Optimal configuration method and system for multi-grid peak load regulation based on big data

Abstract

The present invention relates to the field of power processing technology, and in particular to an optimization configuration method and system for multi-grid peak-shaving based on big data. The method comprises the following steps: performing grid node labeling analysis and big data analysis on the grid system to obtain multi-grid energy production status data and multi-grid power transmission line status data; performing power supply load analysis based on the multi-grid energy production status data and the multi-grid power transmission line status data to obtain multi-grid power supply load data; performing time-series peak-shaving operation analysis based on the multi-grid power supply load data to obtain a multi-grid power supply load peak-shaving operation distribution diagram; performing operation abnormality analysis and frequency conversion analysis on the multi-grid power supply load peak-shaving operation distribution diagram to obtain multi-grid power supply load abnormal frequency data; performing frequency modulation optimization configuration analysis based on the multi-grid power supply load abnormal frequency data to obtain multi-grid power supply load peak-shaving optimization configuration data. The present invention can achieve more efficient load peak-shaving.

Description

Technical Field

[0001] Optimal configuration method and system for multi-grid peak load regulation based on big data Background Art

[0002] With the expansion of the scale of power grid systems and the large-scale access of renewable energy, the dispatching and operation of power grid systems face greater challenges. At the same time, the peak load regulation of power grid systems has also become an important challenge for power grid system management. However, traditional power grid peak regulation methods are limited by insufficient data, low efficiency, and the inability to meet the target power requirements of multi-grid power supply load peak regulation. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an optimization configuration method and system for multi-grid peak regulation based on big data to solve at least one of the above technical problems.

[0004] To achieve the above purpose, an optimization configuration method for multi-grid peak load regulation based on big data includes the following steps:

[0005] Step S1: Perform grid node labeling analysis on the grid system to obtain multiple grid system nodes; perform big data analysis on the multiple grid system nodes to obtain multiple grid energy production status data and multiple grid power transmission line status data; perform power supply load analysis on the grid system based on the multiple grid energy production status data and the multiple grid power transmission line status data to obtain multiple grid power supply load data;

[0006] Step S2: performing a time sequence peak load regulation operation analysis on the nodes of the multi-grid system according to the multi-grid power supply load data to obtain a multi-grid power supply load peak load regulation operation distribution diagram;

[0007] Step S3: Performing operation abnormality analysis on the peak load regulation operation distribution diagram of the power supply loads of multiple power grids to obtain operation abnormality data of the power supply loads of multiple power grids; performing frequency conversion analysis on the operation abnormality data of the power supply loads of multiple power grids to obtain abnormal frequency data of the power supply loads of multiple power grids;

[0008] Step S4: Based on the abnormal frequency data of the power supply loads of the multiple power grids, a frequency regulation optimization configuration analysis is performed on the peak-shaving operation distribution diagram of the power supply loads of the multiple power grids to obtain the peak-shaving optimization configuration data of the power supply loads of the multiple power grids.

[0009] The present invention firstly analyzes the grid node marking of the grid system. The importance of this step is that the accurate marking of the grid nodes can lay the foundation for the subsequent big data analysis process. Obtaining accurate node information is the premise for the management and optimization of the grid system, which can realize the clear description of the structure of multiple grid systems and effectively improve the stability and reliability of the grid system. By performing big data analysis on the nodes of multiple grid systems, the energy production capacity of each grid system and the transmission of electricity in the grid system can be understood, which greatly improves the scope of data, thereby obtaining rich energy production and power transmission line data, which not only provides a deep understanding of the topological structure of the grid system, but also provides a comprehensive and reliable basis for the subsequent power supply load analysis. At the same time, by analyzing the power supply load of the grid system according to the energy production status data of multiple grids and the power transmission line status data of multiple grids, the load situation of the grid system can be fully understood, including the power supply demand of each node and the overall load situation of the system, which provides important data support for grid planning and scheduling, and can also accurately grasp the power supply load characteristics of multiple grids, and provide necessary input for the subsequent peak load operation analysis. Secondly, by analyzing the time-sequential peak-shaving operation of the nodes of the multi-grid system according to the power supply load data of multiple power grids, it is possible to understand the power supply load distribution of the power grid system in different time periods, which is helpful to more reasonably allocate power resources during the peak period of power supply load, improve the dispatching efficiency and operation stability of the power grid system, and thus form a multi-grid power supply load peak-shaving operation distribution map. This distribution map has intuitive guiding significance for system operators, which can help them better plan the operation strategy of the power grid system, thereby improving the efficiency and stability of peak-shaving operation. Then, by performing an operation abnormality analysis on the multi-grid power supply load peak-shaving operation distribution map, potential problems and abnormal conditions can be identified early. And by analyzing the abnormal operation data of the multi-grid power supply load, the nature and impact of abnormal events can be deeply understood. Furthermore, frequency conversion analysis helps to convert abnormal data into frequency domain information and provide accurate cognition of abnormal frequencies, which provides strong data support for the system to deal with abnormal conditions and lays the foundation for the next step of frequency optimization configuration analysis. Finally, by performing frequency optimization configuration analysis on the multi-grid power supply load peak-shaving operation distribution map based on the abnormal frequency data of the multi-grid power supply load, the peak-shaving operation performance of the power grid system under abnormal frequency conditions can be improved. By fine-tuning the abnormal frequency parameters of the system, it is possible to respond more flexibly to abnormal frequency fluctuations, ensuring that the power grid system can maintain efficient and stable operation under various circumstances, thereby providing specific peak-shaving optimization suggestions for the power grid system and making the power grid system more adaptable to the changing peak-shaving power requirements of the power supply load.

[0010] Preferably, the present invention further provides an optimization configuration system based on big data multi-grid peak regulation, which is used to execute the optimization configuration method based on big data multi-grid peak regulation as described above, and the optimization configuration system based on big data multi-grid peak regulation comprises:

[0011] The power supply load analysis module of the power grid system is used to perform grid node labeling analysis on the power grid system to obtain multiple power grid system nodes; perform big data analysis on multiple power grid system nodes to obtain multiple power grid energy production status data and multiple power grid power transmission line status data; perform power supply load analysis on the power grid system based on the multiple power grid energy production status data and the multiple power grid power transmission line status data, thereby obtaining multiple power grid power supply load data;

[0012] The power grid load peak load analysis module is used to analyze the timing peak load operation of the power grid system according to the power grid load data of multiple power grids, so as to obtain the peak load operation distribution diagram of multiple power grids;

[0013] The peak load operation abnormality analysis module is used to perform operation abnormality analysis on the peak load operation distribution diagram of multiple power grids to obtain the operation abnormality data of multiple power grids; perform frequency conversion analysis on the operation abnormality data of multiple power grids to obtain the abnormal frequency data of multiple power grids;

[0014] The power supply load abnormal frequency regulation optimization module is used to perform frequency regulation optimization configuration analysis on the peak-shaving operation distribution diagram of the power supply load of multiple power grids according to the abnormal frequency data of the power supply load of multiple power grids, so as to obtain the peak-shaving optimization configuration data of the power supply load of multiple power grids.

[0015] In summary, the present invention provides an optimization configuration system based on big data multi-grid peak regulation, which is composed of a power grid system power supply load analysis module, a power grid power supply load peak regulation analysis module, a peak regulation operation abnormality analysis module, and a power supply load abnormal frequency modulation optimization module. It can realize any one of the optimization configuration methods based on big data multi-grid peak regulation described in the present invention, and is used to combine the operations between computer programs running on each module to realize an optimization configuration method based on big data multi-grid peak regulation. The internal structures of the system cooperate with each other, and the power supply load data of the power grid system is accurately obtained by combining the energy production status and power transmission status of the multi-grid system, and peak regulation analysis is performed based on the power supply load data to reduce the volatility of the overall power grid power supply load. At the same time, the abnormal operation during the peak regulation process is analyzed to perform abnormal frequency modulation optimization, so as to determine the optimal configuration parameters to achieve the best performance of power grid system peak regulation under abnormal conditions. This can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient multi-grid peak regulation optimization configuration process, thereby simplifying the operation process of the optimization configuration system based on big data multi-grid peak regulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0017] Figure 1 It is a schematic flow chart of the steps of the optimization configuration method of multi-grid peak regulation based on big data of the present invention;

[0018] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0019] Figure 3 for Figure 2 Detailed step flow chart of step S16 in FIG. DETAILED DESCRIPTION

[0020] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0022] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0023] To achieve this, please refer to Figures 1 to 3 The present invention provides an optimization configuration method for multi-grid peak regulation based on big data, comprising the following steps:

[0024] Step S1: Perform grid node labeling analysis on the grid system to obtain multiple grid system nodes; perform big data analysis on the multiple grid system nodes to obtain multiple grid energy production status data and multiple grid power transmission line status data; perform power supply load analysis on the grid system based on the multiple grid energy production status data and the multiple grid power transmission line status data to obtain multiple grid power supply load data;

[0025] Step S2: performing a time sequence peak load regulation operation analysis on the nodes of the multi-grid system according to the multi-grid power supply load data to obtain a multi-grid power supply load peak load regulation operation distribution diagram;

[0026] Step S3: Performing operation abnormality analysis on the peak load regulation operation distribution diagram of the power supply loads of multiple power grids to obtain operation abnormality data of the power supply loads of multiple power grids; performing frequency conversion analysis on the operation abnormality data of the power supply loads of multiple power grids to obtain abnormal frequency data of the power supply loads of multiple power grids;

[0027] Step S4: Based on the abnormal frequency data of the power supply loads of the multiple power grids, a frequency regulation optimization configuration analysis is performed on the peak-shaving operation distribution diagram of the power supply loads of the multiple power grids to obtain the peak-shaving optimization configuration data of the power supply loads of the multiple power grids.

[0028] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic flow chart of the steps of the optimization configuration method based on big data multi-grid peak regulation of the present invention. In this example, the steps of the optimization configuration method based on big data multi-grid peak regulation include:

[0029] Step S1: Perform grid node labeling analysis on the grid system to obtain multiple grid system nodes; perform big data analysis on the multiple grid system nodes to obtain multiple grid energy production status data and multiple grid power transmission line status data; perform power supply load analysis on the grid system based on the multiple grid energy production status data and the multiple grid power transmission line status data to obtain multiple grid power supply load data;

[0030] The embodiment of the present invention analyzes the power grid system by using topological analysis technology to determine the interconnection relationship between the components of multiple power grid systems, forms a power grid system topology, and identifies each node in the power grid system, including power stations, substations, etc., by marking nodes on the analyzed power grid system topology, thereby obtaining multiple power grid system nodes. Then, by using corresponding sensors to collect energy production data of each multi-grid system node, including information such as power generation, power generation mode, energy type, and specific power transmission channel conditions between each multi-grid system node, and by using big data analysis methods to analyze the collected data to determine the energy production status of each node, including the power generation of various energy production equipment, the status of energy storage equipment, etc., and detect and evaluate the power transmission status between each multi-grid system node, including line capacity, impedance, voltage, etc., thereby obtaining multi-grid energy production status data and multi-grid power transmission line status data. Finally, by analyzing the power grid system according to the multi-grid energy production status data and multi-grid power transmission line status data obtained by analysis, the load status of the power grid system is fully understood, and finally the multi-grid power supply load data is obtained.

[0031] Step S2: performing a time sequence peak load regulation operation analysis on the nodes of the multi-grid system according to the multi-grid power supply load data to obtain a multi-grid power supply load peak load regulation operation distribution diagram;

[0032] The embodiment of the present invention first cleans the collected power supply load data of multiple power grids to deal with problems such as missing values ​​and abnormal values ​​to ensure the accuracy and completeness of the data. At the same time, the cleaned data is converted into a time series form by using a time series analysis method to establish a mapping relationship between time and power supply load demand, and a power calculation method is used for calculation to obtain the power supply load power value corresponding to the time series data. The calculated power supply load power value is plotted by using a mathematical statistical method to reflect the power change of the power supply load at different times, and the peak and trough of the power supply load are revealed to perform a time series peak-shaving operation analysis to realize the power peak-shaving process of the power supply load power change, which helps the power grid system to allocate power resources more reasonably during the peak period, and finally obtains a multi-grid power supply load peak-shaving operation distribution diagram.

[0033] Step S3: Performing operation abnormality analysis on the peak load regulation operation distribution diagram of the power supply loads of multiple power grids to obtain operation abnormality data of the power supply loads of multiple power grids; performing frequency conversion analysis on the operation abnormality data of the power supply loads of multiple power grids to obtain abnormal frequency data of the power supply loads of multiple power grids;

[0034] The embodiment of the present invention uses an abnormality detection algorithm (including statistical methods, machine learning methods (such as isolation forest, One-Class SVM) and other algorithms) to analyze the peak-shaving operation distribution map of the multi-grid power supply load to accurately detect abnormal operation data that is significantly different from normal operation in the peak-shaving operation distribution map of the multi-grid power supply load, thereby obtaining abnormal operation data of the multi-grid power supply load. Then, the signal conversion is performed on the abnormal operation data of the multi-grid power supply load by using a signal conversion algorithm to convert the detected abnormal data into an abnormal signal form that is easier to analyze, and statistical analysis is performed based on the fluctuation intensity and change trend of the abnormal signal of the multi-grid power supply load in different time periods to statistically quantify the abnormal frequency of the abnormal signal of the multi-grid power supply load, and finally obtain the abnormal frequency data of the multi-grid power supply load.

[0035] Step S4: Based on the abnormal frequency data of the power supply loads of the multiple power grids, a frequency regulation optimization configuration analysis is performed on the peak-shaving operation distribution diagram of the power supply loads of the multiple power grids to obtain the peak-shaving optimization configuration data of the power supply loads of the multiple power grids.

[0036] In the embodiment of the present invention, the abnormal frequency data of the power supply loads of multiple power grids are divided by using a preset frequency time range interval (for example, a time scale of 5 minutes) to divide the abnormal frequency data of the power supply loads of multiple power grids into different abnormal frequency intervals, and the peak-shaving operation distribution diagram of the power supply loads of multiple power grids obtained after the peak-shaving process is collaboratively divided by using the abnormal frequency intervals obtained after the division, so as to obtain the corresponding abnormal frequency interval area on the peak-shaving operation distribution diagram of the power supply loads of multiple power grids, and further quantitatively analyze the impact of the abnormality on the power on the basis of the abnormal frequency interval area, so as to analyze and reflect the power adjustment demand of each abnormal frequency interval area, and calculate the corresponding adjustment capacity value, and then, the peak-shaving operation distribution diagram of the power supply loads of multiple power grids is optimized by frequency modulation based on the calculated adjustment capacity value and in combination with the frequency modulation optimization objective function, so as to ensure that the power grid system can still maintain a stable operation state under abnormal frequency conditions, and at the same time, determine the best optimization configuration scheme, including adjusting the output of the power grid system generator, using energy storage equipment, etc., so that the best performance of the peak-shaving of the power supply loads of the multiple power grid systems can be achieved under abnormal conditions, and finally obtain the peak-shaving optimization configuration data of the power supply loads of multiple power grids.

[0037] The present invention firstly analyzes the grid node marking of the grid system. The importance of this step is that the accurate marking of the grid nodes can lay the foundation for the subsequent big data analysis process. Obtaining accurate node information is the premise for the management and optimization of the grid system, which can realize the clear description of the structure of multiple grid systems and effectively improve the stability and reliability of the grid system. By performing big data analysis on the nodes of multiple grid systems, the energy production capacity of each grid system and the transmission of electricity in the grid system can be understood, which greatly improves the scope of data, thereby obtaining rich energy production and power transmission line data, which not only provides a deep understanding of the topological structure of the grid system, but also provides a comprehensive and reliable basis for the subsequent power supply load analysis. At the same time, by analyzing the power supply load of the grid system according to the energy production status data of multiple grids and the power transmission line status data of multiple grids, the load situation of the grid system can be fully understood, including the power supply demand of each node and the overall load situation of the system, which provides important data support for grid planning and scheduling, and can also accurately grasp the power supply load characteristics of multiple grids, and provide necessary input for the subsequent peak load operation analysis. Secondly, by analyzing the time-sequential peak-shaving operation of the nodes of the multi-grid system according to the power supply load data of multiple power grids, it is possible to understand the power supply load distribution of the power grid system in different time periods, which is helpful to more reasonably allocate power resources during the peak period of power supply load, improve the dispatching efficiency and operation stability of the power grid system, and thus form a multi-grid power supply load peak-shaving operation distribution map. This distribution map has intuitive guiding significance for system operators, which can help them better plan the operation strategy of the power grid system, thereby improving the efficiency and stability of peak-shaving operation. Then, by performing an operation abnormality analysis on the multi-grid power supply load peak-shaving operation distribution map, potential problems and abnormal conditions can be identified early. And by analyzing the abnormal operation data of the multi-grid power supply load, the nature and impact of abnormal events can be deeply understood. Furthermore, frequency conversion analysis helps to convert abnormal data into frequency domain information and provide accurate cognition of abnormal frequencies, which provides strong data support for the system to deal with abnormal conditions and lays the foundation for the next step of frequency optimization configuration analysis. Finally, by performing frequency optimization configuration analysis on the multi-grid power supply load peak-shaving operation distribution map based on the abnormal frequency data of the multi-grid power supply load, the peak-shaving operation performance of the power grid system under abnormal frequency conditions can be improved. By fine-tuning the abnormal frequency parameters of the system, it is possible to respond more flexibly to abnormal frequency fluctuations, ensuring that the power grid system can maintain efficient and stable operation under various circumstances, thereby providing specific peak-shaving optimization suggestions for the power grid system and making the power grid system more adaptable to the changing peak-shaving power requirements of the power supply load.

[0038] Preferably, step S1 comprises the following steps:

[0039] Step S11: Analyze the topology of the power grid system to obtain a topology distribution diagram of multiple power grid systems;

[0040] Step S12: performing grid node labeling analysis on the multi-grid system topology structure distribution diagram to obtain multi-grid system nodes;

[0041] Step S13: performing energy production analysis on multiple power grid system nodes to obtain energy production status data of multiple power grids;

[0042] Step S14: extracting power transmission lines from multiple power grid system nodes to obtain node power transmission line data;

[0043] Step S15: performing power transmission detection on the nodes of the multi-grid system according to the node power transmission line data to obtain the multi-grid power transmission line status data;

[0044] Step S16: Analyze the power supply load of the power grid system according to the energy production status data of the multiple power grids and the power transmission line status data of the multiple power grids to obtain the power supply load data of the multiple power grids.

[0045] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0046] Step S11: Analyze the topology of the power grid system to obtain a topology distribution diagram of multiple power grid systems;

[0047] The embodiment of the present invention analyzes the power grid system by using topology analysis technology to determine the interconnection relationship between the components of multiple power grid systems, forming a topological structure of the power grid system, and draws a corresponding topological structure distribution map based on the analyzed power grid system topological structure to clearly display the connection relationship between the various power grid systems, and finally obtain a topological structure distribution map of multiple power grid systems.

[0048] Step S12: performing grid node labeling analysis on the multi-grid system topology structure distribution diagram to obtain multi-grid system nodes;

[0049] The embodiment of the present invention identifies various nodes in the power grid system, including power stations, substations, etc., by marking nodes on a topological structure distribution diagram of a multi-grid system, and finally obtains multi-grid system nodes.

[0050] Step S13: performing energy production analysis on multiple power grid system nodes to obtain energy production status data of multiple power grids;

[0051] The embodiment of the present invention collects energy production data of each multi-grid system node by using corresponding sensors, including information such as power generation, power generation method, energy type, etc., and then analyzes the collected data by using a data analysis method to determine the energy production status of each node, including the power generation of various energy production equipment, the status of energy storage equipment, etc., and finally obtains multi-grid energy production status data.

[0052] Step S14: extracting power transmission lines from multiple power grid system nodes to obtain node power transmission line data;

[0053] The embodiment of the present invention extracts the specific channel conditions of power transmission between the nodes of each multi-grid system according to the previous topological structure and the node information of the multi-grid system, and finally obtains the node power transmission line data.

[0054] Step S15: performing power transmission detection on the nodes of the multi-grid system according to the node power transmission line data to obtain the multi-grid power transmission line status data;

[0055] The embodiment of the present invention detects the corresponding multi-grid system nodes according to the power transmission lines in the node power transmission line data to detect and evaluate the power transmission status between each multi-grid system node, including line capacity, impedance, voltage and other information, and finally obtains the multi-grid power transmission line status data.

[0056] Step S16: Analyze the power supply load of the power grid system according to the energy production status data of the multiple power grids and the power transmission line status data of the multiple power grids to obtain the power supply load data of the multiple power grids.

[0057] The embodiment of the present invention analyzes the power grid system based on the analyzed multi-grid energy production status data and multi-grid power transmission line status data to fully understand the load situation of the power grid system, including the power supply demand of each node and the overall load situation of the system, and finally obtains the multi-grid power supply load data.

[0058] The present invention firstly analyzes the topological structure of the power grid system, which is the basis for the planning and management of the power grid system. Through this step, the topological structure distribution map of multiple power grid systems can be obtained, which can provide a clear understanding of the interconnection relationship between the components of multiple power grid systems, and provide a reliable topological basis for subsequent node labeling and energy analysis. This comprehensive structural analysis can provide guidance for the subsequent processing process. At the same time, by analyzing the topological structure distribution map of the multiple power grid systems, the importance of this step is that the accurate labeling of the power grid nodes can lay the foundation for subsequent energy production analysis and power transmission line extraction. Obtaining accurate node information is a prerequisite for power grid system management and optimization, which can effectively improve the stability and reliability of the system. Secondly, by analyzing the energy production of the nodes of the multiple power grid systems, the energy production capacity of each power grid system can be understood, including the output and distribution of various energy sources, which provides key information for the energy dispatching and optimization of the power grid system, and helps to improve the energy utilization efficiency and the sustainability of the system. Then, by extracting the transmission lines of the nodes of the multiple power grid systems, a specific channel for power transmission can be established, which provides a clear path for power flow, which is the basis for the operation of the power grid system and also provides basic data for subsequent power transmission detection. Next, by performing power transmission detection on the nodes of the multi-grid system based on the node power transmission line data, the power transmission situation in the power grid system can be understood through the power transmission line, including the line load, loss and other aspects of the data, which provides key insights into the efficiency and stability of power transmission and provides guidance for the improvement and optimization of the power grid system. Finally, by performing power supply load analysis on the power grid system based on the multi-grid energy production status data and the multi-grid power transmission line status data, the load situation of the power grid system can be fully understood, including the power supply demand of each node and the overall load situation of the system, which provides important data support for power grid planning and scheduling, and helps to improve the reliability and efficiency of the power grid.

[0059] Preferably, step S16 comprises the following steps:

[0060] Step S161: performing energy savings forecasting analysis on the power grid system according to the energy production status data of multiple power grids to obtain energy savings status data of multiple power grids;

[0061] Step S162: performing power generation capacity forecasting and analysis on the power grid system according to the power transmission line status data of multiple power grids to obtain power generation capacity data of multiple power grids;

[0062] Step S163: Perform power supply load analysis on the energy storage status data of multiple power grids and the power generation capacity data of multiple power grids to obtain power supply load data of multiple power grids.

[0063] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 1 is a schematic diagram of a detailed step flow chart of step S16 in FIG. 1 . In this embodiment, step S16 includes the following steps:

[0064] Step S161: performing energy savings forecasting analysis on the power grid system according to the energy production status data of multiple power grids to obtain energy savings status data of multiple power grids;

[0065] The embodiment of the present invention uses the energy production status data of multiple power grids (including the power generation of various energy production equipment, the status of energy storage equipment, etc.) and combines relevant algorithms or models to perform predictive analysis on the power grid system to predict and evaluate the energy storage status of the power grid system, including information such as the capacity of energy storage equipment, charging and discharging efficiency, and energy storage status, and finally obtains the energy storage status data of multiple power grids.

[0066] Step S162: performing power generation capacity forecasting and analysis on the power grid system according to the power transmission line status data of multiple power grids to obtain power generation capacity data of multiple power grids;

[0067] The embodiment of the present invention uses the power transmission line status data of multiple power grids (including line capacity, impedance, voltage and other information) and combines relevant algorithms or models to perform predictive analysis on the power grid system to predict and evaluate the power generation capacity of the power grid system, including the capacity, power generation efficiency, power generation method and other information of various power generation equipment in the power grid system, and finally obtains the power generation capacity data of multiple power grids.

[0068] Step S163: Perform power supply load analysis on the energy storage status data of multiple power grids and the power generation capacity data of multiple power grids to obtain power supply load data of multiple power grids.

[0069] The embodiment of the present invention first ensures the accuracy and consistency of the data by collating and cleaning the energy storage status data of multiple power grids and the power generation capacity data of multiple power grids, and then analyzes the cleaned energy storage status data of multiple power grids and the power generation capacity data of multiple power grids to determine the power supply load situation of the power grid system, and finally obtains the power supply load data of multiple power grids.

[0070] The present invention firstly predicts and analyzes the energy savings of the power grid system according to the energy production status data of multiple power grids, and can predict and evaluate the energy savings of the power grid system, which provides an important basis for formulating effective energy scheduling and energy storage strategies, and helps to improve the reliability and stability of the power grid system. By deeply understanding the energy savings status, the power grid system can better cope with changing energy demand and market fluctuations. Then, by predicting and analyzing the power generation capacity of the power grid system according to the status data of the power transmission lines of multiple power grids, the key to this step is to predict and evaluate the power generation capacity of the power grid system by analyzing the load, loss and other data of the power transmission lines, which provides key information for the scheduling and planning of the power grid system, and helps to ensure that the system maintains stable operation when the power supply load fluctuates. By understanding the power generation capacity data, the power grid system can optimize the utilization of power generation resources and improve energy utilization efficiency. Finally, by performing power supply load analysis on the energy storage status data of multiple power grids and the power generation capacity data of multiple power grids, energy savings and power generation capacity can be comprehensively considered to fully understand the power supply load of the power grid system. By analyzing power supply load data, the power grid system can better dispatch electricity, achieve optimized energy distribution, and improve the quality and reliability of power supply. This integrated analysis can enable the power grid system to respond more flexibly to different load demands and energy supply conditions, thereby improving overall operating efficiency.

[0071] Preferably, step S163 includes the following steps:

[0072] Step S1631: performing energy storage power supply load analysis on the energy storage status data of multiple power grids, obtaining the first power supply load data of the energy storage of multiple power grids, and assigning a weight to the first power supply load;

[0073] The embodiment of the present invention analyzes the multi-grid energy storage status data (including information such as energy storage device capacity, charging and discharging efficiency, and energy storage status) obtained through prediction and analysis to comprehensively analyze and understand the impact of energy storage status on the power supply load of the power grid system, thereby obtaining the multi-grid energy storage first power supply load data. At the same time, the multi-grid energy storage first power supply load data obtained through analysis is given corresponding weights to quantify the contribution of the energy storage status of each power grid system to the power supply load, and finally obtain the first power supply load weight.

[0074] Step S1632: performing power generation load analysis on the first power supply load data of the multi-grid energy storage according to the power generation capacity data of the multi-grid, obtaining the second power supply load data of the multi-grid power generation, and assigning a weight to the second power supply load;

[0075] The embodiment of the present invention analyzes the first power supply load data of multi-grid energy storage according to the predicted multi-grid power generation capacity data (including the capacity, power generation efficiency, power generation mode and other information of various power generation equipment in the power grid system), so as to further refine the analysis and understand the contribution evaluation of the power generation capacity to the power supply load of the power grid system, thereby obtaining the second power supply load data of multi-grid power generation. At the same time, the second power supply load data of multi-grid power generation obtained by analysis is given a corresponding weight to quantify the contribution of the power generation capacity to the power supply load satisfaction, and finally obtain the second power supply load weight.

[0076] Step S1633: performing power supply load fluctuation analysis on the first power supply load data of the multi-grid energy storage and the second power supply load data of the multi-grid power generation to obtain the first power supply load fluctuation data of the multi-grid and the second power supply load fluctuation data of the multi-grid;

[0077] The embodiment of the present invention analyzes the first power supply load data of multi-grid energy storage and the second power supply load data of multi-grid power generation by using a time series analysis method or other data fluctuation technology, so as to fully understand the fluctuation of load data due to energy storage and power generation capacity, and finally obtain the first power supply load fluctuation data of multi-grid and the second power supply load fluctuation data of multi-grid.

[0078] Step S1634: reconstructing the first power supply load weight according to the first power supply load fluctuation data of the multi-grid to obtain the first power supply load reconstruction weight; reconstructing the second power supply load weight according to the second power supply load fluctuation data of the multi-grid to obtain the second power supply load reconstruction weight;

[0079] The embodiment of the present invention reconstructs the assigned first power supply load weight according to the power supply load fluctuation change of the first power supply load fluctuation data of the multi-power grid, and timely and dynamically adjusts the first power supply load weight according to the fluctuation of the first power supply load, thereby obtaining the first power supply load reconstruction weight. At the same time, the assigned second power supply load weight is reconstructed according to the power supply load fluctuation change of the second power supply load fluctuation data of the multi-power grid, and timely and dynamically adjusts the second power supply load weight according to the fluctuation of the second power supply load, thereby obtaining the second power supply load reconstruction weight.

[0080] Step S1635: reconstruct and fuse the multi-grid energy storage first power supply load data and the multi-grid power generation second power supply load data according to the first power supply load reconstruction weight and the second power supply load reconstruction weight to obtain the multi-grid power supply load data.

[0081] The embodiment of the present invention analyzes the corresponding multi-grid energy storage first power supply load data and multi-grid power generation second power supply load data by using the reconstructed first power supply load reconstruction weight and the second power supply load weight, so as to comprehensively consider the contribution and volatility of each node to consider the load conditions of energy storage power supply and power generation power supply, and finally obtain the multi-grid power supply load data.

[0082] The present invention firstly analyzes the energy storage power supply load of the multi-grid energy storage status data, and can obtain the first power supply load data of the multi-grid energy storage, and assign corresponding weights to these data. The key to this step is that by comprehensively considering the energy storage status, it can identify and quantify the contribution of each multi-grid system node in meeting the grid load. The process of assigning weights helps to more accurately reflect the importance of each node to the power supply, and provides a reliable basis for subsequent load analysis and decision-making. Secondly, by analyzing the first power supply load data of the multi-grid energy storage according to the power generation capacity of the multi-grid power generation capacity data, it is possible to obtain the second power supply load data of the multi-grid power generation, and assign appropriate weights to these data. The key to this step is that by comprehensively considering the power generation capacity, it is possible to further refine the power supply contribution evaluation of each node. By assigning weights to the second power supply load data, the contribution of the power generation capacity in meeting the power supply load can be better reflected, laying the foundation for subsequent integrated analysis. Then, by analyzing the power supply load fluctuation of the first power supply load data of multi-grid energy storage and the second power supply load data of multi-grid power generation, we can fully understand the fluctuation of energy storage and power generation capacity on load data, and more accurately capture the fluctuation characteristics of the power supply of the power grid system, providing substantial support for subsequent weight adjustment and load reconstruction. Next, the first power supply load weight is reconstructed according to the first power supply load fluctuation data, and at the same time, the second power supply load weight is reconstructed according to the second power supply load fluctuation data. The key to this step is to be able to adjust the load weight in a timely and dynamic manner according to the power supply load fluctuation to reflect the fluctuation of the power grid system in actual operation, enhance the system's adaptability to different load states, and thus improve the robustness of the power grid system. Finally, by using the first power supply load reconstruction weight and the second power supply load reconstruction weight, the first power supply load data of multi-grid energy storage and the second power supply load data of multi-grid power generation are reconstructed and analyzed. The key to this step is to conduct fusion analysis by comprehensively considering the contribution and volatility of each node, thereby obtaining more accurate and reliable power supply load data, which provides a more scientific basis for the dispatching and planning of the power grid system, helps to optimize the utilization of power resources, and improve the reliability and economy of the power grid.

[0083] Preferably, step S2 comprises the following steps:

[0084] Step S21: performing time series analysis on the power supply load data of multiple power grids to obtain time series data of the power supply load of multiple power grids;

[0085] The embodiment of the present invention first cleans the collected power supply load data of multiple power grids to deal with missing values, outliers and other problems to ensure the accuracy and completeness of the data. Then, the cleaned data is converted into a time series form by using a time series analysis method, a mapping relationship between time and power supply load demand is established, and the fluctuation characteristics, seasonal changes and other information of the power grid system in the time dimension are revealed, and finally the time series data of the power supply load of multiple power grids are obtained.

[0086] Step S22: performing load power curve analysis on the multi-grid power supply load time series data to obtain the multi-grid power supply load power curve;

[0087] The embodiment of the present invention calculates the time series data of the power supply loads of multiple power grids by using a power calculation method to obtain the power supply load power values ​​corresponding to the time series data, and plots the calculated power supply load power values ​​by using a mathematical statistical method to reflect the power changes of the power supply loads at different times, and reveals the peaks and troughs of the power supply loads, and finally obtains the power supply load power curves of multiple power grids.

[0088] Step S23: performing cluster analysis on the power curves of the power supply loads of multiple power grids using a K-means clustering algorithm to obtain the power classification curves of the power supply loads of multiple power grids; performing key mining analysis on the power classification curves of the power supply loads of multiple power grids to obtain the key power curves of the power supply loads of multiple power grids;

[0089] The embodiment of the present invention first converts the drawn multi-grid power supply load power curve into a format suitable for clustering, and then uses the K-means clustering algorithm to perform cluster analysis on the converted multi-grid power supply load power curve, thereby classifying similar multi-grid power supply load power curves into the same category according to the similarity and difference of power supply load behavior, thereby obtaining a multi-grid power supply load power classification curve. Finally, the divided multi-grid power supply load power classification curve is analyzed by using a key mining algorithm to identify the power curve with key influence, and finally obtain the multi-grid power supply load key curve.

[0090] Step S24: dividing the key power curves of the power supply loads of the multiple power grids into time series according to the preset power time range interval to obtain the time series limited area of ​​the power supply load power curve;

[0091] The embodiment of the present invention segments the key power curves of power supply loads of multiple power grids by using a pre-set power time range interval (for example, a time scale of 1h) to localize the key power curves of the power supply loads in the corresponding time dimension, thereby more accurately locating the timing characteristics in the power grid system and finally obtaining the timing-limited area of ​​the power supply load power curve.

[0092] Step S25: Based on the time-limited area of ​​the power supply load power curve, a time-series peak-shaving operation analysis is performed on the nodes of the multi-grid system using the peak-shaving operation objective function to obtain a multi-grid power supply load peak-shaving operation distribution diagram;

[0093] The embodiment of the present invention forms a suitable peak-shaving operation objective function based on the power supply load power of the corresponding multi-grid system nodes in the time-limited area of ​​the power supply load power curve and combines the index parameters of the multi-grid system nodes and adjacent nodes, the time parameters of the time-series peak-shaving operation analysis, the power supply load power, the peak-shaving target direct power contribution parameter, the peak-shaving target power integral adjustment parameter, the associated weight coefficient and the parameters of the corresponding constraint conditions to perform time-series peak-shaving operation analysis on the multi-grid system nodes, so as to realize the power peak-shaving process of the power supply load power curve, and help the power grid system to allocate power resources more reasonably during the peak period, and finally obtain the multi-grid power supply load peak-shaving operation distribution diagram. In addition, the peak-shaving optimization objective function can also use any time-series peak-shaving algorithm in the field to replace the process of time-series peak-shaving operation analysis, and is not limited to the peak-shaving optimization objective function.

[0094] Among them, the peak load operation objective function is as follows: ;

[0095] In the formula, The first Multiple power grid system nodes at time The peak load operation objective function at is the index parameter of the multi-grid system node, where , The time variable parameters for the time series peaking run analysis, The integral time variable parameter for the timing peak load operation analysis, The first Multiple power grid system nodes at time The power supply load power at Direct power contribution parameters for peak load regulation targets of multiple power grid system nodes, The first Multiple power grid system nodes at time The power supply load power at The peak load target power integral adjustment parameters for multiple power grid system nodes are is the number of adjacent nodes, is the index parameter of the adjacent node, For the The neighboring nodes at time The power supply load power at For the A multi-grid system node and the The association weight coefficient between adjacent nodes is The direct power contribution parameter for the peak load regulation target of the adjacent nodes, For the The neighboring nodes at time The power supply load power at The peak load target power integral adjustment parameter of the adjacent nodes, The constraints of the objective function for peak load operation.

[0096] Among them, the constraints of the peak load operation objective function are Specifically: ;

[0097] ;

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] In the formula, is the index parameter of the multi-grid system node, The time variable parameters for the time series peaking run analysis, is the number of nodes in the multi-grid system, is the index parameter of the adjacent node, The first Multiple power grid system nodes at time The power supply load power at For the The neighboring nodes at time The power supply load power at For multiple power grid system nodes at time The power demand constraint of the power supply load at It is the basic power supply load for multiple power grid system nodes. is the peak power supply load of the multi-grid system node, For multiple power grid system nodes at time The power supply load fluctuation constraint at is the time period measurement parameter, For the The minimum power constraints of multiple power grid system nodes, For the The maximum power constraints of multiple power grid system nodes, For the The power change rate constraints of multiple power grid system nodes, For the A multi-grid system node and the The power difference constraint between adjacent nodes.

[0103] After summarizing and verifying the experience, the present invention obtains the calculation formula of the peak-shaving operation objective function, which is used to perform time-series peak-shaving operation analysis on nodes of multiple power grid systems. The peak-shaving operation objective function comprehensively considers factors such as the node’s own power, the integral of the power, the contribution of the power of adjacent nodes, and related weight coefficients. By adjusting the parameters, the peak-shaving operation target of the node can be quantified in the time-series analysis, which is helpful for optimizing the peak-shaving operation strategy of the multi-grid system. In addition, through the analysis and verification of actual data, as well as the reasonable adjustment of the peak-shaving operation objective function parameters, it is ensured that the objective function can achieve the expected effect in practice. In summary, this formula fully considers the first part of the power supply load power curve within the time-series limited area. Multiple power grid system nodes at time The peak load operation objective function at , index parameters of nodes in multi-grid system ,in, , time variable parameters for timing peak load analysis

[0104] , integral time variable parameters for sequential peak load operation analysis , the power supply load power curve time limit area Multiple power grid system nodes at time Power supply load power , direct power contribution parameters of peak load regulation targets of multi-grid system nodes , the power supply load power curve time limit area Multiple power grid system nodes at time Power supply load power , peak load target power integral adjustment parameters of multiple power grid system nodes , the number of adjacent nodes , the index parameter of the adjacent nodes , No. The neighboring nodes at time Power supply load power , No. A multi-grid system node and the The association weight coefficient between adjacent nodes , the peak load target direct power contribution parameter of the adjacent nodes , No. The neighboring nodes at time Power supply load power , the peak load target power integral adjustment parameter of the adjacent nodes , the constraints of the peak load operation objective function Among them, the constraints of the peak load operation objective function include four aspects: system power balance constraint, node power limit constraint, power change rate limit constraint and node correlation constraint. First, by using the index parameters of the multi-grid system nodes , time variable parameters for timing peak load analysis , the number of nodes in the multi-grid system , the power supply load power curve time limit area Multiple power grid system nodes at time Power supply load power And the nodes of multiple power grid systems at time Power demand constraints of power supply loads at It constitutes a functional relationship of system power balance constraint , and secondly, by using the base load of multiple grid system nodes , time variable parameters for timing peak load analysis , the peak power supply load of multiple power grid system nodes And the nodes of multiple power grid systems at time Power supply load fluctuation constraints It constitutes a power demand constraint for the power supply load Functional relationship In addition, by using the time period measurement parameter , Time variable parameters for time series peak load operation analysis , the sine function and related parameters constitute a power supply load fluctuation constraint Functional relationship , by using the index parameters of the multi-grid system nodes , time variable parameters for timing peak load analysis , the power supply load power curve time limit area Multiple power grid system nodes at time Power supply load power , No. Minimum power constraints for multiple power grid system nodes and Maximum power constraints for multiple power grid nodes It constitutes a functional relationship of node power limit constraint , by using the index parameters of the multi-grid system nodes , time variable parameters for timing peak load analysis , the power supply load power curve time limit area Multiple power grid system nodes at time Power supply load power and Power change rate constraints for multiple power grid system nodes It constitutes a functional relationship of power change rate limit constraint ,Finally, by using the index parameter of the multi-grid system node , time variable parameters for timing peak load analysis , the power supply load power curve time limit area Multiple power grid system nodes at time Power supply load power , the index parameter of the adjacent nodes , No. The neighboring nodes at time Power supply load power and A multi-grid system node and the Power difference constraint between adjacent nodes It constitutes a functional relationship of the association constraints between nodes , according to the power curve of the power supply load, the first Multiple power grid system nodes at time The peak load operation objective function at The correlation between the above parameters forms a functional relationship: ;

[0105] This function formula can realize the analysis process of the timing peak-shaving operation of multiple power grid system nodes. At the same time, by using the constraints of the peak-shaving operation objective function The operation constraints and node power limits of multiple power grid system nodes are precisely constrained, thereby improving the accuracy and applicability of the peak load operation objective function.

[0106] The present invention firstly performs time series analysis on the power supply load data of multiple power grids, and can obtain the time series data of the power supply loads of multiple power grids, thereby revealing the fluctuation characteristics, seasonal changes and other information of the power grid system in the time dimension, which helps to establish a comprehensive understanding of electricity demand and provide a basis for subsequent load power curve analysis. Secondly, by performing load power curve analysis on the time series data of the power supply loads of multiple power grids, it is possible to achieve a deeper mining of the time series data of the power supply loads of multiple power grids, thereby obtaining the power distribution of the power supply loads at different time points, and revealing the peaks and troughs of the power supply loads, providing key clues for subsequent cluster analysis and peak-shaving operation. The key to this step is to provide the system with more specific load characteristics and provide support for refined scheduling and optimization. Then, by using the K-means clustering algorithm to perform cluster analysis on the power curves of the power supply loads of multiple power grids, the potential patterns and trends in the power curves can be discovered, and the power curves can be divided into different categories, thereby identifying the similarities and differences in the behavior of the power supply loads. Further key mining analysis of the power classification curves of the power supply loads of multiple power grids is helpful to identify the key features in the power classification curves of the power supply loads of multiple power grids, and provide a basis for the subsequent time series range segmentation and peak load operation analysis. Next, by using the preset power time range interval to perform time series range segmentation on the key power curves of the power supply loads of multiple power grids, the purpose is to more accurately locate the time series characteristics in the power grid system. The key to this step is to be able to localize the key power curves of the power supply loads in the time dimension, so that the subsequent peak load operation analysis can be more refined and specific. Finally, by using the peak load operation objective function based on the time series limited area of ​​the power supply load power curve to perform time series peak load operation analysis on the nodes of the multi-grid system, the peak load operation analysis can be performed on the nodes of the multi-grid system according to the preset peak load operation objective function, and then the peak load operation distribution diagram of the power supply load can be obtained, which helps to more reasonably allocate power resources during the peak period and improve the dispatching efficiency and operation stability of the power grid system. The combined effect of this series of steps is to establish a comprehensive and time-precise grid system peak-shaving analysis framework to provide more targeted decision support for grid dispatching and planning.

[0107] Preferably, step S3 comprises the following steps:

[0108] Step S31: using an abnormality detection algorithm to perform operation abnormality analysis on the peak load load distribution diagram of the power supply of multiple power grids to obtain abnormal operation data of the power supply load of multiple power grids;

[0109] The embodiment of the present invention analyzes the peak-shaving operation distribution map of multiple power grid power supply loads by using anomaly detection algorithms (including statistical methods, machine learning methods (such as isolation forest, One-Class SVM) and other algorithms) to identify and locate abnormal operation conditions in the power grid system, and accurately detect data points in the peak-shaving operation distribution map of multiple power grid power supply loads that are significantly different from normal operation, and finally obtain abnormal operation data of multiple power grid power supply loads.

[0110] Step S32: converting the abnormal operation data of the power supply loads of the multiple power grids into abnormal signals to obtain abnormal signals of the power supply loads of the multiple power grids;

[0111] The embodiment of the present invention performs signal conversion on the abnormal operation data of the power supply loads of multiple power grids by using a signal conversion algorithm, so as to convert the detected abnormal data into an abnormal signal form that is easier to analyze, and finally obtain the abnormal signal of the power supply loads of multiple power grids.

[0112] Step S33: performing fluctuation range energy analysis on abnormal power supply load signals of multiple power grids to obtain fluctuation energy data of abnormal power supply load signals;

[0113] The embodiment of the present invention performs energy fluctuation detection on abnormal power supply load signals of multiple power grids to detect the amplitude or change range of abnormal power supply load signals of multiple power grids, thereby representing the fluctuation intensity and change trend of abnormal power supply load signals of multiple power grids in different time periods, and finally obtaining power supply load abnormal signal fluctuation energy data.

[0114] Step S34: performing frequency statistical analysis on the abnormal power supply load signals of multiple power grids according to the abnormal power supply load signal fluctuation energy data to obtain abnormal power supply load frequency data of multiple power grids.

[0115] The embodiment of the present invention performs statistical analysis on abnormal power supply load signals of multiple power grids according to the fluctuation intensity and change trend in the abnormal power supply load signal fluctuation energy data, so as to statistically quantify the abnormal frequency of abnormal power supply load signals of multiple power grids, and finally obtain abnormal power supply load frequency data of multiple power grids.

[0116] The present invention firstly analyzes the operation abnormality of the peak load shaving operation distribution diagram of the multi-grid power supply load by using an abnormal detection algorithm, can identify and locate the abnormal operation in the power grid system, and can accurately detect the data points in the peak load shaving operation distribution diagram of the multi-grid power supply load that are significantly different from the normal operation, so as to capture the potential operation abnormality, which provides a basis for the subsequent abnormal signal analysis, and helps to discover the abnormal conditions in the power grid system in advance, so as to respond and process in time. Secondly, by performing abnormal signal conversion on the abnormal operation data of the multi-grid power supply load, the detected abnormal data can be converted into abnormal signals that are easier to analyze. The key of this step is to extract the key features in the abnormal data to establish a characterization model of the abnormal signal, which helps the system to better understand and explain the abnormal phenomenon and provide a more specific data basis for further analysis. Then, by performing fluctuation range energy analysis on the abnormal signal of the multi-grid power supply load, the fluctuation characteristics of the abnormal signal can be deeply excavated. By analyzing the fluctuation range and energy distribution of the abnormal signal, the intensity and change trend of the abnormal signal can be understood, which helps to distinguish the importance of the abnormal signal, provides important clues for the subsequent abnormal frequency statistics, and also guides the subsequent processing and adjustment of the abnormal signal. Finally, by performing frequency statistical analysis on the abnormal power supply load signals of multiple power grids based on the fluctuation energy data of the abnormal power supply load signals, the abnormal frequency of the abnormal power supply load signals of multiple power grids can be quantified according to the fluctuation of the abnormal signals, and the occurrence law of abnormal events can be revealed. By performing statistical analysis on the frequency of abnormal signals, the occurrence frequency of different types of abnormalities can be known, and then the priority and impact of abnormal events in the power grid system can be determined, which provides important information for formulating system response strategies and improving operation strategies.

[0117] Preferably, step S4 comprises the following steps:

[0118] Step S41: performing time series division analysis on the abnormal frequency data of power supply loads of multiple power grids according to a preset frequency time range interval to obtain abnormal frequency interval data of power supply loads;

[0119] The embodiment of the present invention divides the abnormal frequency data of power supply loads of multiple power grids by using a preset frequency time range interval (for example, a time scale of 5 minutes) to divide the abnormal frequency data of power supply loads of multiple power grids into different abnormal frequency intervals, so as to understand the distribution law of abnormal frequencies in different time ranges, and finally obtain the abnormal frequency interval data of power supply loads.

[0120] Step S42: Perform power adjustment analysis on the peak load regulation operation distribution diagram of the power supply load of multiple power grids according to the abnormal frequency interval data of the power supply load, and obtain the abnormal power adjustment capacity value of the power supply load of multiple power grids;

[0121] The embodiment of the present invention uses the power supply load abnormal frequency interval data obtained after the division to collaboratively divide the multi-grid power supply load peak-shaving operation distribution diagram obtained after the peak-shaving processing, thereby obtaining the corresponding abnormal frequency interval area on the multi-grid power supply load peak-shaving operation distribution diagram, and further quantitatively analyzes the impact of the abnormality on power on the basis of the abnormal frequency interval area, so as to analyze and reflect the power adjustment demand of each abnormal frequency interval area, calculate the corresponding adjustment capacity value according to the power adjustment demand obtained by the analysis, and finally obtain the abnormal power adjustment capacity value of the multi-grid power supply load.

[0122] Step S43: Based on the abnormal power adjustment capacity value of the multi-grid power supply load, the multi-grid power supply load peak load operation distribution diagram is subjected to frequency optimization processing using the frequency optimization objective function to obtain the multi-grid power supply load frequency optimization distribution diagram;

[0123] The embodiment of the present invention forms a suitable frequency modulation optimization objective function based on the abnormal power adjustment capacity value of the multi-grid power supply load and in combination with the corresponding time variable parameters of frequency modulation optimization, the multi-grid power supply frequency modulation input power, the multi-grid power supply frequency modulation output power, the weight adjustment parameter, the abnormal power frequency modulation optimization target value, the abnormal power adjustment additional disturbance value, the abnormal power frequency modulation time mean, the abnormal power frequency modulation time standard deviation and the corresponding constraint condition parameters to perform frequency modulation optimization processing on the multi-grid power supply load peak load operation distribution diagram to ensure that the power grid system can still maintain a stable operation state under abnormal frequency conditions, and finally obtain the multi-grid power supply load frequency modulation optimization distribution diagram. In addition, the frequency modulation optimization objective function can also use any time sequence frequency modulation algorithm in the field to replace the frequency modulation optimization process, and is not limited to the frequency modulation optimization objective function.

[0124] Among them, the frequency modulation optimization objective function is as follows: ;

[0125] ;

[0126] In the formula, is the frequency modulation optimization objective function, Time range metric parameters optimized for frequency modulation, Time-variant parameters optimized for frequency modulation, Integration time variable parameters optimized for frequency modulation, For in time The frequency modulation input power of multiple power grids at The weight adjustment parameters for the frequency modulation input power of multiple power grids are For in time The frequency modulation output power of multiple power grids at The weight adjustment parameters for the frequency modulation output power of multiple power grids are is the weight adjustment parameter of the frequency modulation output power change rate, The weight adjustment parameters for the abnormal power frequency modulation optimization target, For in time The abnormal power frequency modulation optimization target value at For in time The abnormal power adjustment capacity value of the multi-grid power supply load at the For in time The abnormal power at adjusts the additional disturbance value, is the mean value of abnormal power frequency modulation time, is the standard deviation of abnormal power frequency modulation time, The constraints of the objective function for frequency modulation optimization;

[0127] Among them, the constraints of the frequency modulation optimization objective function are Specifically: ;

[0128] ;

[0129] ;

[0130] ;

[0131] ;

[0132] In the formula, Time-variant parameters optimized for frequency modulation, Integration time variable parameters optimized for frequency modulation, For in time The frequency modulation input power of multiple power grids at For in time The frequency modulation output power of multiple power grids at For in time The abnormal power frequency modulation optimization target value at For in time The internal mechanical loss constraints of multiple power grids at Minimum loss constraints for mechanical losses within multiple power grids, The maximum loss constraint for the internal mechanical losses of the multi-grid power supply, For in time The transmission loss constraints of multiple power grids at The minimum loss constraint for multi-grid power transmission loss, The maximum loss constraint for multi-grid power transmission losses, Minimum output power constraints for multi-grid power supply frequency regulation, Maximum output power constraints for multi-grid power supply frequency regulation, is the minimum load constraint for the abnormal power frequency regulation optimization objective, Maximum load constraint for abnormal power frequency regulation optimization objective.

[0133] The present invention obtains a calculation formula for the frequency modulation optimization objective function through experience summary and verification, which is used to perform frequency modulation optimization processing on the peak-shaving operation distribution diagram of multiple power grid power supply loads. The frequency modulation optimization objective function comprehensively considers factors such as the frequency modulation input power, the frequency modulation output power, and the rate of power change during the frequency modulation process, and adjusts relevant parameters to quantitatively evaluate the frequency modulation optimization target. The form of the objective function can be flexibly adjusted according to specific frequency modulation optimization goals and requirements. In practical applications, it is usually necessary to combine specific power grid system characteristics and scheduling goals, analyze and verify actual data, and reasonably adjust parameters to ensure that the obtained optimization objective function can produce a beneficial effect on the peak-shaving operation of multiple power grid power supply loads. Therefore, this formula fully considers the frequency modulation optimization objective function. , the time range metric parameter for frequency modulation optimization , the time variable parameters of frequency modulation optimization , integral time variable parameter for frequency modulation optimization , at time Multi-grid power supply frequency modulation input power , weight adjustment parameters of input power of frequency modulation of multi-grid power supply , at time Frequency modulation output power of multiple power grids , weight adjustment parameters of frequency modulation output power of multiple power grids , the weight adjustment parameter of the frequency modulation output power change rate , the weight adjustment parameter of abnormal power frequency modulation optimization objective , at time Abnormal power frequency modulation optimization target value at , at time Abnormal power adjustment capacity value of multiple power grid power supply loads at , at time The abnormal power at the position adjusts the additional disturbance value , Abnormal power frequency modulation time average , abnormal power frequency modulation time standard deviation , the constraints of the objective function of frequency modulation optimization , where the integral time variable parameter is optimized by using frequency modulation , at time Abnormal power adjustment capacity value of multiple power grid power supply loads at and in time The abnormal power at the position adjusts the additional disturbance value constitutes a kind of Abnormal power frequency modulation optimization target value at Functional relationship The constraints of the frequency modulation optimization objective function in this formula include three aspects: mechanical power balance constraint, output power range constraint and load abnormal frequency modulation range constraint. First, by using the time variable parameter of frequency modulation optimization , at time Frequency modulation input power of multiple power grids , at time Frequency modulation output power of multiple power grids , at time Internal mechanical loss constraints of multiple power grids and in time Transmission loss constraints of multiple power grids at It constitutes a functional relationship of mechanical power balance constraint , where the time-variable parameter optimized by frequency modulation is , Minimum loss constraints for internal mechanical losses of multi-grid power supply and the maximum loss constraint of the internal mechanical losses of the multi-grid power supply constitutes a kind of Internal mechanical loss constraints of multiple power grids Functional relationship , but also by using the time-variable parameters of frequency modulation optimization , the minimum loss constraint of multi-grid power transmission loss and the maximum loss constraint of multi-grid power transmission losses constitutes a kind of Transmission loss constraints of multiple power grids at Functional relationship , and secondly, by using the time-variable parameters of frequency modulation optimization , at time Frequency modulation output power of multiple power grids , Minimum output power constraints for multi-grid power supply frequency regulation And the maximum output power constraints of multi-grid power supply frequency regulation It constitutes a functional relationship of output power range constraint , and finally, by using the frequency-modulated optimized integral time variable parameter , at time Abnormal power frequency modulation optimization target value at , the minimum load constraint of abnormal power frequency regulation optimization objective and the maximum load constraint of the abnormal power frequency regulation optimization objective It constitutes a functional relationship of load abnormal frequency regulation range constraint , according to the frequency modulation optimization objective function The correlation between the above parameters forms a functional relationship: ;

[0134] This function formula can realize the frequency optimization processing process of the peak load operation distribution diagram of multiple power grids. At the same time, by using the constraints of the frequency optimization objective function Precise constraints are imposed on various peak-shaving operation restrictions of the power grid system, thereby improving the accuracy and applicability of the frequency regulation operation objective function.

[0135] Step S44: Optimizing configuration analysis is performed on the multi-grid power supply load frequency regulation optimization distribution diagram to obtain multi-grid power supply load peak regulation optimization configuration data.

[0136] The embodiment of the present invention conducts a detailed analysis of the frequency regulation optimization distribution diagram of the power supply loads of multiple power grids after abnormal frequency modulation processing, and determines the best optimization configuration scheme, including adjusting the output of the power grid system generator, using energy storage equipment, etc., so that the best performance of the power supply load peak regulation of the multiple power grid system can be achieved under abnormal conditions, and finally the peak regulation optimization configuration data of the power supply loads of the multiple power grids is obtained.

[0137] The present invention firstly performs time series division analysis on the abnormal frequency data of the power supply load of multiple power grids by using a preset frequency time range interval, and can understand the distribution law of abnormal frequency in different time ranges in detail, which is helpful to deeply analyze the regularity of abnormal occurrence in the time dimension, and provide a more refined time period reference for subsequent peak load optimization. By obtaining the abnormal frequency interval data of the power supply load, it is possible to more accurately capture and quantify abnormal events, providing a basis for further adjustment and optimization. Secondly, by performing power adjustment analysis on the peak load operation distribution diagram of the power supply load of multiple power grids according to the abnormal frequency interval data of the power supply load, the impact of the abnormality on power can be further quantitatively analyzed on the basis of the abnormal frequency. Through this step, the abnormal power adjustment capacity value of the power supply load of multiple power grids can be obtained, which is a key indicator for determining the power demand of the power grid system for abnormal events. The acquisition of this value helps the system plan the capacity of peak load measures and improves the flexibility of the system to deal with abnormal loads. Then, by using the frequency optimization objective function based on the abnormal power adjustment capacity value of the power supply load of multiple power grids obtained by analysis, the peak load operation distribution diagram of the power supply load of multiple power grids is optimized by frequency modulation, and intelligent adjustment can be performed according to specific power adjustment requirements. The core of this step is to achieve the reasonable allocation of abnormal power through the frequency modulation optimization objective function to ensure that the power grid system can still maintain a stable operating state under abnormal conditions, thereby obtaining the multi-grid power supply load frequency modulation optimization distribution map, which can provide the power grid system with an intuitive image of the frequency modulation optimization solution, and help engineers and operators better understand the peak-shaving operation status of the power grid system. Finally, by optimizing the configuration analysis of the multi-grid power supply load frequency modulation optimization distribution map, the frequency modulation optimization results can be deeply studied to find the optimal configuration solution. By analyzing the multi-grid power supply load frequency modulation optimization distribution map, the optimal configuration parameters can be determined to achieve the best performance of the power grid system peak-shaving under abnormal conditions, thereby providing specific configuration suggestions for the power grid system, which helps to optimize the system operation efficiency and improve the peak-shaving performance.

[0138] Preferably, the present invention further provides an optimization configuration system based on big data multi-grid peak regulation, which is used to execute the optimization configuration method based on big data multi-grid peak regulation as described above, and the optimization configuration system based on big data multi-grid peak regulation comprises:

[0139] The power supply load analysis module of the power grid system is used to perform grid node labeling analysis on the power grid system to obtain multiple power grid system nodes; perform big data analysis on multiple power grid system nodes to obtain multiple power grid energy production status data and multiple power grid power transmission line status data; perform power supply load analysis on the power grid system based on the multiple power grid energy production status data and the multiple power grid power transmission line status data, thereby obtaining multiple power grid power supply load data;

[0140] The power grid load peak load analysis module is used to analyze the timing peak load operation of the power grid system according to the power grid load data of multiple power grids, so as to obtain the peak load operation distribution diagram of multiple power grids;

[0141] The peak load operation abnormality analysis module is used to perform operation abnormality analysis on the peak load operation distribution diagram of multiple power grids to obtain the operation abnormality data of multiple power grids; perform frequency conversion analysis on the operation abnormality data of multiple power grids to obtain the abnormal frequency data of multiple power grids;

[0142] The power supply load abnormal frequency regulation optimization module is used to perform frequency regulation optimization configuration analysis on the peak-shaving operation distribution diagram of the power supply load of multiple power grids according to the abnormal frequency data of the power supply load of multiple power grids, so as to obtain the peak-shaving optimization configuration data of the power supply load of multiple power grids.

[0143] In summary, the present invention provides an optimization configuration system based on big data multi-grid peak regulation, which is composed of a power grid system power supply load analysis module, a power grid power supply load peak regulation analysis module, a peak regulation operation abnormality analysis module, and a power supply load abnormal frequency modulation optimization module. It can realize any one of the optimization configuration methods based on big data multi-grid peak regulation described in the present invention, and is used to combine the operations between computer programs running on each module to realize an optimization configuration method based on big data multi-grid peak regulation. The internal structures of the system cooperate with each other, and the power supply load data of the power grid system is accurately obtained by combining the energy production status and power transmission status of the multi-grid system, and peak regulation analysis is performed based on the power supply load data to reduce the volatility of the overall power grid power supply load. At the same time, the abnormal operation during the peak regulation process is analyzed to perform abnormal frequency modulation optimization, so as to determine the optimal configuration parameters to achieve the best performance of power grid system peak regulation under abnormal conditions. This can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient multi-grid peak regulation optimization configuration process, thereby simplifying the operation process of the optimization configuration system based on big data multi-grid peak regulation.

[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An optimization configuration method for multi-grid peak load regulation based on big data, characterized in that: The following steps are involved: Step S1: perform grid node labeling analysis on the grid system to obtain multiple grid system nodes; Conduct big data analysis on multi-grid system nodes to obtain multi-grid energy production status data and multi-grid power transmission line status data; Analyze the power supply load of the power grid system according to the energy production status data of multiple power grids and the power transmission line status data of multiple power grids to obtain the power supply load data of multiple power grids; Step S2: performing a time sequence peak load regulation operation analysis on the nodes of the multi-grid system according to the multi-grid power supply load data to obtain a multi-grid power supply load peak load regulation operation distribution diagram; Step S3: performing operation abnormality analysis on the peak load regulation operation distribution diagram of the power supply loads of multiple power grids to obtain operation abnormality data of the power supply loads of multiple power grids; Perform frequency conversion analysis on the abnormal operation data of the power supply loads of multiple power grids to obtain abnormal frequency data of the power supply loads of multiple power grids; wherein step S3 includes the following steps: Step S31: using an abnormality detection algorithm to perform operation abnormality analysis on the peak load load distribution diagram of the power supply of multiple power grids to obtain abnormal operation data of the power supply load of multiple power grids; Step S32: converting the abnormal operation data of the power supply loads of the multiple power grids into abnormal signals to obtain abnormal signals of the power supply loads of the multiple power grids; Step S33: performing fluctuation range energy analysis on abnormal power supply load signals of multiple power grids to obtain fluctuation energy data of abnormal power supply load signals; Step S34: performing frequency statistical analysis on the abnormal power supply load signals of multiple power grids according to the power supply load abnormal signal fluctuation energy data to obtain the abnormal power supply load frequency data of multiple power grids; Step S4: Based on the abnormal frequency data of the power supply loads of the multiple power grids, a frequency regulation optimization configuration analysis is performed on the peak-shaving operation distribution diagram of the power supply loads of the multiple power grids to obtain the peak-shaving optimization configuration data of the power supply loads of the multiple power grids.

2. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Analyze the topology of the power grid system to obtain a topology distribution diagram of multiple power grid systems; Step S12: performing grid node labeling analysis on the multi-grid system topology structure distribution diagram to obtain multi-grid system nodes; Step S13: performing energy production analysis on multiple power grid system nodes to obtain energy production status data of multiple power grids; Step S14: extracting power transmission lines from multiple power grid system nodes to obtain node power transmission line data; Step S15: performing power transmission detection on the nodes of the multi-grid system according to the node power transmission line data to obtain the multi-grid power transmission line status data; Step S16: Analyze the power supply load of the power grid system according to the energy production status data of the multiple power grids and the power transmission line status data of the multiple power grids to obtain the power supply load data of the multiple power grids.

3. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 2 is characterized in that: Step S16 includes the following steps: Step S161: performing energy savings forecasting and analysis on the power grid system according to the energy production status data of multiple power grids to obtain energy savings status data of multiple power grids; Step S162: performing power generation capacity prediction and analysis on the power grid system according to the power transmission line status data of multiple power grids to obtain power generation capacity data of multiple power grids; Step S163: Perform power supply load analysis on the energy storage status data of multiple power grids and the power generation capacity data of multiple power grids to obtain power supply load data of multiple power grids.

4. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 3 is characterized in that: Step S163 includes the following steps: Step S1631: performing energy storage power supply load analysis on the energy storage status data of multiple power grids, obtaining the first power supply load data of the energy storage of multiple power grids, and assigning a weight to the first power supply load; Step S1632: performing power generation load analysis on the first power supply load data of the multi-grid energy storage according to the power generation capacity data of the multi-grid, obtaining the second power supply load data of the multi-grid power generation, and assigning a weight to the second power supply load; Step S1633: performing power supply load fluctuation analysis on the first power supply load data of the multi-grid energy storage and the second power supply load data of the multi-grid power generation to obtain the first power supply load fluctuation data of the multi-grid and the second power supply load fluctuation data of the multi-grid; Step S1634: reconstructing the first power supply load weight according to the first power supply load fluctuation data of the multi-grids to obtain the first power supply load reconstruction weight; reconstructing the second power supply load weight according to the second power supply load fluctuation data of the multi-grids to obtain the second power supply load reconstruction weight; Step S1635: reconstruct and fuse the multi-grid energy storage first power supply load data and the multi-grid power generation second power supply load data according to the first power supply load reconstruction weight and the second power supply load reconstruction weight to obtain the multi-grid power supply load data.

5. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing time series analysis on the power supply load data of multiple power grids to obtain time series data of the power supply load of multiple power grids; Step S22: performing load power curve analysis on the multi-grid power supply load time series data to obtain the multi-grid power supply load power curve; Step S23: performing cluster analysis on the power curves of the power supply loads of multiple power grids using a K-means clustering algorithm to obtain the power classification curves of the power supply loads of multiple power grids; performing key mining analysis on the power classification curves of the power supply loads of multiple power grids to obtain the key power curves of the power supply loads of multiple power grids; Step S24: dividing the key power curves of the power supply loads of the multiple power grids into time series according to the preset power time range interval to obtain the time series limited area of ​​the power supply load power curve; Step S25: Based on the time-limited area of ​​the power supply load power curve, a time-series peak-shaving operation analysis is performed on the nodes of the multi-grid system using the peak-shaving operation objective function to obtain a multi-grid power supply load peak-shaving operation distribution diagram; Among them, the peak load operation objective function is as follows: ； In the formula, The first Multiple power grid system nodes at time The peak load operation objective function at is the index parameter of the multi-grid system node, where , The time variable parameters for the time series peaking run analysis, The integral time variable parameter for the timing peak load operation analysis, The first Multiple power grid system nodes at time The power supply load power at Direct power contribution parameters for peak load regulation targets of multiple power grid system nodes, The first Multiple power grid system nodes at time The power supply load power at The peak load target power integral adjustment parameters for multiple power grid system nodes are is the number of adjacent nodes, is the index parameter of the adjacent node, For the The neighboring nodes at time The power supply load power at For the A multi-grid system node and the The association weight coefficient between adjacent nodes is The direct power contribution parameter for the peak load target of the adjacent nodes, For the The neighboring nodes at time The power supply load power at The peak load target power integral adjustment parameter of the adjacent nodes, The constraints of the objective function for peak load operation.

6. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 5 is characterized in that: Constraints of the peak load operation objective function in step S25 Specifically: ； ； ； ； ； ； In the formula, is the index parameter of the multi-grid system node, The time variable parameters for the time series peaking run analysis, is the number of nodes in the multi-grid system, is the index parameter of the adjacent node, The first Multiple power grid system nodes at time The power supply load power at For the The neighboring nodes at time The power supply load power at For multiple power grid system nodes at time The power demand constraint of the power supply load at It is the basic power supply load for multiple power grid system nodes. is the peak power supply load of the multi-grid system node, For multiple power grid system nodes at time The power supply load fluctuation constraint at is the time period measurement parameter, For the The minimum power constraints of multiple power grid system nodes, For the The maximum power constraints of multiple power grid system nodes, For the The power change rate constraints of multiple power grid system nodes, For the A multi-grid system node and the The power difference constraint between adjacent nodes.

7. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing time series division analysis on the abnormal frequency data of power supply loads of multiple power grids according to a preset frequency time range interval to obtain abnormal frequency interval data of power supply loads; Step S42: Perform power adjustment analysis on the peak load regulation operation distribution diagram of the power supply load of multiple power grids according to the abnormal frequency interval data of the power supply load, and obtain the abnormal power adjustment capacity value of the power supply load of multiple power grids; Step S43: Based on the abnormal power adjustment capacity value of the multi-grid power supply load, the multi-grid power supply load peak load operation distribution diagram is subjected to frequency optimization processing using the frequency optimization objective function to obtain the multi-grid power supply load frequency optimization distribution diagram; Among them, the frequency modulation optimization objective function is as follows: ； ； In the formula, is the frequency modulation optimization objective function, Time range metric parameters optimized for frequency modulation, Time-variant parameters optimized for frequency modulation, Integration time variable parameters optimized for frequency modulation, For in time The frequency modulation input power of multiple power grids at The weight adjustment parameters for the frequency modulation input power of multiple power grids are For in time The frequency modulation output power of multiple power grids at The weight adjustment parameters for the frequency modulation output power of multiple power grids are is the weight adjustment parameter of the frequency modulation output power change rate, The weight adjustment parameters for the abnormal power frequency modulation optimization target, For in time The abnormal power frequency modulation optimization target value at For in time The abnormal power adjustment capacity value of the multi-grid power supply load at the For in time The abnormal power at adjusts the additional disturbance value, is the mean value of abnormal power frequency modulation time, is the standard deviation of abnormal power frequency modulation time, The constraints of the objective function for frequency modulation optimization; Step S44: Optimizing configuration analysis is performed on the multi-grid power supply load frequency regulation optimization distribution diagram to obtain multi-grid power supply load peak regulation optimization configuration data.

8. The optimization configuration method for multi-grid peak load regulation based on big data according to claim 7 is characterized in that: Constraints of the frequency modulation optimization objective function in step S43 Specifically: ； ； ； ； ； In the formula, Time-variant parameters optimized for frequency modulation, Integration time variable parameters optimized for frequency modulation, For in time The frequency modulation input power of multiple power grids at For in time The frequency modulation output power of multiple power grids at For in time The abnormal power frequency modulation optimization target value at For in time The internal mechanical loss constraints of multiple power grids at Minimum loss constraints for internal mechanical losses in multi-grid power supply, The maximum loss constraint for the internal mechanical losses of the multi-grid power supply, For in time The transmission loss constraints of multiple power grids at The minimum loss constraint for multi-grid power transmission loss, The maximum loss constraint for multi-grid power transmission losses, Minimum output power constraints for multi-grid power supply frequency regulation, Maximum output power constraints for multi-grid power supply frequency regulation, is the minimum load constraint for the abnormal power frequency regulation optimization objective, Maximum load constraint for abnormal power frequency regulation optimization objective.

9. An optimization configuration system for multi-grid peak load regulation based on big data, characterized in that: For executing the optimization configuration method based on big data multi-grid peak regulation according to claim 1, the optimization configuration system based on big data multi-grid peak regulation comprises: The power supply load analysis module of the power grid system is used to perform grid node labeling analysis on the power grid system to obtain multiple power grid system nodes; perform big data analysis on multiple power grid system nodes to obtain multiple power grid energy production status data and multiple power grid power transmission line status data; perform power supply load analysis on the power grid system based on the multiple power grid energy production status data and the multiple power grid power transmission line status data, thereby obtaining multiple power grid power supply load data; The power grid load peak load analysis module is used to analyze the timing peak load operation of the power grid system according to the power grid load data of multiple power grids, so as to obtain the peak load operation distribution diagram of multiple power grids; The peak load operation abnormality analysis module is used to perform operation abnormality analysis on the peak load operation distribution diagram of multiple power grids using an abnormality detection algorithm to obtain operation abnormality data of multiple power grids; perform abnormal signal conversion on the operation abnormality data of multiple power grids to obtain abnormal signals of multiple power grids; perform fluctuation range energy analysis on the abnormal signals of multiple power grids to obtain fluctuation energy data of abnormal signals of power grids; perform frequency statistical analysis on the abnormal signals of multiple power grids according to the fluctuation energy data of abnormal signals of power grids to obtain abnormal frequency data of multiple power grids; The power supply load abnormal frequency regulation optimization module is used to perform frequency regulation optimization configuration analysis on the peak-shaving operation distribution diagram of the power supply load of multiple power grids according to the abnormal frequency data of the power supply load of multiple power grids, so as to obtain the peak-shaving optimization configuration data of the power supply load of multiple power grids.

Images