Power regulation and control method and system based on power characteristic matrix

Abstract

The invention relates to the technical field of electric power regulation and control, in particular to an electric power regulation and control method and system based on a power characteristic matrix. The method comprises the following steps: obtaining distributed power plant equipment data, carrying out abnormal value replacement, generating complete equipment data, screening out standard operation parameters, carrying out equipment unit simulation processing, generating a simulation power plant equipment unit, and carrying out combined power generation simulation to obtain various simulation data; historical power output data are obtained, power demand analysis is carried out, power output data and power demand peak and valley data required by prediction are generated, based on the data, intensity adaptation screening is carried out on combined power generation simulation, an operation period is adjusted, and finally a distributed equipment scheduling instruction is generated, so that efficient regulation and control of the intelligent virtual power plant are realized. According to the invention, a more efficient and more reliable intelligent power regulation and control method is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power regulation and control, and in particular to an electric power regulation and control method and system based on a power characteristic matrix. Background Art

[0002] Power regulation is to improve energy efficiency by integrating decentralized power generation resources and loads, and provide flexible scheduling capabilities for the power market. However, virtual power plants currently still face many challenges in the regulation process. Real-time acquisition and processing of equipment data, accurate demand forecasting, and effective scheduling strategies have not been fully resolved, which seriously affects the operating efficiency and reliability of virtual power plants. Obtaining high-quality distributed power plant equipment data is the basis for realizing intelligent regulation. Existing systems often face problems of data anomalies and missing data, which makes it difficult to generate complete equipment data, which in turn affects the screening and application of standard operating parameters. In addition, the collaborative operation effect between devices has not been fully explored, resulting in insufficient data accuracy in combined power generation simulation, which cannot provide effective support for power demand. Summary of the invention

[0003] Based on this, it is necessary to provide a power control method and system based on a power characteristic matrix to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a power control method based on power characteristic evidence includes the following steps:

[0005] Step S1: Obtain distributed power plant equipment data; replace abnormal values ​​in the distributed power plant equipment data to obtain complete equipment data; perform standard operation parameter screening on the complete equipment data to generate standard equipment operation parameters;

[0006] Step S2: Perform equipment unit simulation processing on the standard equipment operating parameters to generate simulated power plant equipment units; perform combined power generation simulation on the simulated power plant equipment units to obtain multiple combined power generation simulation data;

[0007] Step S3: Acquire historical power output data; perform power demand analysis on the historical power output data to obtain historical power demand data; perform power generation demand forecasting on the standard equipment operating parameters based on the historical power demand data to generate predicted power output data; perform demand peak and valley analysis on the predicted power output data to obtain power demand peak and valley data;

[0008] Step S4: Based on the predicted required power output data, multiple combined power generation simulation data are strength-adaptively screened to obtain a power generation strength adaptation combination unit; based on the power demand peak and valley data, the power generation strength adaptation combination unit is operated periodically adjusted to generate adaptation equipment combination scheduling data;

[0009] Step S5: Generate a distributed device dispatching instruction according to the adaptive device combination dispatching data; use the distributed device dispatching instruction to dispatch the equipment operation of the virtual power plant to realize the intelligent power control method.

[0010] The present invention ensures the comprehensiveness and accuracy of the data basis by acquiring the data of distributed power plant equipment. The processing of replacing outliers on these data can effectively eliminate inaccurate data caused by data acquisition errors or equipment failures, thereby improving the reliability of the overall data. Then, the standard operating parameters are screened for the complete equipment data to ensure that the data used meets the normal operating requirements of the equipment, which is crucial for subsequent analysis and simulation. This standardized processing of data not only improves the availability and consistency of the data, but also lays a solid foundation for subsequent simulation analysis, ensures the effectiveness and accuracy of subsequent steps, and performs equipment unit simulation processing on the standard equipment operating parameters to generate a variety of simulated power plant equipment units. This process enables a variety of equipment combinations to be simulated under different operating conditions, providing a more comprehensive operating perspective. This simulation can not only help identify the synergy between different equipment, but also generate a variety of combined power generation simulation data through combined power generation simulation, providing a rich basis for the dispatching decision of the power plant. Through these simulation data, the operating efficiency of the power plant can be deeply analyzed, the configuration scheme of the equipment can be optimized, thereby improving the flexibility and efficiency of the overall power production, and by acquiring historical power output data and performing power demand analysis, an important foundation is established for the change of power demand. This stage not only involves in-depth analysis of historical data, but also requires extracting the laws and trends of power demand from it in order to make more accurate power output forecasts. Based on these historical data, the power generation demand forecast significantly improves the accuracy of the forecast, which helps the power plant to be fully prepared to cope with future power demand fluctuations. Further demand peak and valley analysis can help identify the peak and valley periods of power demand, which provides an important basis for the subsequent optimization of scheduling strategies, ensuring the stability and reliability of power supply. Based on the analysis of the power output data required for the forecast, the intensity adaptation screening of multiple combined power generation simulation data is carried out to ensure efficient power generation of different equipment combinations under various demand conditions. The implementation of this process can not only improve the adaptability of the equipment combination, but also ensure that the dispatching strategy of the power plant can respond flexibly when facing different power demands. Next, the operation cycle of the power generation intensity adaptation combination unit is adjusted based on the power demand peak and valley data to further optimize the dispatching efficiency of the equipment combination. By reasonably arranging the operation cycle of the equipment, sufficient power output can be provided during the peak period of power demand, and unnecessary energy loss can be reduced during the trough period of demand, thereby achieving efficient utilization of resources. The generated distributed equipment dispatch instructions realize the intelligent management of the virtual power plant. These instructions can dynamically dispatch equipment operations based on real-time data and forecast results, improving the responsiveness and control capabilities of power plants. This process not only promotes coordination between distributed power plants and the power grid, but also enhances the stability and reliability of the entire power system.Driven by intelligent control methods, distributed power plants can more efficiently utilize renewable energy and promote the development and application of green energy. At the same time, by improving the flexibility of power supply, it can better meet the diverse power needs of users, thereby enhancing user satisfaction and optimizing the overall power service quality.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: Obtain distributed power plant equipment data; perform abnormal value interval detection on the distributed power plant equipment data to obtain abnormal value intervals of power plant equipment;

[0013] Step S12: removing abnormal values ​​from the abnormal value interval of the power plant equipment to generate cleaning power plant equipment data;

[0014] Step S13: performing linear interpolation of abnormal intervals on the cleaning power plant equipment data to obtain complete equipment data;

[0015] Step S14: performing equipment operation simulation on the complete equipment data to obtain a simulation operation parameter set;

[0016] Step S15: clustering the simulation operation parameter set to obtain a clustered operation parameter set;

[0017] Step S16: Standardize the clustered operating parameter set to generate standard equipment operating parameters.

[0018] The present invention ensures the comprehensiveness and accuracy of the data source by acquiring the distributed power plant equipment data. By detecting the abnormal value interval of the distributed power plant equipment data, the abnormal range in the data can be effectively identified, thereby laying the foundation for subsequent data cleaning and processing. The generation of abnormal value intervals for power plant equipment can help identify potential problems, improve the pertinence and effectiveness of data processing, ensure that the data based on which the subsequent analysis is based is reliable, and enhance the basic data quality of the entire system. The step of performing abnormal elimination on the abnormal value interval of power plant equipment realizes further cleaning of the data. By eliminating data that does not conform to the normal operating range, clean power plant equipment data is generated, and the integrity and accuracy of the data are ensured. This operation significantly improves the quality of the data, provides a more reliable data basis for subsequent analysis and simulation, reduces the analysis deviation caused by abnormal values, and ensures the effectiveness and accuracy of subsequent steps. Scientificity: The implementation of linear interpolation of abnormal intervals on the cleaning power plant equipment data can fill the gaps caused by the removal of abnormal values ​​in the data cleaning process and obtain complete equipment data. The linear interpolation method not only retains the original trend of the data, but also improves the continuity and integrity of the data, providing high-quality data support for subsequent equipment operation simulations, enhancing the applicability of the data and the accuracy of the analysis, and ensuring the reliability of the simulation results. The steps of equipment operation simulation for complete equipment data, through the generation of simulated operation parameter sets, can deeply analyze the performance of the equipment under different operating conditions, provide targeted data support, and improve the operating efficiency and flexibility of the power plant. This simulation not only helps identify potential problems in equipment operation, but also provides a basis for optimizing equipment operation strategies, enhancing the system's adaptability in the face of changes, and ensuring the best power generation effect under different circumstances. The operation of clustering the operation parameters of the simulated operation parameter set can identify the different modes in the operation of the equipment through cluster analysis, and classify similar operation parameters into one category to obtain the clustered operation parameter set. This step helps to simplify data analysis, reveal the inherent laws of equipment operation, and improve the depth and breadth of analysis. It lays the foundation for subsequent standardization processing and ensures that the equipment performance can be effectively identified and managed under various operating conditions. The step of standardizing the clustered operation parameter set generates standard equipment operation parameters to ensure that the parameters between different equipment are comparable. Standardization can eliminate the analysis deviation caused by different dimensions and improve the accuracy and reliability of data analysis. This result provides a scientific basis for subsequent scheduling and decision-making, enhances the overall operation efficiency of the system, promotes the realization of intelligent control, and ensures that the power plant can maintain an efficient and stable operation state under various operating conditions.

[0019] Preferably, step S2 comprises the following steps:

[0020] Step S21: extracting features of standard equipment operating parameters to obtain equipment characteristic parameters; performing correlation analysis on the equipment characteristic parameters to generate a parameter correlation matrix;

[0021] Step S22: performing equipment unit operating condition analysis on the equipment characteristic parameters based on the parameter association matrix to obtain an operating condition parameter set; performing operation trajectory calculation on the operating condition parameter set to obtain equipment operation trajectory data;

[0022] Step S23: performing equipment simulation processing on equipment characteristic parameters according to equipment operation trajectory data to generate a simulated power plant equipment unit;

[0023] Step S24: simulating the power generation operation of the simulated power plant equipment unit to obtain simulated equipment working data;

[0024] Step S25: Based on the simulated equipment working data, feasible combined power generation simulation is performed on the simulated power plant equipment units to obtain multiple combined power generation simulation data.

[0025] The present invention can effectively identify the key parameter characteristics of the equipment by extracting the characteristics of the standard equipment operating parameters, thereby laying the foundation for subsequent analysis. By performing correlation analysis on the equipment characteristic parameters and generating a parameter correlation matrix, the intrinsic relationship between different parameters can be revealed, providing an important reference for subsequent working condition analysis, enhancing the depth and breadth of data analysis, ensuring that the operating characteristics of the equipment can be accurately identified in a complex operating environment, and improving the system's understanding and management capabilities of the equipment status. Based on the parameter correlation matrix, the equipment unit working condition analysis of the equipment characteristic parameters can be performed to deeply understand the performance of the equipment under different working conditions, obtain the working condition parameter set, and generate equipment operating trajectory data by calculating the operating trajectory of the working condition parameter set. This process provides detailed dynamic data support for subsequent equipment simulation, ensuring that the actual operating status of the equipment can be accurately reflected during the simulation process, improving the authenticity and reliability of the simulation, and providing a scientific basis for optimizing the equipment operation strategy. The equipment characteristic parameters are simulated according to the equipment operation trajectory data to generate simulated power plant equipment units, which can simulate the actual operation of the equipment in a virtual environment. Through this simulation, the performance of the equipment under different operating conditions can be evaluated, potential operating problems can be identified, and the understanding of equipment performance can be enhanced. It provides data support for the optimized operation of the power plant, ensures that various challenges can be better coped with in actual operation, and improves the overall flexibility and adaptability of the system. The operation of simulating the power generation operation of the simulated power plant equipment unit can generate simulated equipment working data. Through this simulation, the power generation performance of the equipment under specific working conditions can be evaluated, and detailed data support is provided to help identify the efficiency and stability of the equipment under different conditions, ensuring that reasonable scheduling and management can be carried out based on the real simulation results during the decision-making process, and improving the overall operating efficiency and power generation capacity of the power plant. Based on the simulated equipment working data, feasible combined power generation simulation is carried out on the simulated power plant equipment units to generate a variety of combined power generation simulation data. This process can provide power plants with diversified power generation solutions by exploring the power generation potential of different equipment combinations, optimize resource allocation, and improve power generation efficiency. It ensures that when facing different power demands, power plants can flexibly adjust their operating strategies, enhance the system's resilience and economic benefits, and ultimately achieve more efficient power production and supply.

[0026] Preferably, step S25 comprises the following steps:

[0027] Step S251: classify the simulated device working data into types to obtain a device classification data set; perform power characteristic analysis on the device classification data set to obtain a power characteristic matrix;

[0028] Step S252: performing independent operation simulation on the simulated power plant equipment units according to the power characteristic matrix to generate equipment independent operation data; performing permutation, combination and grouping on the simulated power plant equipment units to generate multiple groups of permutation equipment units;

[0029] Step S253: performing combined operation simulation on the arranged equipment units according to the power characteristic matrix to generate multiple sets of equipment combined operation data; performing optimized combination screening on the equipment combined operation data based on the equipment independent operation data to obtain feasible equipment combined operation data;

[0030] Step S254: Based on the feasible equipment combination working data, a combined power generation simulation is performed on the simulated power plant equipment units to obtain a variety of combined power generation simulation data.

[0031] The present invention can effectively classify the equipment according to different characteristics by dividing the working data of the simulated equipment into types, and obtain the equipment classification data set. By performing power characteristic analysis on the equipment classification data set and generating a power characteristic matrix, it is possible to deeply understand the power output characteristics of various types of equipment under different working conditions, and provide a scientific basis for subsequent simulation and combination, ensuring that reasonable scheduling can be performed according to the actual power characteristics during resource allocation, and improving the system's performance in power generation efficiency and resource utilization. According to the power characteristic matrix, the simulated power plant equipment unit is simulated to work independently, and the equipment independent working data is generated, which can evaluate the performance of each device without being affected by other equipment, and provide detailed data support, ensuring that the independent operation capability of the equipment can be better understood in actual operation, identifying potential efficiency problems, and providing a basis for optimizing the working strategy of the equipment, which is of great significance to improving the overall performance of the system. The step of arranging, combining and grouping the simulated power plant equipment units can generate multiple groups of arranged equipment units. Through this combination method, the overall performance of the equipment can be evaluated under different configurations. Further, the arranged equipment units are simulated in combination according to the power characteristic matrix to generate multiple groups of equipment combination working data, ensuring that the power generation potential of the equipment combination under various operating conditions can be explored in the simulation, and the understanding of the performance of the equipment combination is enhanced. Based on the independent working data of the equipment, the equipment combination working data is optimized and combined to obtain feasible equipment combination working data, which can identify the best configuration in a variety of combination schemes, optimize resource allocation, and improve power generation efficiency, ensuring that the power plant can flexibly adjust the operation strategy in the face of different power demands, and enhance the economy and sustainability of the system. Through this series of steps, the simulated power plant equipment units are finally combined and powered based on the feasible equipment combination working data. Power generation simulation, a variety of combined power generation simulation data, provides a variety of power generation schemes for the power plant in actual operation, improves the flexibility and adaptability of the overall operation, and ensures that the power needs of users can be efficiently met.

[0032] Preferably, step S3 comprises the following steps:

[0033] Step S31: acquiring historical power output data; performing frequency domain transformation processing on the historical power output data to obtain a historical power feature sequence; performing power output pattern recognition on the historical power feature sequence to generate a historical power output pattern;

[0034] Step S32: Analyze the power demand of the historical power output mode to obtain the historical power demand data; calculate the current power demand of the standard equipment operating parameters according to the historical power demand data to obtain the power demand data required by the current equipment;

[0035] Step S33: predicting the required power output of the standard equipment operating parameters according to the power generation data required by the current equipment, and generating predicted required power output data;

[0036] Step S34: performing curve fitting on the predicted required power output data to obtain the predicted required power output curve; performing curve extreme point detection on the predicted required power output curve to obtain power demand peak and valley data.

[0037] The present invention ensures the extensiveness and reliability of the data source by obtaining the operation of historical power output data. By performing frequency domain transformation processing on the historical power output data, the key features of the power output can be extracted to obtain the historical power feature sequence, and then the power output mode recognition is performed on the sequence to generate the historical power output mode, which lays the foundation for the subsequent power demand analysis and ensures that the rules of historical data can be accurately grasped when analyzing the power output mode, thereby improving the accuracy and reliability of subsequent predictions. The step of performing power demand analysis on the historical power output mode can deeply understand the changes in power demand under different power output modes, obtain historical power demand data, calculate the current power generation demand for the standard equipment operating parameters based on these data, and generate the power generation data required by the current equipment. This series of operations ensures the accurate grasp of the changes in power demand, provides a scientific basis for subsequent power output predictions, and improves the flexibility and response speed of the system in dealing with power demand fluctuations. The operation of predicting the required power output of standard equipment operating parameters according to the power generation data required by the current equipment can generate the predicted power output data, ensuring that scientific power output predictions can be made based on historical data and current demand in actual operation, improving the accuracy and effectiveness of the prediction, and providing reliable data support for power plants in scheduling and resource allocation, ensuring that reasonable decisions can be made in the face of a changing power market, and enhancing the economy and effectiveness of the system. The step of curve fitting for the predicted power output data can generate a predicted power output curve, and by detecting extreme points on the predicted curve, power demand peak and valley data can be obtained, ensuring that the changing trend of power demand can be accurately identified during peak and trough periods of power demand, providing an important basis for optimizing the dispatching strategy of the power plant, improving the responsiveness and flexibility of the overall system, and ensuring that efficient power supply and management can be achieved under different power demand conditions.

[0038] Preferably, step S4 comprises the following steps:

[0039] Step S41: performing power superposition calculation on multiple combined power generation simulation data to generate combined power data; performing stable efficiency calculation on the combined power data to generate a combined efficiency index;

[0040] Step S42: Based on the predicted required power output data, the combined efficiency index is screened for power generation intensity adaptation to obtain an efficiency adaptation combination; and according to the efficiency adaptation combination, a plurality of combined power generation simulation data are matched with equipment combinations to obtain a power generation intensity adaptation combination unit;

[0041] Step S43: Associatively link the power demand peak and valley data and the power generation intensity adaptation combination unit to obtain a peak and valley adaptation device unit table;

[0042] Step S44: adjusting the operation cycle of the power generation intensity adaptation combination unit based on the peak-valley adaptation device unit table to generate adaptation device combination scheduling data.

[0043] The present invention can effectively integrate the power output of different equipment combinations in the power generation process and generate combined power data by performing power superposition calculation on multiple combined power generation simulation data. By performing stable efficiency calculation on the combined power data and generating a combined efficiency index, it is ensured that the synergy between the various devices can be fully considered when evaluating the power generation efficiency, thereby improving the accuracy of the overall power generation efficiency evaluation, providing a scientific basis for subsequent scheduling and resource allocation, and optimizing the operation strategy of the power plant. Based on the predicted required power output data, the combined efficiency index is subjected to power generation intensity adaptation screening, which can ensure that the optimal equipment combination is selected under different power demand states to obtain an efficiency adaptation combination. By matching the equipment combination of multiple combined power generation simulation data according to the efficiency adaptation combination and generating a power generation intensity adaptation combination unit, the flexibility and adaptability of the equipment configuration are improved, ensuring that the power plant can achieve efficient power generation under different operating conditions, and enhancing the economy and resource utilization of the system. The steps of associating and linking the peak and valley data of power demand and the power generation intensity adaptation combination unit can effectively identify the best equipment combination under different power demand conditions, obtain the peak and valley adaptation equipment unit table, ensure that the appropriate equipment combination can be quickly matched during the peak and valley periods of power demand, improve the dispatch flexibility of the power plant in the face of demand fluctuations, enhance the system's ability to respond to changes in power demand, and provide an important basis for subsequent dispatch decisions. Based on the peak and valley adaptation equipment unit table, the operation cycle of the power generation intensity adaptation combination unit is adjusted to generate the adaptation equipment combination dispatch data, ensure that the equipment operation cycle can be flexibly adjusted under different power demand conditions, optimize resource allocation, improve power generation efficiency, ensure that the power plant can provide stable power supply during peak periods, and reasonably reduce operating costs during valley periods, enhance the overall system's operating efficiency and stability, and provide solid technical support for the realization of intelligent power plant management.

[0044] Preferably, step S44 includes the following steps:

[0045] Step S441: performing time series decomposition on the peak-valley adaptation equipment unit table to obtain a basic cycle sequence; performing principal component extraction on the basic cycle sequence to obtain a core cycle pattern;

[0046] Step S442: divide the core cycle mode into time windows to obtain scheduling time segments; perform device state mapping on the power generation intensity adaptation combination unit according to the scheduling time segments to generate a device state sequence;

[0047] Step S443: Calculate the state transition cost of the device state sequence to obtain a state transition matrix;

[0048] Step S444: perform the shortest step length detection on the state transition matrix to generate the shortest path data; perform the equipment operation cycle adjustment on the shortest path data to generate the adaptive equipment combination scheduling data.

[0049] The present invention can effectively identify the basic cycle sequences in the operation of the equipment by performing time series decomposition on the peak-valley adaptation equipment unit table. After obtaining these basic cycle sequences, the core cycle patterns are generated through principal component extraction, ensuring that the most representative cycle features can be extracted when analyzing the equipment operation rules, thereby improving the understanding of the equipment operation status, enhancing the scientificity and rationality of subsequent scheduling strategies, and providing an important basis for optimizing equipment operation. The step of dividing the core cycle mode into time windows can divide the equipment operation data into scheduling time segments. Through this division, a corresponding scheduling strategy can be formulated for each time segment. The equipment state mapping of the power generation intensity adaptation combination unit is performed according to the scheduling time segment to generate an equipment state sequence, ensuring that the equipment operation state can be accurately reflected in different scheduling time periods, improving the real-time and flexibility of the scheduling process, and laying the foundation for subsequent state analysis. The state transition cost calculation operation is performed on the equipment state sequence to generate a state transition matrix. Through this matrix, the cost of equipment transitions between different states can be effectively evaluated, providing a quantitative basis for subsequent scheduling decisions, ensuring that the economy and feasibility of equipment state transitions can be fully considered when formulating scheduling strategies, improving the efficiency and rationality of the overall scheduling, and providing support for the efficient use of power plant resources. The step of performing the shortest step length detection on the state transition matrix can identify the optimal path in equipment operation and generate the shortest path data, ensuring that the equipment state transition plan with the lowest cost can be selected in actual scheduling, and the equipment operation cycle can be adjusted for the shortest path data to generate adaptive equipment combination scheduling data, ensuring that the power plant can flexibly adjust the equipment operation cycle during peak and trough periods, optimize resource allocation, improve power generation efficiency, enhance the adaptability and economy of the power plant in responding to changes in electricity demand, and provide technical support for efficient power plant management.

[0050] Preferably, step S443 includes the following steps:

[0051] Performing state quantization processing on the device state sequence to obtain a quantized state sequence;

[0052] Perform transfer frequency statistics on the quantized state sequence to generate a state transfer frequency table;

[0053] Based on the preset state transition weight data, the state transition frequency table is cost calculated to obtain the basic state transition cost; the basic state transition cost is matrix constructed to generate the state transition cost matrix;

[0054] Identify unreasonable costs on the state transfer cost matrix and obtain unreasonable conversion costs;

[0055] The cost branches of the state transfer cost matrix are cleaned up according to the unreasonable conversion costs to generate the state transition matrix.

[0056] The present invention can convert the running state of the equipment into a quantifiable value by performing state quantization processing on the equipment state sequence, and obtain a quantized state sequence. Through this quantization, it is ensured that the running performance of the equipment can be evaluated in a data-driven manner in the subsequent analysis, which improves the analyzability and accuracy of the data, provides a basis for the subsequent state transition frequency statistics, and enhances the comprehensive understanding of the equipment running state. The step of performing transfer frequency statistics on the quantized state sequence generates a state transition frequency table, which can reveal the frequency of the equipment switching between different states, and provides a real basis for the subsequent cost calculation, ensuring that the actual operation situation can be reflected when analyzing the effectiveness of the equipment operation, improving the grasp of the equipment operation dynamics, and laying the foundation for formulating a more reasonable scheduling strategy. Based on the preset state transition weight data, the state transition frequency table is cost-calculated to obtain the basic state transition cost, ensuring that the cost of switching between each state can be fully considered when evaluating the economic efficiency of the equipment state conversion, and constructing a state transfer cost matrix, which can clearly present the conversion cost between different states, promotes the in-depth analysis of the equipment operation efficiency, and provides a quantitative basis for the subsequent scheduling optimization. The operation of identifying unreasonable costs on the state transfer cost matrix can effectively find out the economic problems existing in the equipment state conversion, obtain the unreasonable conversion cost, and provide direction for the subsequent cost branch cleaning, ensuring that unnecessary resource waste can be avoided when formulating scheduling strategies, and improving the rationality and efficiency of the overall scheduling. According to the steps of cleaning the cost branches of the state transfer cost matrix based on the unreasonable conversion cost, the state transition matrix is ​​generated to ensure that the reasonable state conversion cost can be reflected in the final model, thereby providing a scientific basis for subsequent scheduling decisions, improving the flexibility and economy of power plants in resource allocation and equipment scheduling, and ensuring efficient and stable power generation output under different power demand conditions.

[0057] The present invention also provides a power control system based on a power characteristic matrix, which is used to execute the power control method based on the power characteristic matrix as described above. The power control system based on the power characteristic matrix includes:

[0058] The data preprocessing module is used to obtain the distributed power plant equipment data; replace the abnormal values ​​of the distributed power plant equipment data to obtain the complete equipment data; screen the complete equipment data for standard operating parameters to generate standard equipment operating parameters;

[0059] The combined simulation module is used to simulate the equipment unit of the standard equipment operating parameters to generate simulated power plant equipment units; to simulate the combined power generation of the simulated power plant equipment units to obtain a variety of combined power generation simulation data;

[0060] The power generation and demand analysis module is used to obtain historical power output data; perform power demand analysis on the historical power output data to obtain historical power demand data; perform power generation demand forecasting on the standard equipment operating parameters based on the historical power demand data to generate the power output data required for forecasting; perform demand peak and valley analysis on the power output data required for forecasting to obtain power demand peak and valley data;

[0061] The scheduling analysis module is used to perform intensity adaptation screening on multiple combined power generation simulation data based on the predicted required power output data to obtain a power generation intensity adaptation combination unit; adjust the operation cycle of the power generation intensity adaptation combination unit based on the power demand peak and valley data to generate adaptive equipment combination scheduling data;

[0062] The operation scheduling module is used to generate distributed equipment scheduling instructions based on the combined scheduling data of the adapted equipment; and use the distributed equipment scheduling instructions to perform equipment operation scheduling on the virtual power plant to realize an intelligent power control method.

[0063] The present invention obtains distributed power plant equipment data through the data preprocessing module to ensure the comprehensiveness and reliability of the data. The implementation of abnormal value replacement effectively eliminates data deviations caused by equipment failures or data collection errors, thereby generating complete equipment data. These complete data are further screened for standard operating parameters to ensure that the data based on which subsequent analysis is based meets the normal operating standards of the equipment, thereby enhancing the consistency and effectiveness of the data, laying a solid foundation for subsequent analysis and optimization, and improving the technical level and reliability of the overall system. The combined simulation module generates a variety of simulated power plant equipment units by simulating the equipment units of standard equipment operating parameters. This process is The operation strategy of the power plant provides rich simulation data, which can deeply analyze the synergy between different equipment combinations. With the help of combined power generation simulation, a variety of combined power generation simulation data are generated, which provides diverse choices for decision-making, optimizes the flexibility and efficiency of power plant operation, ensures the best power generation effect under different conditions, and improves the adaptability and response speed of the technology. The power generation demand analysis module establishes an important foundation for changes in power demand by acquiring and analyzing historical power output data. The in-depth analysis of historical data not only extracts the law of power demand, but also predicts power generation demand for standard equipment operating parameters, thereby generating the power output data required for prediction, and further implementing demand peaks and valleys. The analysis helps identify the peak and trough periods of electricity demand, provides a scientific basis for the optimization of subsequent dispatch strategies, ensures accurate dispatch decisions in the face of fluctuations in electricity demand, and improves the overall responsiveness of the system. The dispatch analysis module is based on the analysis of the predicted power output data, and performs strength adaptation screening on a variety of combined power generation simulation data to ensure efficient power generation of different equipment combinations under various power demand conditions. It further generates adaptive equipment combination dispatch data by adjusting the operating cycle based on the peak and trough data of power demand. This highly adaptable dispatch strategy optimizes the operating efficiency of the equipment, ensuring that sufficient power output can be provided during peak power demand periods and sufficient power output during trough demand periods. It effectively reduces unnecessary waste of resources and improves the overall operational efficiency and benefits of the power plant. The operation dispatching module generates distributed equipment dispatching instructions according to the combined dispatching data of the adapted equipment to realize the intelligent management of the virtual power plant. These dispatching instructions can dynamically adjust the operating status of the equipment based on real-time data and prediction results, improve the degree of automation of equipment operation, and enhance the flexibility and response speed of power supply. The overall system not only promotes the coordination between distributed power plants and power grids, improves the stability and reliability of the power system, but also supports the efficient use of renewable energy, promotes the development and application of green energy, and ultimately meets the diversified power needs of users and enhances user satisfaction and service quality.

[0064] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the power control method based on the power characteristic matrix as described in any one of the above items are implemented.

[0065] The present invention can optimize power production and distribution through real-time data collection and analysis, improve the overall operating efficiency of the power system, ensure rapid response and adjustment of power generation combinations when power demand fluctuates, effectively reduce operating costs, and improve economic benefits. Through in-depth mining and pattern recognition of equipment operation data, it can accurately identify power output modes and demand changes, optimize equipment scheduling strategies, so that various types of equipment can perform at their best under different working conditions, ensure the stability and reliability of power supply, use advanced algorithms for state conversion and cost analysis, monitor equipment status in real time and make reasonable evaluations, identify unreasonable operating costs, ensure the reasonable allocation and use of resources, reduce equipment maintenance costs and unnecessary power waste, and achieve Predictions and simulations based on historical data, through accurate prediction and analysis of electricity demand, can provide a scientific basis for the dispatching decisions of power plants, ensure that electricity demand can be met during peak periods, and effectively adjust equipment operation during off-peak periods to improve resource utilization. Through state quantification and frequency statistics, it can record the operating state changes of equipment in detail and generate a clear state transfer matrix, providing accurate data support for subsequent dispatch optimization and decision-making, thereby improving the intelligence and automation level of power plant management, and providing a flexible strategy adjustment mechanism for power dispatch. Through dynamic optimization and adjustment of equipment combinations, it can respond quickly to real-time changes in electricity demand, ensure the efficiency and economy of power supply, and promote the integration and development of renewable energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic diagram of the steps of a power control method based on a power characteristic matrix;

[0067] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0068] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0069] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0070] The technical method of the present invention is described clearly and completely below 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.

[0071] 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.

[0072] 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.

[0073] To achieve this, please refer to Figures 1 to 3 , a power control method based on a power characteristic matrix, comprising the following steps:

[0074] Step S1: Obtain distributed power plant equipment data; replace abnormal values ​​in the distributed power plant equipment data to obtain complete equipment data; perform standard operation parameter screening on the complete equipment data to generate standard equipment operation parameters;

[0075] Step S2: Perform equipment unit simulation processing on the standard equipment operating parameters to generate simulated power plant equipment units; perform combined power generation simulation on the simulated power plant equipment units to obtain multiple combined power generation simulation data;

[0076] Step S3: Acquire historical power output data; perform power demand analysis on the historical power output data to obtain historical power demand data; perform power generation demand forecasting on the standard equipment operating parameters based on the historical power demand data to generate predicted power output data; perform demand peak and valley analysis on the predicted power output data to obtain power demand peak and valley data;

[0077] Step S4: Based on the predicted required power output data, multiple combined power generation simulation data are strength-adaptively screened to obtain a power generation strength adaptation combination unit; based on the power demand peak and valley data, the power generation strength adaptation combination unit is operated periodically adjusted to generate adaptation equipment combination scheduling data;

[0078] Step S5: Generate a distributed device dispatching instruction according to the adaptive device combination dispatching data; use the distributed device dispatching instruction to dispatch the equipment operation of the virtual power plant to realize the intelligent power control method.

[0079] The present invention ensures the comprehensiveness and accuracy of the data basis by acquiring the data of distributed power plant equipment. The processing of replacing outliers on these data can effectively eliminate inaccurate data caused by data acquisition errors or equipment failures, thereby improving the reliability of the overall data. Then, the standard operating parameters are screened for the complete equipment data to ensure that the data used meets the normal operating requirements of the equipment, which is crucial for subsequent analysis and simulation. This standardized processing of data not only improves the availability and consistency of the data, but also lays a solid foundation for subsequent simulation analysis, ensures the effectiveness and accuracy of subsequent steps, and performs equipment unit simulation processing on the standard equipment operating parameters to generate a variety of simulated power plant equipment units. This process enables a variety of equipment combinations to be simulated under different operating conditions, providing a more comprehensive operating perspective. This simulation can not only help identify the synergy between different equipment, but also generate a variety of combined power generation simulation data through combined power generation simulation, providing a rich basis for the dispatching decision of the power plant. Through these simulation data, the operating efficiency of the power plant can be deeply analyzed, the configuration scheme of the equipment can be optimized, thereby improving the flexibility and efficiency of the overall power production, and by acquiring historical power output data and performing power demand analysis, an important foundation is established for the change of power demand. This stage not only involves in-depth analysis of historical data, but also requires extracting the laws and trends of power demand from it in order to make more accurate power output forecasts. Based on these historical data, the power generation demand forecast significantly improves the accuracy of the forecast, which helps the power plant to be fully prepared to cope with future power demand fluctuations. Further demand peak and valley analysis can help identify the peak and valley periods of power demand, which provides an important basis for the subsequent optimization of scheduling strategies, ensuring the stability and reliability of power supply. Based on the analysis of the power output data required for the forecast, the intensity adaptation screening of multiple combined power generation simulation data is carried out to ensure efficient power generation of different equipment combinations under various demand conditions. The implementation of this process can not only improve the adaptability of the equipment combination, but also ensure that the dispatching strategy of the power plant can respond flexibly when facing different power demands. Next, the operation cycle of the power generation intensity adaptation combination unit is adjusted based on the power demand peak and valley data to further optimize the dispatching efficiency of the equipment combination. By reasonably arranging the operation cycle of the equipment, sufficient power output can be provided during the peak period of power demand, and unnecessary energy loss can be reduced during the trough period of demand, thereby achieving efficient utilization of resources. The generated distributed equipment dispatch instructions realize the intelligent management of the virtual power plant. These instructions can dynamically dispatch equipment operations based on real-time data and forecast results, improving the responsiveness and control capabilities of power plants. This process not only promotes coordination between distributed power plants and the power grid, but also enhances the stability and reliability of the entire power system.Driven by intelligent control methods, distributed power plants can more efficiently utilize renewable energy and promote the development and application of green energy. At the same time, by improving the flexibility of power supply, it can better meet the diverse power needs of users, thereby enhancing user satisfaction and optimizing the overall power service quality.

[0080] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a power control method based on a power characteristic matrix of the present invention. In this example, the power control method based on the power characteristic matrix includes the following steps:

[0081] Step S1: Obtain distributed power plant equipment data; replace abnormal values ​​in the distributed power plant equipment data to obtain complete equipment data; perform standard operation parameter screening on the complete equipment data to generate standard equipment operation parameters;

[0082] In this embodiment, the operation of obtaining distributed power plant equipment data is performed by using a data acquisition system to read sensor data from each distributed device in real time, using industrial communication protocols such as Modbus or OPC UA (OLE for Process Control Unified Architecture) for data transmission to ensure the accuracy and timeliness of the data, replacing outliers in the acquired equipment data, using statistical methods such as Z-score or IQR (Interquartile Range) for outlier detection, replacing or eliminating data that exceeds the normal range, and finally obtaining complete equipment data. Subsequently, standard operating parameters are screened for the complete equipment data, and data mining techniques such as cluster analysis or principal component analysis (PCA) are used to identify standard operating parameters of the equipment to ensure that subsequent analysis is based on accurate equipment performance data.

[0083] Step S2: Perform equipment unit simulation processing on the standard equipment operating parameters to generate simulated power plant equipment units; perform combined power generation simulation on the simulated power plant equipment units to obtain multiple combined power generation simulation data;

[0084] In this embodiment, the equipment unit simulation processing is performed on the standard equipment operating parameters, and the model is built using simulation software such as MATLAB / Simulink or ANSYS to construct a simulated power plant model that includes the characteristics of various types of equipment. The standard operating parameters are used to input the model, and dynamic simulation is performed to generate simulated power plant equipment units. Next, the simulated power plant equipment units are simulated for combined power generation, and the power generation performance of different equipment combinations is analyzed using methods such as Monte Carlo Simulation to obtain a variety of combined power generation simulation data. These data provide a real reference for subsequent power demand and resource scheduling.

[0085] Step S3: Acquire historical power output data; perform power demand analysis on the historical power output data to obtain historical power demand data; perform power generation demand forecasting on the standard equipment operating parameters based on the historical power demand data to generate predicted power output data; perform demand peak and valley analysis on the predicted power output data to obtain power demand peak and valley data;

[0086] In this embodiment, the operation of obtaining historical power output data is performed by calling the historical data storage of the power company or the smart meter system. The data format is usually CSV (Comma-Separated Values) or database format. Next, the power demand analysis is performed on the historical power output data. Time series analysis methods, such as ARIMA (Autoregressive Integrated Moving Average model), are used to identify the trend and cyclical changes in power demand to obtain historical power demand data. Based on the historical power demand data, the power generation demand is predicted for the standard equipment operating parameters. Linear regression or machine learning models such as Random Forest are used for prediction to generate the power output data required for the prediction. Subsequently, the demand peak and valley analysis is performed on the power output data required for the prediction. The peak and valley analysis method is used to identify the peaks and valleys of power demand and obtain the peak and valley data of power demand to provide a basis for subsequent scheduling.

[0087] Step S4: Based on the predicted required power output data, multiple combined power generation simulation data are strength-adaptively screened to obtain a power generation strength adaptation combination unit; based on the power demand peak and valley data, the power generation strength adaptation combination unit is operated periodically adjusted to generate adaptation equipment combination scheduling data;

[0088] In this embodiment, intensity adaptation screening is performed on multiple combinations of power generation simulation data based on the predicted required power output data, and optimization algorithms such as genetic algorithm (Genetic Algorithm) or particle swarm optimization (Particle Swarm Optimization) are used to evaluate the power generation intensity of different combinations to generate a power generation intensity adaptation combination unit. Subsequently, the operation cycle of the power generation intensity adaptation combination unit is adjusted based on the peak and valley data of power demand, and scheduling optimization is performed using linear programming or integer programming methods to generate adaptive equipment combination scheduling data to ensure that the operating time of the equipment can be reasonably configured during peak and valley periods to improve power generation efficiency.

[0089] Step S5: Generate a distributed device dispatching instruction according to the adaptive device combination dispatching data; use the distributed device dispatching instruction to dispatch the equipment operation of the virtual power plant to realize the intelligent power control method.

[0090] In this embodiment, distributed device dispatching instructions are generated according to the combined dispatching data of the adapted devices, and a dispatching management system such as SCADA (Supervisory Control and Data Acquisition) is used to generate and issue instructions. The dispatching instructions include equipment startup, shutdown and operation parameter settings. The distributed device dispatching instructions are used to dispatch the equipment operation of the virtual power plant to ensure that each device works together according to the predetermined plan, monitor the equipment status in real time, and make dynamic adjustments through the feedback mechanism to ensure the efficient operation of the virtual power plant, ultimately realizing an intelligent power control method and improving the flexibility and reliability of the power system.

[0091] Preferably, step S1 comprises the following steps:

[0092] Step S11: Obtain distributed power plant equipment data; perform abnormal value interval detection on the distributed power plant equipment data to obtain abnormal value intervals of power plant equipment;

[0093] Step S12: removing abnormal values ​​from the abnormal value interval of the power plant equipment to generate cleaning power plant equipment data;

[0094] Step S13: performing linear interpolation of abnormal intervals on the cleaning power plant equipment data to obtain complete equipment data;

[0095] Step S14: performing equipment operation simulation on the complete equipment data to obtain a simulation operation parameter set;

[0096] Step S15: clustering the simulation operation parameter set to obtain a clustered operation parameter set;

[0097] Step S16: Standardize the clustered operating parameter set to generate standard equipment operating parameters.

[0098] In this embodiment, the operation of obtaining the distributed power plant equipment data is to collect real-time data from each distributed device by using a data acquisition system. The specific method includes using Modbus protocol or OPC UA (OLE for Process Control Unified Architecture) for data communication to ensure that the data transmission between devices is real-time and accurate. The collected data includes multiple parameters such as voltage, current, power, temperature, etc. Next, the distributed power plant equipment data is detected for abnormal value intervals, and statistical methods such as Z-score detection or box plot (Box Plot) method is used to identify abnormal points in the data, determine the upper and lower limits of abnormal values, generate abnormal value intervals for power plant equipment, and perform abnormal elimination operations on abnormal value intervals for power plant equipment. First, according to the determined abnormal value interval, by writing a data processing script, using Python or R language to implement data filtering, the data that is not in the normal interval is eliminated, and the cleaning power plant equipment data is generated. The specific method includes using the DataFrame in the Pandas library to perform data operations, traversing each data point, determining whether it is within the normal range, and ensuring that valid data is retained. After eliminating abnormal data, the generated data set should contain historical data of each device under normal operating conditions, perform linear interpolation operations on the abnormal interval of the cleaning power plant equipment data, and apply the linear interpolation algorithm to fill in missing or incomplete data. The specific steps are to first identify the location of the missing value in the data set, and then calculate the interpolation based on the valid data points adjacent to the front and back. The interpolation function of the NumPy library is used to perform linear interpolation calculations to generate complete device data and ensure data continuity during the interpolation process. The specific method includes setting the value of the missing data point to the weighted average of the valid data points before and after it, performing device operation simulation operations on the complete device data, using simulation software such as MATLAB / Simulink to construct a dynamic model of the device, establishing a mathematical model including device characteristics and operating parameters, inputting complete device data, performing time domain simulation, and generating a simulation operation parameter set. The specific implementation steps include defining the physical parameters, operating constraints and environmental conditions of the device, setting the simulation time, running the simulation model and recording the operating status of the device under different conditions, and finally obtaining a simulation operation data set containing multiple parameters such as device output power and temperature changes, performing operation parameter clustering operations on the simulation operation parameter set, and using clustering algorithms such as K-means or hierarchical clustering (Hierarchical Clustering). Clustering) is used to analyze the simulation data. First, the simulation operation parameter set is standardized to eliminate the influence of different dimensions on the clustering results. Then the parameters of the clustering algorithm are set, such as the number of clusters. Then, the standardized data is clustered to generate a clustering operation parameter set. Each cluster represents a group of similar equipment operation states. In the specific implementation, the Python Scikit-learn library is used to cluster the data.Ensure that the clustering results can effectively reflect the operating characteristics of the equipment under different working conditions, and provide a basis for subsequent standardization. The operation of standardizing the clustering operating parameter set uses standardization techniques such as Z-score standardization or Min-Max scaling to unify the clustering results to eliminate the dimensional influence between different characteristics. The specific method is to calculate the mean and standard deviation of each clustering parameter, use the formula for standardization, generate standard equipment operating parameters, ensure that all parameters are on the same scale, and facilitate subsequent analysis and comparison. The final standard equipment operating parameters will provide basic data for equipment performance evaluation and optimization, and ensure the effectiveness of subsequent scheduling and decision-making. ,

[0099] Preferably, step S2 comprises the following steps:

[0100] Step S21: extracting features of standard equipment operating parameters to obtain equipment characteristic parameters; performing correlation analysis on the equipment characteristic parameters to generate a parameter correlation matrix;

[0101] Step S22: performing equipment unit operating condition analysis on the equipment characteristic parameters based on the parameter association matrix to obtain an operating condition parameter set; performing operation trajectory calculation on the operating condition parameter set to obtain equipment operation trajectory data;

[0102] Step S23: performing equipment simulation processing on equipment characteristic parameters according to equipment operation trajectory data to generate a simulated power plant equipment unit;

[0103] Step S24: simulating the power generation operation of the simulated power plant equipment unit to obtain simulated equipment working data;

[0104] Step S25: Based on the simulated equipment working data, feasible combined power generation simulation is performed on the simulated power plant equipment units to obtain multiple combined power generation simulation data.

[0105] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0106] Step S21: extracting features of standard equipment operating parameters to obtain equipment characteristic parameters; performing correlation analysis on the equipment characteristic parameters to generate a parameter correlation matrix;

[0107] In this embodiment, the operation of feature extraction of standard equipment operating parameters first uses data processing tools such as the Pandas library in Python to clean and organize the equipment operating parameter data, and extract key features such as equipment power, efficiency, temperature, etc., and then uses feature selection algorithms such as Random Forest or Principal Component Analysis (PCA) to screen out the most influential features to ensure that the extracted features can effectively reflect the equipment performance and generate equipment characteristic parameters. Subsequently, the equipment characteristic parameters are subjected to correlation analysis, and a correlation coefficient matrix and visualization tools such as the Seaborn library are used to draw a heat map and generate a parameter correlation matrix. By analyzing the correlation between different features, the key parameters affecting the equipment performance are identified to ensure the accuracy and effectiveness of subsequent analysis.

[0108] Step S22: performing equipment unit operating condition analysis on the equipment characteristic parameters based on the parameter association matrix to obtain an operating condition parameter set; performing operation trajectory calculation on the operating condition parameter set to obtain equipment operation trajectory data;

[0109] In this embodiment, the operation of performing equipment unit operating condition analysis on equipment characteristic parameters based on the parameter association matrix first uses a machine learning algorithm such as a support vector machine (SVM) or a decision tree to classify the equipment characteristic parameters to obtain an operating condition parameter set, and then calculates the operating trajectory of the operating condition parameter set. A simulation tool such as MATLAB / Simulink is used to build a dynamic model to simulate the operating behavior of the equipment under different operating conditions and generate equipment operating trajectory data to ensure that the simulation process takes into account the actual working environment and dynamic changes of the equipment. By analyzing the operating trajectory, the operating characteristics of the equipment under various operating conditions are identified to provide real basic data for subsequent simulations.

[0110] Step S23: performing equipment simulation processing on equipment characteristic parameters according to equipment operation trajectory data to generate a simulated power plant equipment unit;

[0111] In this embodiment, the operation of performing equipment simulation processing on the equipment characteristic parameters according to the equipment operation trajectory data is to first establish a mathematical model of the equipment in the simulation software, input the acquired equipment operation trajectory data, select a suitable simulation algorithm, such as discrete event simulation (Discrete Event Simulation) or continuous simulation, run the simulation model, generate a simulated power plant equipment unit, and ensure that the simulation model can truly reflect the operating characteristics and behaviors of the equipment. During the simulation process, record various operating parameters of the equipment, such as power output, load changes, etc., and generate a detailed simulation report to provide necessary data support for subsequent power generation operation simulations to ensure the accuracy and reliability of the simulation results.

[0112] Step S24: simulating the power generation operation of the simulated power plant equipment unit to obtain simulated equipment working data;

[0113] In this embodiment, the operation of power generation operation simulation is performed on the simulated power plant equipment unit. Simulation software such as MATLAB or Simulink is used to build a comprehensive simulation model containing all equipment parameters. Various data of the simulated power plant equipment unit are input to perform dynamic operation simulation to ensure that the power generation efficiency and output power of each device can be simulated under different operating conditions. The equipment working data of each simulation operation, such as power output, energy consumption and operating time, is recorded to generate simulated equipment working data to ensure that the simulation results cover different operating scenarios and can truly reflect the performance of the equipment in actual operation, thereby providing an accurate data basis for subsequent combined power generation simulation.

[0114] Step S25: Based on the simulated equipment working data, feasible combined power generation simulation is performed on the simulated power plant equipment units to obtain multiple combined power generation simulation data.

[0115] In this embodiment, a feasible combination power generation simulation operation is performed on the simulated power plant equipment units based on the simulated equipment working data. First, the simulated equipment working data is analyzed to identify the power generation potential and operating efficiency of the equipment. Then, a combinatorial optimization algorithm, such as a genetic algorithm (Genetic Algorithm) or a mixed integer linear programming (MILP), is used to evaluate different equipment combinations and generate a variety of combined power generation simulation data to ensure that each combination takes into account the synergy and load balancing between the equipment. Finally, the power generation capacity, operating cost and efficiency of each combination are output to form a feasible equipment combination plan, which provides a scientific basis for the scheduling and management of the power plant and ensures the comprehensiveness and effectiveness of the combined power generation simulation results.

[0116] Preferably, step S25 comprises the following steps:

[0117] Step S251: classify the simulated device working data into types to obtain a device classification data set; perform power characteristic analysis on the device classification data set to obtain a power characteristic matrix;

[0118] Step S252: performing independent operation simulation on the simulated power plant equipment units according to the power characteristic matrix to generate equipment independent operation data; performing permutation, combination and grouping on the simulated power plant equipment units to generate multiple groups of permutation equipment units;

[0119] Step S253: performing combined operation simulation on the arranged equipment units according to the power characteristic matrix to generate multiple sets of equipment combined operation data; performing optimized combination screening on the equipment combined operation data based on the equipment independent operation data to obtain feasible equipment combined operation data;

[0120] Step S254: Based on the feasible equipment combination working data, a combined power generation simulation is performed on the simulated power plant equipment units to obtain a variety of combined power generation simulation data.

[0121] In this embodiment, the operation of classifying the simulated equipment working data by type is to first collect and organize the equipment working data by using data mining technology. The data includes the operating parameters, power output and working status of the equipment. Then, the Pandas library in Python is used to classify the data, group them according to the equipment type and working status, and generate the equipment classification data set. Next, the power characteristics of the equipment classification data set are analyzed, and statistical analysis tools such as NumPy and SciPy are used to calculate the power output of different equipment and generate a power characteristic matrix to ensure that the matrix contains the power output characteristics of each equipment under different working conditions, so as to provide the necessary parameters for the subsequent independent working simulation. According to the power characteristic matrix, the operation of the simulated power plant equipment unit is carried out to simulate the independent working, and the simulation software such as MATLAB / Simulink is used to establish a dynamic model containing all equipment parameters, input the data in the power characteristic matrix, perform the operation simulation of the individual equipment, record the output data of each equipment in the independent working state, generate the equipment independent working data, ensure that the dynamic response and load change of the equipment are taken into account in the simulation process, and the obtained independent working data will provide the basis for the subsequent equipment combination simulation. The steps of arranging, combining and grouping the simulated power plant equipment units are as follows: by writing an algorithm, the equipment is fully arranged and combined using Python's itertools library to generate multiple groups of arranged equipment units, ensuring that each combination takes into account the equipment's operating characteristics and power output limitations, and then the arranged equipment units are simulated for combined operation according to the power characteristic matrix, and each combination is simulated for operation using the above simulation model, and the output data of each group of equipment in the combined working state is recorded to generate multiple groups of equipment combination working data to ensure that the actual operation of each group of combinations is effectively evaluated. The operation of optimizing and combining the equipment combination working data based on the equipment's independent working data is to first evaluate each group of equipment combination working data, and use a multi-objective optimization algorithm, such as a genetic algorithm or a particle swarm optimization (Particle Swarm Optimization), to analyze the combined power generation efficiency and operating cost, screen out the optimal combination, and obtain feasible equipment combination working data, ensuring that the equipment's synergy and load balance are taken into account during the screening process. Based on the working data of feasible equipment combinations, the simulated power plant equipment units are combined to simulate power generation. The feasible combination data obtained are used to simulate power generation using simulation software. A comprehensive simulation model containing all feasible combinations is established. The operating parameters of the equipment combination are input to perform dynamic simulation, and the power generation performance and efficiency of each combination are recorded. Finally, multiple combinations of power generation simulation data are generated to provide a scientific basis for the dispatch and management of power plants, ensuring that the equipment combination can be flexibly adjusted to achieve efficient power generation under different power demand conditions.

[0122] Preferably, step S3 comprises the following steps:

[0123] Step S31: acquiring historical power output data; performing frequency domain transformation processing on the historical power output data to obtain a historical power feature sequence; performing power output pattern recognition on the historical power feature sequence to generate a historical power output pattern;

[0124] Step S32: Analyze the power demand of the historical power output mode to obtain the historical power demand data; calculate the current power demand of the standard equipment operating parameters according to the historical power demand data to obtain the power demand data required by the current equipment;

[0125] Step S33: predicting the required power output of the standard equipment operating parameters according to the power generation data required by the current equipment, and generating predicted required power output data;

[0126] Step S34: performing curve fitting on the predicted required power output data to obtain the predicted required power output curve; performing curve extreme point detection on the predicted required power output curve to obtain power demand peak and valley data.

[0127] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0128] Step S31: acquiring historical power output data; performing frequency domain transformation processing on the historical power output data to obtain a historical power feature sequence; performing power output pattern recognition on the historical power feature sequence to generate a historical power output pattern;

[0129] In this embodiment, the operation of obtaining historical power output data is achieved by extracting data from a power management system or a smart meter. The data format is usually CSV (Comma-Separated Values) or a database format, which contains power output records over a period of time in the past. Next, the historical power output data is transformed in the frequency domain, and the time domain data is converted into frequency domain data using a fast Fourier transform (FFT), and the main frequency components in the power output signal are identified to generate a historical power feature sequence. Subsequently, the historical power feature sequence is subjected to power output pattern recognition, and a clustering algorithm such as K-means or DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is used to analyze the data, identify different power output patterns, and finally generate a historical power output pattern to provide basic data for subsequent power demand analysis.

[0130] Step S32: Analyze the power demand of the historical power output mode to obtain the historical power demand data; calculate the current power demand of the standard equipment operating parameters according to the historical power demand data to obtain the power demand data required by the current equipment;

[0131] In this embodiment, the operation of performing power demand analysis on historical power output patterns first models the power demand change trend based on the identified historical power output patterns using time series analysis methods, such as ARIMA (autoregressive integrated moving average model), to obtain historical power demand data. Next, based on the historical power demand data, the current power demand is calculated for the standard equipment operating parameters, and the current power demand is predicted using linear regression or machine learning models, such as random forests, to ensure that the calculated power production data required by the current equipment can accurately reflect the changes in power demand, thereby providing real data support for subsequent power output predictions.

[0132] Step S33: predicting the required power output of the standard equipment operating parameters according to the power generation data required by the current equipment, and generating predicted required power output data;

[0133] In this embodiment, the required power output of the standard equipment operating parameters is predicted based on the current equipment required power production data. First, the standard equipment operating parameters are combined with the current power production demand, and a multivariate linear regression or neural network model is used for prediction. The input of the model includes historical power output, equipment performance parameters and current power demand, and the predicted required power output data is generated to ensure that the prediction process fully considers the efficiency and load characteristics of the equipment. The final output predicted required power output data will provide a basis for the scheduling and management of the power plant, ensuring that the equipment operation strategy can be adjusted in time when the power demand changes.

[0134] Step S34: performing curve fitting on the predicted required power output data to obtain the predicted required power output curve; performing curve extreme point detection on the predicted required power output curve to obtain power demand peak and valley data.

[0135] In this embodiment, a curve fitting operation is performed on the predicted power output data. A data analysis tool such as SciPy or MATLAB is used to perform curve fitting on the predicted data using a polynomial fitting method or a spline fitting method to generate a smooth predicted power output curve. It is ensured that a suitable degree of fitting is selected during the fitting process to avoid overfitting or underfitting. The predicted power output curve is then tested for extreme points of the curve. The extreme points of the curve are identified using a derivative method or a second-order derivative method to obtain peak and valley data of power demand. It is ensured that the identified peak and valley data can accurately reflect the peaks and valleys of power demand, provide a scientific basis for the scheduling and resource allocation of power plants, and ensure that reasonable decisions can be made under different power demand conditions.

[0136] Preferably, step S4 comprises the following steps:

[0137] Step S41: performing power superposition calculation on multiple combined power generation simulation data to generate combined power data; performing stable efficiency calculation on the combined power data to generate a combined efficiency index;

[0138] Step S42: Based on the predicted required power output data, the combined efficiency index is screened for power generation intensity adaptation to obtain an efficiency adaptation combination; and according to the efficiency adaptation combination, a plurality of combined power generation simulation data are matched with equipment combinations to obtain a power generation intensity adaptation combination unit;

[0139] Step S43: Associatively link the power demand peak and valley data and the power generation intensity adaptation combination unit to obtain a peak and valley adaptation device unit table;

[0140] Step S44: adjusting the operation cycle of the power generation intensity adaptation combination unit based on the peak-valley adaptation device unit table to generate adaptation device combination scheduling data.

[0141] In this embodiment, the operation of power superposition calculation is performed on multiple combinations of power generation simulation data. First, the power generation simulation data of all combinations are collected to ensure that the data is complete and in a consistent format. Then, the NumPy library in Python is used to superimpose the power generation of each combination, and the total power output of each combination in different time periods is calculated to generate combined power data. Next, the combined power data is subjected to stable efficiency calculation, and the efficiency formula is adopted, that is, the efficiency is equal to the ratio of the output power to the input power. The calculation results are sorted using the Pandas library to generate a combined efficiency index to ensure that the efficiency index of each combination can accurately reflect its performance in actual operation, providing a basis for subsequent adaptation and screening. Based on the predicted required power output data, the operation of power generation intensity adaptation screening of the combined efficiency index is performed. First, the predicted required power output data and the combined efficiency index are cross-analyzed. The conditional screening algorithm is used to ensure that the efficiency of all combinations meets the set threshold standard to obtain an efficiency adaptation combination. Then, the multiple combinations of power generation simulation data are matched with equipment combinations according to the efficiency adaptation combination. A matching algorithm, such as a greedy algorithm or dynamic programming, is used to combine the qualified equipment to generate an efficiency adaptation combination. The power generation intensity adaptation combination unit is formed to ensure that the matching process takes into account the power output and stability of the equipment, improve the overall efficiency of the combination, and perform correlation linking operations on the power demand peak and valley data and the power generation intensity adaptation combination unit. First, the peak and valley data are integrated with the power generation intensity adaptation combination unit. The two are connected according to time series or specific conditions using data framework tools such as Pandas' merge function to generate a peak and valley adaptation equipment unit table to ensure that each combination unit can correspond to the corresponding power demand peak and valley data. Through this association, the operating characteristics of different equipment combinations during peak and valley periods are clarified to provide a basis for subsequent scheduling decisions and ensure the accuracy and real-time nature of the data. Based on the peak and valley adaptation equipment unit table, the operation cycle of the power generation intensity adaptation combination unit is adjusted. First, the operating time and power demand of each combination unit in the peak and valley adaptation equipment unit table are analyzed. Optimization algorithms such as linear programming are used to adjust the operating cycle of the equipment to ensure that during peak power demand periods, high-efficiency equipment combinations can be scheduled first, and adaptive equipment combination scheduling data is generated. Use scheduling management system software such as SCADA (Supervisory The generated dispatch data can be visualized to ensure the rationality and feasibility of the dispatch plan, and finally form a set of efficient equipment combination dispatch strategies to cope with changes in power demand.

[0142] Preferably, step S44 includes the following steps:

[0143] Step S441: performing time series decomposition on the peak-valley adaptation equipment unit table to obtain a basic cycle sequence; performing principal component extraction on the basic cycle sequence to obtain a core cycle pattern;

[0144] Step S442: divide the core cycle mode into time windows to obtain scheduling time segments; perform device state mapping on the power generation intensity adaptation combination unit according to the scheduling time segments to generate a device state sequence;

[0145] Step S443: Calculate the state transition cost of the device state sequence to obtain a state transition matrix;

[0146] Step S444: perform the shortest step length detection on the state transition matrix to generate the shortest path data; perform the equipment operation cycle adjustment on the shortest path data to generate the adaptive equipment combination scheduling data.

[0147] In this embodiment, the operation of time series decomposition of the peak-valley adaptation equipment unit table is first performed by using the statsmodels library in Python to perform seasonal decomposition on the equipment operation data, and an additive or multiplicative model is used to obtain a basic cycle sequence, which includes a trend component, a seasonal component, and a residual component. The next step is to extract the principal component of the basic cycle sequence and use principal component analysis (PCA) to extract the principal component of the basic cycle sequence. Analysis), using the PCA tool in the Scikit-learn library to extract the core cycle pattern that best represents the data variability, ensuring that the extracted principal components can effectively reflect the main characteristics of the equipment's operating status, generating the core cycle pattern, and providing a basis for the subsequent scheduling time segment division. The core cycle pattern is divided into time windows. First, according to the actual needs of the equipment operation and historical data, a reasonable time window length is set. The core cycle pattern is sliced ​​using Python's Pandas library to generate scheduling time segments, ensuring that each time segment can represent a complete equipment operation cycle. Next, the power generation intensity adaptation combination unit is mapped to the equipment state according to the scheduling time segment. Using the mapping algorithm, each time segment is matched with the corresponding equipment state to generate an equipment state sequence, ensuring that the state sequence can truly reflect the equipment's operating status in each time period, providing basic data for the subsequent state transition cost calculation. The state transition cost calculation operation is performed on the equipment state sequence. First, the cost function of the state transition is defined. The cost function can consider factors such as the energy consumption, start and stop time of the equipment, and then build a state transition matrix. Use the NumPy library in Python to count the transitions between the states in the equipment state sequence and generate a state transition matrix to ensure that each element in the matrix can accurately reflect the cost of transitioning from one state to another. After completion, the state transition matrix obtained provides necessary data support for the subsequent shortest step detection. The state transition matrix is ​​subjected to the shortest step detection operation. The state transition matrix is ​​analyzed using the Dijkstra algorithm or the A* algorithm to find the shortest path from the initial state to the target state, ensuring that the algorithm can effectively handle the conversion cost of each state in the matrix and generate the shortest path data. Next, the equipment operation cycle is adjusted according to the obtained shortest path data. The scheduling optimization tool is used to generate the adaptive equipment combination scheduling data by adjusting the equipment operation time and sequence to ensure that the final scheduling plan can maximize the power generation efficiency of the equipment and reduce the operating cost. The obtained scheduling data will provide a scientific basis for the intelligent scheduling of the power plant.

[0148] Preferably, step S443 includes the following steps:

[0149] Performing state quantization processing on the device state sequence to obtain a quantized state sequence;

[0150] Perform transfer frequency statistics on the quantized state sequence to generate a state transfer frequency table;

[0151] Based on the preset state transition weight data, the state transition frequency table is cost calculated to obtain the basic state transition cost; the basic state transition cost is matrix constructed to generate the state transition cost matrix;

[0152] Identify unreasonable costs on the state transfer cost matrix and obtain unreasonable conversion costs;

[0153] The cost branches of the state transfer cost matrix are cleaned up according to the unreasonable conversion costs to generate the state transition matrix.

[0154] In this embodiment, the operation of performing state quantization processing on the device state sequence first classifies the continuous states in the device state sequence, defines the quantization standard for each state, and uses the NumPy library or Pandas library in Python to convert the state sequence into a quantized state sequence to ensure that each state is mapped to a discrete value. Next, the transition frequency of the quantized state sequence is counted, and the groupby function in the Pandas library is used to count the transitions between adjacent states to generate a state transition frequency table, which includes the number of transitions between each state, to ensure that the statistical results can truly reflect the changing patterns of the device state and provide a data basis for subsequent cost calculations. The operation of cost calculation for the state transition frequency table based on the preset state transition weight data first sets the weight data for each state transition. These weights can be set according to the energy consumption, maintenance cost and operating efficiency of the equipment. Then, the frequency in the state transition frequency table is multiplied by the corresponding weight to obtain the basic state transition cost. The Pandas library in Python is used for data processing to ensure that the cost of each state transition can accurately reflect the actual situation. After completion, the basic state transition cost is constructed into a matrix to generate a state transition cost matrix. Each element of the matrix corresponds to the conversion cost between each pair of states in the state transition frequency table, ensuring that the matrix is ​​structured for subsequent analysis. The operation of identifying unreasonable costs for the state transition cost matrix first sets the threshold of reasonable costs. These thresholds can be set based on industry standards or historical equipment data. Then, the NumPy library in Python is used to compare each element in the state transition cost matrix, identify costs that exceed reasonable thresholds, and generate unreasonable conversion costs. Ensure that the identified unreasonable costs can accurately reflect abnormal conditions in equipment operation and provide a basis for subsequent cost cleanup. The cost branch cleaning operation of the state transfer cost matrix is ​​performed according to the unreasonable conversion cost. First, the unreasonable costs identified are analyzed to determine the state transfers that need to be cleaned up. The drop function in the Pandas library is used to remove the unreasonable state transfers from the cost matrix and generate a cleaned state transition matrix to ensure that the cleaned matrix only contains reasonable state transfer costs. The final state transition matrix will provide accurate data support for subsequent scheduling optimization and equipment management, ensuring cost control and efficiency improvement during equipment operation.

[0155] The present invention also provides a power control system based on a power characteristic matrix, which is used to execute the power control method based on the power characteristic matrix as described above. The power control system based on the power characteristic matrix includes:

[0156] The data preprocessing module is used to obtain the distributed power plant equipment data; replace the abnormal values ​​of the distributed power plant equipment data to obtain the complete equipment data; screen the complete equipment data for standard operating parameters to generate standard equipment operating parameters;

[0157] The combined simulation module is used to simulate the equipment unit of the standard equipment operating parameters to generate simulated power plant equipment units; to simulate the combined power generation of the simulated power plant equipment units to obtain a variety of combined power generation simulation data;

[0158] The power generation and demand analysis module is used to obtain historical power output data; perform power demand analysis on the historical power output data to obtain historical power demand data; perform power generation demand forecasting on the standard equipment operating parameters based on the historical power demand data to generate the power output data required for forecasting; perform demand peak and valley analysis on the power output data required for forecasting to obtain power demand peak and valley data;

[0159] The scheduling analysis module is used to perform intensity adaptation screening on multiple combined power generation simulation data based on the predicted required power output data to obtain a power generation intensity adaptation combination unit; adjust the operation cycle of the power generation intensity adaptation combination unit based on the power demand peak and valley data to generate adaptive equipment combination scheduling data;

[0160] The operation scheduling module is used to generate distributed equipment scheduling instructions based on the combined scheduling data of the adapted equipment; and use the distributed equipment scheduling instructions to perform equipment operation scheduling on the virtual power plant to realize an intelligent power control method.

[0161] The present invention obtains distributed power plant equipment data through the data preprocessing module to ensure the comprehensiveness and reliability of the data. The implementation of abnormal value replacement effectively eliminates data deviations caused by equipment failures or data collection errors, thereby generating complete equipment data. These complete data are further screened for standard operating parameters to ensure that the data based on which subsequent analysis is based meets the normal operating standards of the equipment, thereby enhancing the consistency and effectiveness of the data, laying a solid foundation for subsequent analysis and optimization, and improving the technical level and reliability of the overall system. The combined simulation module generates a variety of simulated power plant equipment units by simulating the equipment units of standard equipment operating parameters. This process is The operation strategy of the power plant provides rich simulation data, which can deeply analyze the synergy between different equipment combinations. With the help of combined power generation simulation, a variety of combined power generation simulation data are generated, which provides diverse choices for decision-making, optimizes the flexibility and efficiency of power plant operation, ensures the best power generation effect under different conditions, and improves the adaptability and response speed of the technology. The power generation demand analysis module establishes an important foundation for changes in power demand by acquiring and analyzing historical power output data. The in-depth analysis of historical data not only extracts the law of power demand, but also predicts power generation demand for standard equipment operating parameters, thereby generating the power output data required for prediction, and further implementing demand peaks and valleys. The analysis helps identify the peak and trough periods of electricity demand, provides a scientific basis for the optimization of subsequent dispatch strategies, ensures accurate dispatch decisions in the face of fluctuations in electricity demand, and improves the overall responsiveness of the system. The dispatch analysis module is based on the analysis of the predicted power output data, and performs strength adaptation screening on a variety of combined power generation simulation data to ensure efficient power generation of different equipment combinations under various power demand conditions. It further generates adaptive equipment combination dispatch data by adjusting the operating cycle based on the peak and trough data of power demand. This highly adaptable dispatch strategy optimizes the operating efficiency of the equipment, ensuring that sufficient power output can be provided during peak power demand periods and sufficient power output during trough demand periods. It effectively reduces unnecessary waste of resources and improves the overall operational efficiency and benefits of the power plant. The operation dispatching module generates distributed equipment dispatching instructions according to the combined dispatching data of the adapted equipment to realize the intelligent management of the virtual power plant. These dispatching instructions can dynamically adjust the operating status of the equipment based on real-time data and prediction results, improve the degree of automation of equipment operation, and enhance the flexibility and response speed of power supply. The overall system not only promotes the coordination between distributed power plants and power grids, improves the stability and reliability of the power system, but also supports the efficient use of renewable energy, promotes the development and application of green energy, and ultimately meets the diversified power needs of users and enhances user satisfaction and service quality.

[0162] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the power control method based on the power characteristic matrix as described in any one of the above items are implemented.

[0163] The present invention can optimize power production and distribution through real-time data collection and analysis, improve the overall operating efficiency of the power system, ensure rapid response and adjustment of power generation combinations when power demand fluctuates, effectively reduce operating costs, and improve economic benefits. Through in-depth mining and pattern recognition of equipment operation data, it can accurately identify power output modes and demand changes, optimize equipment scheduling strategies, so that various types of equipment can perform at their best under different working conditions, ensure the stability and reliability of power supply, use advanced algorithms for state conversion and cost analysis, monitor equipment status in real time and make reasonable evaluations, identify unreasonable operating costs, ensure the reasonable allocation and use of resources, reduce equipment maintenance costs and unnecessary power waste, and achieve Predictions and simulations based on historical data, through accurate prediction and analysis of electricity demand, can provide a scientific basis for the dispatching decisions of power plants, ensure that electricity demand can be met during peak periods, and effectively adjust equipment operation during off-peak periods to improve resource utilization. Through state quantification and frequency statistics, it can record the operating state changes of equipment in detail and generate a clear state transfer matrix, providing accurate data support for subsequent dispatch optimization and decision-making, thereby improving the intelligence and automation level of power plant management, and providing a flexible strategy adjustment mechanism for power dispatch. Through dynamic optimization and adjustment of equipment combinations, it can respond quickly to real-time changes in electricity demand, ensure the efficiency and economy of power supply, and promote the integration and development of renewable energy.

[0164] 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.

[0165] 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. A power control method based on a power characteristic matrix, characterized in that: The following steps are involved: Step S1: Obtaining distributed power plant equipment data; Replace outliers in distributed power plant equipment data to obtain complete equipment data; Screen the complete equipment data for standard operating parameters and generate standard equipment operating parameters; Step S2: Perform equipment unit simulation processing on the standard equipment operating parameters to generate simulated power plant equipment units; perform combined power generation simulation on the simulated power plant equipment units to obtain multiple combined power generation simulation data; Step S3: Obtain historical power output data; Conducting power demand analysis on historical power output data to obtain historical power demand data; According to the historical power demand data, the power demand is predicted for the standard equipment operating parameters to generate the predicted power output data; the demand peak and valley analysis is performed on the predicted power output data to obtain the power demand peak and valley data; Step S4: Based on the predicted required power output data, multiple combined power generation simulation data are strength-adaptively screened to obtain a power generation strength adaptation combination unit; based on the power demand peak and valley data, the power generation strength adaptation combination unit is operated periodically adjusted to generate adaptation equipment combination scheduling data; Step S5: Generate a distributed device dispatching instruction according to the adaptive device combination dispatching data; use the distributed device dispatching instruction to dispatch the equipment operation of the virtual power plant to realize the intelligent power control method.

2. The power control method based on the power characteristic matrix according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtain distributed power plant equipment data; perform abnormal value interval detection on the distributed power plant equipment data to obtain abnormal value intervals of power plant equipment; Step S12: removing abnormal values ​​from the abnormal value interval of the power plant equipment to generate cleaning power plant equipment data; Step S13: performing linear interpolation of abnormal intervals on the cleaning power plant equipment data to obtain complete equipment data; Step S14: performing equipment operation simulation on the complete equipment data to obtain a simulation operation parameter set; Step S15: clustering the simulation operation parameter set to obtain a clustered operation parameter set; Step S16: Standardize the clustered operating parameter set to generate standard equipment operating parameters.

3. The power control method based on the power characteristic matrix according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: extracting features of standard equipment operating parameters to obtain equipment characteristic parameters; performing correlation analysis on the equipment characteristic parameters to generate a parameter correlation matrix; Step S22: performing equipment unit operating condition analysis on the equipment characteristic parameters based on the parameter association matrix to obtain an operating condition parameter set; performing operation trajectory calculation on the operating condition parameter set to obtain equipment operation trajectory data; Step S23: performing equipment simulation processing on equipment characteristic parameters according to equipment operation trajectory data to generate a simulated power plant equipment unit; Step S24: simulating the power generation operation of the simulated power plant equipment unit to obtain simulated equipment working data; Step S25: Based on the simulated equipment working data, feasible combined power generation simulation is performed on the simulated power plant equipment units to obtain multiple combined power generation simulation data.

4. The power control method based on the power characteristic matrix according to claim 3 is characterized in that: Step S25 includes the following steps: Step S251: classify the simulated device working data into types to obtain a device classification data set; perform power characteristic analysis on the device classification data set to obtain a power characteristic matrix; Step S252: performing independent operation simulation on the simulated power plant equipment units according to the power characteristic matrix to generate equipment independent operation data; performing permutation, combination and grouping on the simulated power plant equipment units to generate multiple groups of permutation equipment units; Step S253: performing combined operation simulation on the arranged equipment units according to the power characteristic matrix to generate multiple sets of equipment combined operation data; performing optimized combination screening on the equipment combined operation data based on the equipment independent operation data to obtain feasible equipment combined operation data; Step S254: Based on the feasible equipment combination working data, a combined power generation simulation is performed on the simulated power plant equipment units to obtain a variety of combined power generation simulation data.

5. The power control method based on the power characteristic matrix according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: acquiring historical power output data; performing frequency domain transformation processing on the historical power output data to obtain a historical power feature sequence; performing power output pattern recognition on the historical power feature sequence to generate a historical power output pattern; Step S32: Analyze the power demand of the historical power output mode to obtain the historical power demand data; calculate the current power demand of the standard equipment operating parameters according to the historical power demand data to obtain the power demand data required by the current equipment; Step S33: predicting the required power output of the standard equipment operating parameters according to the power generation data required by the current equipment, and generating predicted required power output data; Step S34: performing curve fitting on the predicted required power output data to obtain the predicted required power output curve; performing curve extreme point detection on the predicted required power output curve to obtain power demand peak and valley data.

6. The power control method based on the power characteristic matrix according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing power superposition calculation on multiple combined power generation simulation data to generate combined power data; performing stable efficiency calculation on the combined power data to generate a combined efficiency index; Step S42: Based on the predicted required power output data, the combined efficiency index is screened for power generation intensity adaptation to obtain an efficiency adaptation combination; and according to the efficiency adaptation combination, a plurality of combined power generation simulation data are matched with equipment combinations to obtain a power generation intensity adaptation combination unit; Step S43: Associatively link the power demand peak and valley data and the power generation intensity adaptation combination unit to obtain a peak and valley adaptation device unit table; Step S44: adjusting the operation cycle of the power generation intensity adaptation combination unit based on the peak-valley adaptation device unit table to generate adaptation device combination scheduling data.

7. The power control method based on the power characteristic matrix according to claim 6 is characterized in that: Step S44 includes the following steps: Step S441: performing time series decomposition on the peak-valley adaptation equipment unit table to obtain a basic cycle sequence; performing principal component extraction on the basic cycle sequence to obtain a core cycle pattern; Step S442: divide the core cycle mode into time windows to obtain scheduling time segments; perform device state mapping on the power generation intensity adaptation combination unit according to the scheduling time segments to generate a device state sequence; Step S443: Calculate the state transition cost of the device state sequence to obtain a state transition matrix; Step S444: perform the shortest step length detection on the state transition matrix to generate the shortest path data; perform the equipment operation cycle adjustment on the shortest path data to generate the adaptive equipment combination scheduling data.

8. The power control method based on the power characteristic matrix according to claim 7 is characterized in that: Step S443 includes the following steps: Performing state quantization processing on the device state sequence to obtain a quantized state sequence; Perform transfer frequency statistics on the quantized state sequence to generate a state transfer frequency table; Based on the preset state transition weight data, the state transition frequency table is cost calculated to obtain the basic state transition cost; the basic state transition cost is matrix constructed to generate the state transition cost matrix; Identify unreasonable costs on the state transfer cost matrix and obtain unreasonable conversion costs; The cost branches of the state transfer cost matrix are cleaned up according to the unreasonable conversion costs to generate the state transition matrix.

9. A power control system based on a power characteristic matrix, characterized in that: For executing the power control method based on the power characteristic matrix as claimed in claim 1, the power control system based on the power characteristic matrix comprises: The data preprocessing module is used to obtain the distributed power plant equipment data; replace the abnormal values ​​of the distributed power plant equipment data to obtain the complete equipment data; screen the complete equipment data for standard operating parameters to generate standard equipment operating parameters; The combined simulation module is used to simulate the equipment unit of the standard equipment operating parameters to generate simulated power plant equipment units; to simulate the combined power generation of the simulated power plant equipment units to obtain a variety of combined power generation simulation data; The power generation and demand analysis module is used to obtain historical power output data; perform power demand analysis on the historical power output data to obtain historical power demand data; perform power generation demand forecasting on the standard equipment operating parameters based on the historical power demand data to generate the power output data required for forecasting; perform demand peak and valley analysis on the power output data required for forecasting to obtain power demand peak and valley data; The scheduling analysis module is used to perform intensity adaptation screening on multiple combined power generation simulation data based on the predicted required power output data to obtain a power generation intensity adaptation combination unit; adjust the operation cycle of the power generation intensity adaptation combination unit based on the power demand peak and valley data to generate adaptive equipment combination scheduling data; The operation scheduling module is used to generate distributed equipment scheduling instructions based on the combined scheduling data of the adapted equipment; and use the distributed equipment scheduling instructions to perform equipment operation scheduling on the virtual power plant to realize an intelligent power control method.

Images