[0060] The restoration progress is determined according to the restoration coverage condition.

[0061] As a preferred solution, the matrix construction module obtains multi-dimensional impact data caused by disaster events from the target power grid's equipment operation logs, meteorological warning information, and communication network status, including:

[0062] The matrix construction module obtains original log records from the equipment operation log, wherein the original log records include fields associated with equipment damage conditions; and obtains extreme weather event data from the weather warning information;

[0063] Performing data fusion processing on the original log records and the extreme weather event data in chronological order to obtain a fused data set;

[0064] Based on the fused data set and combined with the communication network status, communication interruption distribution characteristics are obtained, thereby obtaining the multi-dimensional impact data.

[0065] As a preferred solution, the matrix construction module constructs an initial disaster impact matrix based on the multi-dimensional impact data, including:

[0066] The matrix construction module filters the multi-dimensional impact data through a pre-built support vector machine model to obtain a risk data set;

[0067] The risk dataset is converted into an initial disaster impact matrix.

[0068] Correspondingly, the present application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the disaster awareness-based power grid optimization control method.

[0069] Accordingly, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid optimization control method based on disaster awareness.

[0070] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0071] The present invention provides a power grid optimization control method, system, equipment and medium based on disaster awareness. The power grid optimization control method includes: obtaining multi-dimensional impact data caused by disaster events from the equipment operation logs, meteorological warning information and communication network status of the target power grid, and constructing an initial disaster impact matrix based on the multi-dimensional impact data; based on the initial disaster impact matrix, obtaining the diffusion trend data of the disaster event by tracking time series data analysis; according to the diffusion trend, extracting the key node characteristics of the target power grid in the self-healing process; according to the key node characteristics, constructing a power grid dynamic response mechanism; according to the power grid dynamic response mechanism, obtaining a preliminary recovery path planning scheme; the preliminary recovery path planning scheme includes a key load protection scheme and a resource scheduling scheme; obtaining the operating status data of the target power grid in real time, and continuously tracking the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection scheme and the resource scheduling scheme are corrected to obtain an optimized recovery path planning scheme, and the target power grid is optimized and controlled based on the optimized recovery path planning scheme. The present invention obtains multi-dimensional impact data caused by disaster events from the target power grid's equipment operation logs, meteorological warning information, and communication network status. The impact of disaster events can be obtained from multiple dimensions such as equipment damage, communication status, and weather. Multi-source data integration is achieved by constructing an initial disaster impact matrix. Time-series data tracking and analysis are used to obtain diffusion trend data of the disaster event, and key node features during the self-healing process are extracted. A dynamic response mechanism for the power grid is then constructed to obtain a preliminary recovery path planning scheme. During the power grid self-healing recovery process, the recovery progress is continuously tracked. When the progress threshold corresponding to the same time is not reached, the key load protection plan and resource scheduling plan are revised to obtain an optimized recovery path planning scheme, thereby achieving optimized control of the target power grid. Compared with existing control schemes that rely on static plans, the present invention can ensure that the power grid recovery is more closely aligned with its actual state. When the progress does not meet expectations (for example, when the progress threshold corresponding to the same time is not reached), timely intervention can be made to achieve optimized control, avoiding problems such as load distribution imbalance and control rigidity, and effectively improving the stability and reliability of the power grid during recovery. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 : A flow chart of an embodiment of a power grid optimization control method based on disaster awareness provided by the present invention.

[0073] Figure 2 : A flow chart of a preferred implementation mode 1 of an embodiment of a power grid optimization control method based on disaster awareness provided by the present invention.

[0074] Figure 3: A flow chart of a preferred implementation mode 2 of an embodiment of a power grid optimization control method based on disaster awareness provided by the present invention.

[0075] Figure 4 : A flow chart of a preferred implementation mode three of an embodiment of a power grid optimization control method based on disaster awareness provided by the present invention.

[0076] Figure 5 : A flow chart of a preferred implementation mode 4 of an embodiment of a power grid optimization control method based on disaster awareness provided by the present invention.

[0077] Figure 6 : A flow chart of a preferred implementation mode five of an embodiment of a power grid optimization control method based on disaster awareness provided by the present invention.

[0078] Figure 7 : A structural diagram of an embodiment of a power grid optimization control system based on disaster awareness provided by the present invention. DETAILED DESCRIPTION

[0079] The following will clearly and completely describe 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.

[0080] Embodiment one:

[0081] Please refer to Figure 1 , Figure 1 A flowchart of an embodiment of a disaster-aware power grid optimization control method provided by the present invention.

[0082] In this embodiment, the optimization control system can be applied to a control module of a target power grid, and the control module can be applied to a computer device, including but not limited to smartphones, laptops, tablet computers, desktop computers, physical servers, cloud servers and other devices.

[0083] Figure 1 The embodiment shown includes steps S101 to S105. Each step is described in detail as follows:

[0084] Step S101 : obtaining multi-dimensional impact data caused by a disaster event from the equipment operation logs, meteorological warning information, and communication network status of the target power grid, and constructing an initial disaster impact matrix based on the multi-dimensional impact data.

[0085] In this embodiment, the target power grid may be provided with a multi-dimensional perception system, which may acquire multi-source heterogeneous data, including but not limited to equipment operation logs of the target power grid, meteorological warning information, and communication network status.

[0086] like Figure 2 As shown, in a preferred embodiment, step S101 obtains multi-dimensional impact data caused by the disaster event from the equipment operation log, meteorological warning information and communication network status of the target power grid, including steps S201 to S203. Each step is described in detail as follows:

[0087] Step S201: obtaining an original log record from the equipment operation log, wherein the original log record includes a field associated with the equipment damage condition; and obtaining extreme weather event data from the weather warning information;

[0088] Step S202, performing data fusion processing on the original log records and the extreme weather event data in chronological order to obtain a fused data set;

[0089] Step S203 : Based on the fused data set and in combination with the communication network status, communication interruption distribution characteristics are obtained to obtain the multi-dimensional impact data.

[0090] In this preferred embodiment, when obtaining fields associated with equipment damage conditions in step S201, these fields can also be parsed and cleaned simultaneously to optimize data quality. When fusing the original log records with the extreme weather event data in chronological order in step S202, the original log records and extreme weather event data can be identified by identifying timestamps to identify the original log records and extreme weather event data at the same time. Furthermore, in step S203, based on this fused dataset and combined with the communication network status, the communication interruption distribution characteristics obtained can, to a certain extent, reflect the correlation between communication interruptions, equipment damage, and extreme weather events, thereby generating multi-dimensional impact data.

[0091] Furthermore, if Figure 3 As shown, step S101 constructs an initial disaster impact matrix based on the multi-dimensional impact data, including steps S301 to S302. Each step is described in detail as follows:

[0092] Step S301 : Screening the multi-dimensional impact data using a pre-built support vector machine model to obtain a risk data set.

[0093] Step S302: converting the risk data set into an initial disaster impact matrix.

[0094] For step S301, the multi-dimensional impact data can be risk predicted, identified or classified through a pre-built support vector machine model, so that the prediction, identification or classification results can be used as a reference to further screen the multi-dimensional impact data, and then the results of the further screening can be integrated and converted into an initial disaster impact matrix in the form of a data matrix.

[0095] Step S102 : Based on the initial disaster impact matrix, obtain the diffusion trend data of the disaster event by tracking time series data analysis.

[0096] In this embodiment, the information of the initial disaster impact matrix can be analyzed and extracted by a time series data analysis method to obtain the diffusion trend of the disaster event. The diffusion trend includes but is not limited to the speed of fault diffusion.

[0097] For example, based on the initial disaster impact matrix, the grid status changes at a time node every 6 hours can be extracted from the system operation data of the past 48 hours. For example, the voltage fluctuation rate of a key substation increases from the initial 2.5% to 4.8%. Combined with the correlation between equipment and load in the initial disaster impact matrix, the existing long-short-term memory network model can be used to predict the impact diffusion speed. It is calculated that the diffusion time of the voltage fluctuation on the surrounding nodes is 3 hours, and the fault diffusion speed can also be calculated.

[0098] From the above, obtaining diffusion trend data through similar methods as above will help to analyze and obtain key node features in subsequent steps.

[0099] Step S103 : extracting key node features of the target power grid during the self-healing process based on the diffusion trend data.

[0100] In this embodiment, the target power grid includes several nodes, and according to the importance of the nodes, some of the nodes may be determined as key nodes.

[0101] When a disaster occurs and causes a certain degree of failure in a local area of ​​the target power grid, the target power grid will begin self-recovery according to the preset control plan.

[0102] During the self-healing process, the power grid typically isolates and disconnects the faulty area. After repairing the faulty equipment, the equipment in the faulty area is restarted according to load priority (or other priorities designed based on other principles). This process is known as the self-healing process of the power grid. This step analyzes the diffusion trend data to extract key node characteristics during the target power grid's self-healing process.

[0103] In a preferred embodiment, Figure 4As shown, step S103 extracts the key node features of the target power grid during the self-healing process based on the diffusion trend data, including steps S401 to S404. Each step is described in detail as follows:

[0104] Step S401: Analyze the diffusion trend data to obtain the fault diffusion speed.

[0105] Step S402, when the fault diffusion speed exceeds a preset speed threshold, the diffusion trend data is segmented according to time points, divided into several time periods for analysis, and then the fault isolation speed data at each time point is determined to obtain a fault isolation speed data set.

[0106] Step S403 : Based on the fault isolation speed data set and in combination with a preset key node protection strategy, node protection priorities are sorted by a preset random forest model to obtain a key node protection sequence.

[0107] Step S404 : analyzing the impact of key node status changes on the fault diffusion trend through the key node protection sequence and the fault isolation speed data set, thereby obtaining key node characteristics.

[0108] This preferred implementation method obtains key node characteristics, and then in subsequent steps, analyzing the above key node characteristics can obtain the dynamic response law of the power grid to a certain extent, and then build a reasonable power grid dynamic response mechanism, laying the foundation for accurate planning of recovery paths.

[0109] Step S104, constructing a power grid dynamic response mechanism according to the key node characteristics; obtaining a preliminary restoration path planning scheme according to the power grid dynamic response mechanism; the preliminary restoration path planning scheme includes a key load protection scheme and a resource scheduling scheme.

[0110] In this embodiment, the dynamic response mechanism of the power grid can be understood as a number of data response rules. For example, when the system designs the above-mentioned data response rules with resource scheduling flexibility as one of its goals, a genetic algorithm can be used to optimize resource allocation, analyze the power grid operation data over the past 24 hours, and extract the load demand change rate every 4 hours. For example, if the load demand in a certain area increases from 100 MW to 120 MW, with a change rate of 20%, the algorithm dynamically adjusts the scheduling ratio of energy storage equipment and distributed power sources based on this data, and calculates the optimal scheduling solution to increase resource utilization to 92%. The above-mentioned calculation and response control logic of the scheduling process can be understood as the above-mentioned data response rules, and the superposition of several data response rules results in the above-mentioned dynamic response mechanism of the power grid.

[0111] In a preferred embodiment, Figure 5As shown, step S104 obtains a preliminary restoration path planning scheme according to the dynamic response mechanism of the power grid, including steps S501 to S504. Each step is described in detail as follows:

[0112] Step S501 : Divide the target power grid into a plurality of partitions; for example, partitions S1 , S2 , S3 , . . . , Sn in sequence, with a total of n partitions.

[0113] Step S502: determining resource allocation for each of the partitions according to a preset resource distribution ratio; and determining a partition response mechanism for each of the partitions according to the power grid dynamic response mechanism.

[0114] Step S503: determining a partition control order according to resource allocation of each partition and a response mechanism of each partition.

[0115] Step S504: obtaining a multi-stage emergency plan; optimizing the multi-stage emergency plan according to the partition control sequence to obtain a preliminary restoration path planning scheme.

[0116] In this preferred embodiment, the preset resource distribution ratio can be understood as the initial or default resource distribution ratio when a disaster occurs. By combining the partitioning results, the resource allocation of each partition can be preliminarily determined, and then decomposed according to the dynamic response mechanism of the power grid, the partition response mechanism corresponding to each partition is determined, and then the partition control order is further determined; this preferred embodiment uses the determined partition control order to optimize the multi-stage emergency plan, and can obtain a preliminary recovery path planning scheme to achieve sequential control of each partition while ensuring the rationality of resource allocation.

[0117] In some embodiments, in addition to considering resource allocation and scheduling, the critical load protection priority principle can also be considered to establish a control target for critical load protection. Therefore, the preliminary recovery path planning plan can include a critical load protection plan and a resource scheduling plan.

[0118] Step S105, obtaining the operating status data of the target power grid in real time; and continuously tracking the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection plan and the resource scheduling plan are corrected to obtain an optimized recovery path planning plan, and the target power grid is optimized and controlled based on the optimized recovery path planning plan.

[0119] In this embodiment, according to different partitions of the target power grid, the operating status data includes operating status information of each partition.

[0120] Continuously tracking the recovery progress based on the operating status data includes: monitoring the operating status information of each partition to obtain the distribution of abnormal fluctuation areas; obtaining path recovery information for each partition based on the abnormal fluctuation area distribution, and then determining the recovery coverage; and determining the recovery progress based on the recovery coverage. It is understood that in addition to determining the recovery progress based on the recovery coverage, the recovery progress can also be considered based on the time level of recovery.

[0121] This step continuously tracks the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time (different times can correspond to different progress thresholds in this embodiment, and the progress threshold settings at different times can be uniform or uneven, depending on the actual situation of the target power grid), the critical load protection plan and resource scheduling plan are revised to obtain an optimized recovery path planning plan.

[0122] In a preferred embodiment, Figure 6 The step S105 of optimizing and controlling the target power grid based on the optimized restoration path planning scheme includes steps S601 to S604. Each step is described in detail as follows:

[0123] Step S601: monitoring abnormal fluctuations of the target power grid according to the operating status data.

[0124] Step S602 : Based on the optimized recovery path planning scheme, combined with the preset system redundancy mechanism and the grid dynamic response mechanism, recovery control is performed on the local area of ​​the grid corresponding to the abnormal fluctuation, and local recovery feedback information is obtained.

[0125] Step S603, based on the operating status data, comprehensively analyze the post-disaster recovery efficiency, disaster resistance and post-disaster adaptive adjustment capability of the target power grid to determine the load distribution; based on the load distribution, analyze the relative relationship between the recovery efficiency of the local area of ​​the power grid and the target power grid.

[0126] Step S604: Based on the local recovery feedback information and the relative relationship, determine the optimization direction of dynamic resource allocation, thereby achieving optimized control of the target power grid.

[0127] In addition to monitoring the current operating status, this preferred embodiment can also combine the preset system redundancy mechanism and the power grid dynamic response mechanism to perform recovery control on the local area of ​​the power grid corresponding to the abnormal fluctuation and obtain local recovery feedback information; by analyzing the relative relationship between the recovery efficiency of the local area of ​​the power grid and the target power grid, combined with the above-mentioned local recovery feedback information as a reference, the optimization direction of dynamic resource allocation is determined, and further optimization control of the target power grid is achieved, realizing real-time optimization of dynamic resource allocation at multiple levels such as the real-time operating status of the power grid, real-time feedback, and local areas of the power grid, making the optimization control of the power grid more targeted and accurate.

[0128] Accordingly, if Figure 7 As shown, the present invention also provides a power grid optimization control system 700 based on disaster awareness, including a matrix construction module 701, an analysis module 702, a feature extraction module 703, a solution planning module 704 and an optimization control module 705; wherein,

[0129] The matrix construction module 701 is used to obtain multi-dimensional impact data caused by the disaster event from the equipment operation logs, meteorological warning information and communication network status of the target power grid, and construct an initial disaster impact matrix based on the multi-dimensional impact data;

[0130] The analysis module 702 is configured to obtain the diffusion trend data of the disaster event by tracking time series data analysis based on the initial disaster impact matrix;

[0131] The feature extraction module 703 is used to extract key node features of the target power grid during the self-healing process based on the diffusion trend data;

[0132] The solution planning module 704 is used to build a power grid dynamic response mechanism based on the key node characteristics; obtain a preliminary restoration path planning solution based on the power grid dynamic response mechanism; the preliminary restoration path planning solution includes a key load protection solution and a resource scheduling solution;

[0133] The optimization control module 705 is used to obtain the operating status data of the target power grid in real time; and continuously track the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection plan and resource scheduling plan are corrected to obtain an optimized recovery path planning plan, and the target power grid is optimized and controlled based on the optimized recovery path planning plan.

[0134] As a preferred solution, the optimization control module 705 performs optimization control on the target power grid based on the optimization restoration path planning solution, including:

[0135] The optimization control module 705 monitors abnormal fluctuations of the target power grid according to the operating status data;

[0136] Based on the optimized recovery path planning scheme, combined with the preset system redundancy mechanism and the grid dynamic response mechanism, recovery control is performed on the local area of ​​the grid corresponding to the abnormal fluctuation, and local recovery feedback information is obtained;

[0137] Based on the operating status data, a comprehensive analysis is performed on the post-disaster recovery efficiency, disaster resistance, and post-disaster adaptive adjustment capability of the target power grid to determine the load distribution; based on the load distribution, a relative relationship between the recovery efficiency of the local area of ​​the power grid and the target power grid is analyzed;

[0138] Based on the local recovery feedback information and the relative relationship, an optimization direction of dynamic resource allocation is determined, thereby achieving optimized control of the target power grid.

[0139] As a preferred solution, the feature extraction module 703 extracts key node features of the target power grid during the self-healing process based on the diffusion trend data, including:

[0140] The feature extraction module 703 analyzes the diffusion trend data to obtain the fault diffusion speed;

[0141] When the fault diffusion speed exceeds a preset speed threshold, segmenting the diffusion trend data according to time points, determining the fault isolation speed data at each time point, and obtaining a fault isolation speed data set;

[0142] Based on the fault isolation speed dataset and the preset key node protection strategy, the node protection priority is sorted by a preset random forest model to obtain a key node protection sequence;

[0143] Through the key node protection sequence and the fault isolation speed data set, the impact of key node state changes on the fault diffusion trend is analyzed, and then the key node characteristics are obtained.

[0144] As a preferred solution, the solution planning module 704 obtains a preliminary restoration path planning solution according to the dynamic response mechanism of the power grid, including:

[0145] The solution planning module 704 divides the target power grid into a plurality of partitions;

[0146] Determining resource allocation for each of the partitions according to a preset resource distribution ratio; determining a partition response mechanism for each of the partitions according to the power grid dynamic response mechanism;

[0147] Determining a partition control order according to resource allocation of each partition and a response mechanism of each partition;

[0148] Obtain a multi-stage emergency plan; optimize the multi-stage emergency plan according to the partition control sequence to obtain a preliminary recovery path planning scheme.

[0149] As a preferred solution, the operating status data includes operating status information of each partition; the optimization control module 705 continuously tracks the recovery progress based on the operating status data, including:

[0150] The optimization control module 705 monitors the operating status information of each partition and obtains the distribution of abnormal fluctuation areas;

[0151] Obtaining path restoration information for each partition based on the distribution of abnormal fluctuation areas, and then determining the restoration coverage status;

[0152] The restoration progress is determined according to the restoration coverage condition.

[0153] As a preferred solution, the matrix construction module 701 obtains multi-dimensional impact data caused by disaster events from the target power grid's equipment operation logs, meteorological warning information, and communication network status, including:

[0154] The matrix construction module 701 obtains original log records from the equipment operation log, wherein the original log records include fields associated with equipment damage conditions; and obtains extreme weather event data from the weather warning information;

[0155] Performing data fusion processing on the original log records and the extreme weather event data in chronological order to obtain a fused data set;

[0156] Based on the fused data set and combined with the communication network status, communication interruption distribution characteristics are obtained, thereby obtaining the multi-dimensional impact data.

[0157] As a preferred solution, the matrix construction module 701 constructs an initial disaster impact matrix based on the multi-dimensional impact data, including:

[0158] The matrix construction module 701 filters the multi-dimensional impact data using a pre-built support vector machine model to obtain a risk data set;

[0159] The risk dataset is converted into an initial disaster impact matrix.

[0160] Correspondingly, the present application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the disaster awareness-based power grid optimization control method.

[0161] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal and connects various parts of the entire terminal using various interfaces and lines.

[0162] The memory can be used to store the computer program. The processor implements the various functions of the terminal by running or executing the computer program stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data, a phone book, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0163] Accordingly, the present application also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid optimization control method based on disaster awareness.

[0164] If the integrated module of the disaster-aware power grid optimization control system is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium.

[0165] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0166] The present invention provides a power grid optimization control method, system, equipment and medium based on disaster awareness. The power grid optimization control method includes: obtaining multi-dimensional impact data caused by disaster events from the equipment operation logs, meteorological warning information and communication network status of the target power grid, and constructing an initial disaster impact matrix based on the multi-dimensional impact data; based on the initial disaster impact matrix, obtaining the diffusion trend data of the disaster event by tracking time series data analysis; according to the diffusion trend, extracting the key node characteristics of the target power grid in the self-healing process; according to the key node characteristics, constructing a power grid dynamic response mechanism; according to the power grid dynamic response mechanism, obtaining a preliminary recovery path planning scheme; the preliminary recovery path planning scheme includes a key load protection scheme and a resource scheduling scheme; obtaining the operating status data of the target power grid in real time, and continuously tracking the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection scheme and the resource scheduling scheme are corrected to obtain an optimized recovery path planning scheme, and the target power grid is optimized and controlled based on the optimized recovery path planning scheme. The present invention obtains multi-dimensional impact data caused by disaster events from the target power grid's equipment operation logs, meteorological warning information, and communication network status. The impact of disaster events can be obtained from multiple dimensions such as equipment damage, communication status, and weather. Multi-source data integration is achieved by constructing an initial disaster impact matrix. Time-series data tracking and analysis are used to obtain diffusion trend data of the disaster event, and key node features during the self-healing process are extracted. A dynamic response mechanism for the power grid is then constructed to obtain a preliminary recovery path planning scheme. During the power grid self-healing recovery process, the recovery progress is continuously tracked. When the progress threshold corresponding to the same time is not reached, the key load protection plan and resource scheduling plan are revised to obtain an optimized recovery path planning scheme, thereby achieving optimized control of the target power grid. Compared with existing control schemes that rely on static plans, the present invention can ensure that the power grid recovery is more closely aligned with its actual state. When the progress does not meet expectations (for example, when the progress threshold corresponding to the same time is not reached), timely intervention can be made to achieve optimized control, avoiding problems such as load distribution imbalance and control rigidity, and effectively improving the stability and reliability of the power grid during recovery.

[0167] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A power grid optimization control method based on disaster awareness, characterized in that: include: Obtain multi-dimensional impact data caused by the disaster event from the target power grid's equipment operation logs, meteorological warning information, and communication network status, and construct an initial disaster impact matrix based on the multi-dimensional impact data; Based on the initial disaster impact matrix, obtaining the diffusion trend data of the disaster event by tracking time series data analysis; Extracting key node features of the target power grid during the self-healing process based on the diffusion trend data; constructing a power grid dynamic response mechanism based on the key node characteristics; obtaining a preliminary restoration path planning scheme based on the power grid dynamic response mechanism; The preliminary restoration path planning scheme includes a critical load protection scheme and a resource scheduling scheme; Acquiring operating status data of the target power grid in real time; and continuously tracking the recovery progress based on the operating status data. When the recovery progress does not reach a progress threshold corresponding to the same time, revising the key load protection plan and resource scheduling plan to obtain an optimized recovery path planning plan, and optimizing and controlling the target power grid based on the optimized recovery path planning plan; The optimizing control of the target power grid based on the optimized restoration path planning scheme includes: monitoring abnormal fluctuations of the target power grid according to the operating status data; Based on the optimized recovery path planning scheme, combined with the preset system redundancy mechanism and the grid dynamic response mechanism, recovery control is performed on the local area of ​​the grid corresponding to the abnormal fluctuation, and local recovery feedback information is obtained; Based on the operating status data, a comprehensive analysis is performed on the post-disaster recovery efficiency, disaster resistance, and post-disaster adaptive adjustment capability of the target power grid to determine the load distribution; based on the load distribution, a relative relationship between the recovery efficiency of the local area of ​​the power grid and the target power grid is analyzed; Determining an optimization direction for dynamic resource allocation based on the local recovery feedback information and the relative relationship, thereby achieving optimized control of the target power grid; The step of obtaining a preliminary restoration path planning scheme according to the dynamic response mechanism of the power grid includes: Dividing the target power grid into a plurality of partitions; Determining resource allocation for each of the partitions according to a preset resource distribution ratio; determining a partition response mechanism for each of the partitions according to the power grid dynamic response mechanism; Determining a partition control order according to resource allocation of each partition and a response mechanism of each partition; Obtain a multi-stage emergency plan; optimize the multi-stage emergency plan according to the partition control sequence to obtain a preliminary recovery path planning scheme.

2. The power grid optimization control method based on disaster awareness according to claim 1, characterized in that: Extracting key node features of the target power grid during the self-healing process based on the diffusion trend data includes: Analyzing the diffusion trend data to obtain a fault diffusion speed; When the fault diffusion speed exceeds a preset speed threshold, segmenting the diffusion trend data according to time points, determining the fault isolation speed data at each time point, and obtaining a fault isolation speed data set; Based on the fault isolation speed dataset and the preset key node protection strategy, the node protection priority is sorted by a preset random forest model to obtain a key node protection sequence; Through the key node protection sequence and the fault isolation speed data set, the impact of key node state changes on the fault diffusion trend is analyzed, and then the key node characteristics are obtained.

3. The power grid optimization control method based on disaster awareness according to claim 1, characterized in that: The operating status data includes operating status information of each partition; The continuously tracking the recovery progress based on the operating status data includes: Monitor the operating status of each partition and obtain the distribution of abnormal fluctuation areas; Obtaining path restoration information for each partition based on the distribution of abnormal fluctuation areas, and then determining the restoration coverage status; The restoration progress is determined according to the restoration coverage condition.

4. The power grid optimization control method based on disaster awareness according to claim 1, characterized in that: The multi-dimensional impact data caused by the disaster event is obtained from the equipment operation logs, meteorological warning information and communication network status of the target power grid, including: Obtaining an original log record from the equipment operation log, wherein the original log record includes a field associated with the equipment damage condition; obtaining extreme weather event data from the weather warning information; Performing data fusion processing on the original log records and the extreme weather event data in chronological order to obtain a fused data set; Based on the fused data set and combined with the communication network status, communication interruption distribution characteristics are obtained, thereby obtaining the multi-dimensional impact data.

5. The power grid optimization control method based on disaster awareness according to claim 4, characterized in that: The constructing of an initial disaster impact matrix based on the multi-dimensional impact data includes: The multi-dimensional impact data is screened by using a pre-built support vector machine model to obtain a risk data set; The risk dataset is converted into an initial disaster impact matrix.

6. A power grid optimization control system based on disaster awareness, characterized in that: The power grid optimization control method based on disaster awareness according to any one of claims 1 to 5 is adopted; the power grid optimization control system includes a matrix construction module, an analysis module, a feature extraction module, a program planning module and an optimization control module; wherein, The matrix construction module is used to obtain multi-dimensional impact data caused by the disaster event from the equipment operation logs, meteorological warning information and communication network status of the target power grid, and to construct an initial disaster impact matrix based on the multi-dimensional impact data; The analysis module is configured to obtain the diffusion trend data of the disaster event by tracking time series data analysis based on the initial disaster impact matrix; The feature extraction module is used to extract key node features of the target power grid during the self-healing process based on the diffusion trend data; The program planning module is used to construct a power grid dynamic response mechanism based on the characteristics of the key nodes; obtain a preliminary restoration path planning scheme based on the power grid dynamic response mechanism; the preliminary restoration path planning scheme includes a key load protection scheme and a resource scheduling scheme; The optimization control module is used to obtain the operating status data of the target power grid in real time; and continuously track the recovery progress based on the operating status data. When the recovery progress does not reach the progress threshold corresponding to the same time, the key load protection plan and resource scheduling plan are revised to obtain an optimized recovery path planning plan, and the target power grid is optimized and controlled based on the optimized recovery path planning plan.

7. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for optimizing and controlling a power grid based on disaster awareness according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the disaster-aware-based power grid optimization control method according to any one of claims 1 to 5.

Images