Electrical real-time modeling method based on source network load storage mode and related system

Abstract

The invention belongs to the field of electrical data modeling, and discloses an electrical real-time modeling method based on a source network load storage mode and a related system, and the method can effectively improve the data quality through obtaining the real-time data of power generation equipment, and carrying out the preprocessing and cleaning of the real-time data, thereby guaranteeing the accuracy of subsequent analysis. According to the method, errors are found and corrected in time by analyzing the preprocessed data, and model deviation caused by inaccurate data can be reduced. According to the method, global and local parameters are respectively optimized by using an external particle swarm algorithm and an internal genetic algorithm, and a data space can be more comprehensively explored and utilized, so that the prediction precision and reliability of the model are improved. When an accident occurs, the accident scene is reconstructed according to the accident data, a fault mechanism can be better understood, and a basis is provided for subsequent fault removal and system improvement.

Description

Technical Field

[0001] The present invention belongs to the field of electrical data modeling, and in particular relates to an electrical real-time modeling method based on a source-grid-load-storage mode and a related system. Background Art

[0002] The new power system dominated by a high proportion of renewable energy has brought profound impacts to the power grid. The form of the power grid has evolved. The traditional simulation calculation driven by mechanism models has poor real-time and interactivity, and cannot characterize the characteristics of the system, making it difficult to meet the needs of the digital transformation of the power grid.

[0003] In view of the complexity of modeling and limited computing power, traditional power system simulation rarely considers the transient processes of key components such as IGBT at multiple time scales, and usually ignores the equipment communication delay link, measurement link, and embedded operating system scheduling link. At the same time, the combined influence of electrothermal effects and other multi-physical field factors is not considered, and there is little research on the simulation of comprehensive characteristics of the entire link from system to equipment and even devices. In engineering applications, such full-link simulation can support the realization of refined system full-condition characteristic analysis, help device selection and controller design, and help to troubleshoot potential fault occurrence and propagation risks in various links of flexible DC or new energy power generation grid-connected systems, or conduct comprehensive diagnosis of existing faults. Therefore, it is necessary to study systematic full-link simulation technology in combination with multiple time scales, multiple influencing links, and multiple physical field factors.

[0004] 1. Traditional simulation updates parameters offline, and the static results of the simulation cannot reflect the state of the power system in real time. The power system is a multi-scale system with complex dynamic characteristics. Traditional simulation can only depict the dynamic process at a certain time and space scale, and the update parameters are updated offline, which has large inherent errors. Lagging and isolated data will also result in low simulation efficiency and low data utilization.

[0005] 2. Traditional simulation only contains some physical laws and cannot describe the random processes in the power system. For example, relay protection is based on some physical laws followed by the object, and it is difficult to fully describe the protected object; the physical mechanisms of circuit breaker switching process and nuclear reactor safety analysis are unclear, and traditional simulation cannot accurately describe the random process of the object and it is difficult to quantify the uncertainty of the system.

[0006] 3. Traditional simulation does not include situational awareness of the power system, making it difficult to predict the state of the power system. Traditional static simulation and dynamic simulation describe the universal changes of the system or the significant dynamic changes of the system within a certain period of time. They cannot fully describe the complete changes of the entire cycle, let alone complete the perception of the current state. At present, online simulation of power systems mainly focuses on the speed of online analysis and calculation, and pays insufficient attention to the future operation trend of the power system.

[0007] 4. Low utilization rate of traditional simulation data. The characteristic of simulation is to use mathematical language to describe some consensus cognition, and use different solution methods under different working conditions to obtain the specific representation of the physical phenomenon of the system under specific conditions. This specific representation is the simulation result, which is mostly presented in various numerical (data) forms. This determines that it can only reflect the evolution law of a certain period of time in the whole life cycle, so it cannot make full use of the data. Summary of the invention

[0008] The purpose of the present invention is to overcome the shortcomings of the above method, such as low data utilization rate, difficulty in quantifying the system, and difficulty in predicting operating trends, and to provide an electrical real-time modeling method and related system based on the source-grid-load-storage mode.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides an electrical real-time modeling method based on a source-grid-load-storage mode, comprising the following steps: Obtain real-time data of power generation equipment; Preprocess the received data to remove invalid data and noise; Analyze the preprocessed data and generate simulation data after error detection and data integration; The global parameters of the simulation data are optimized by the external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; the local parameters of the simulation data are optimized by the internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and the optimized simulation data are obtained by combining the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm; Analyze the optimized simulation data. If the data includes power generation equipment accident data, reconstruct the accident scenario based on the power generation equipment accident data; otherwise, re-analyze the simulation data; According to the accident scenario, the grid structure and component data of the power generation equipment are adjusted.

[0010] A further improvement of the present invention is that when preprocessing the received data, the specific method is as follows: The received data is classified according to different power generation equipment, outliers and noise are removed from each type of data, and missing values ​​are filled to obtain first data; The first data is subjected to standardization and normalization processing, and then encoded to generate second data in a required format, and each type of second data is pre-processed data.

[0011] A further improvement of the present invention is that the pre-processed data is analyzed, and after error detection and data integration, the specific method of generating simulation data is as follows: Perform time series analysis on the preprocessed data to filter out mutation data; The data with mutations filtered out from all classes are integrated to obtain a unified data set as simulation data.

[0012] A further improvement of the present invention is that the specific method for optimizing the global parameters of simulation data by using an external particle swarm algorithm is as follows: Obtain the global parameter set that needs to be optimized in the simulation data, and set the parameters of the particle swarm algorithm according to the global parameter set; For each particle in the particle swarm algorithm, the trust region reflection method is used to evaluate it and generate solutions and fitness values; According to the fitness value, the individual optimal solution and the global optimal solution are updated. If the individual optimal solution and the global optimal solution meet the requirements, the global optimal solution and its objective function value are output; otherwise, the speed and position of the particles in the parameters of the particle swarm algorithm are updated, and each particle in the particle swarm algorithm is re-evaluated using the trust region reflection method until the individual optimal solution and the global optimal solution meet the requirements, and the data optimized by the external particle swarm algorithm is obtained.

[0013] A further improvement of the present invention is that the specific method for optimizing the local parameters of the simulation data by the internal genetic algorithm is as follows: Obtaining a local parameter set that needs to be optimized in the simulation data, and setting the parameters of the genetic algorithm according to the local parameter set; Evaluate the deviation of the local parameter set from the actual data; Simulate each parameter in the evaluation local parameter set, calculate the fitness value of each parameter, and select parameters whose fitness values ​​are within a preset range; Perform crossover and mutation processing on the selected parameters to generate new offspring data; Repeated evaluation, selection, crossover and mutation processing are performed on the offspring data until the current parameter reaches the maximum number of iterations or the fitness converges, and the data optimized by the internal genetic algorithm is obtained.

[0014] A further improvement of the present invention is that, if the data includes power generation equipment accident data, the specific method for reconstructing the accident scene based on the power generation equipment accident data is as follows: Obtaining power generation equipment accident data from the data; Pre-process the power generation equipment accident data and remove outliers; According to the characteristics of power generation equipment, structure and equipment, a mathematical model of the power grid is established, and the model parameters are set according to the real-time data of the power generation equipment; The preprocessed power generation equipment accident data is input into the mathematical model of the power grid to obtain the reconstructed accident scenario.

[0015] In a second aspect, the present invention provides an electrical real-time modeling system based on a source-grid-load-storage mode, comprising: A data acquisition module, used to acquire real-time data of power generation equipment; A preprocessing module is used to preprocess the received data and remove invalid data and noise; The detection and integration module is used to analyze the preprocessed data and generate simulation data after error detection and data integration; The optimization module is used to optimize the global parameters of the simulation data by using an external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; optimize the local parameters of the simulation data by using an internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and combine the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm to obtain the optimized simulation data; The accident scene reconstruction module is used to analyze the optimized simulation data. If the data includes power generation equipment accident data, the accident scene is reconstructed based on the power generation equipment accident data; otherwise, the simulation data is analyzed again; The data adjustment module is used to adjust the grid structure and component data of the power generation equipment according to the accident scenario.

[0016] In a third aspect, the present invention provides an electrical real-time modeling system based on a source-grid-load-storage mode, comprising: A data receiving module is used to obtain real-time data of power generation equipment; The data processing module is used to pre-process the received data and remove invalid data and noise; analyze the pre-processed data and generate simulation data through error detection and data integration; optimize the global parameters of the simulation data through the external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; optimize the local parameters of the simulation data through the internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and combine the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm to obtain the optimized simulation data; The accident inversion module is used to analyze the optimized simulation data. If the data includes power generation equipment accident data, the accident scene is reconstructed based on the power generation equipment accident data; otherwise, the simulation data is analyzed again; The collaborative control module is used to adjust the grid structure and component data of the power generation equipment according to the accident scenario.

[0017] In a fourth aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an electrical real-time modeling method based on a source-grid-load-storage mode when executing the computer program.

[0018] In a fifth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of a method for real-time electrical modeling based on a source-grid-load-storage mode are implemented.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention can effectively improve the data quality by acquiring the real-time data of the power generation equipment and preprocessing and cleaning it, thereby ensuring the accuracy of subsequent analysis. The present invention can reduce the model deviation caused by inaccurate data by analyzing the preprocessed data, timely discovering and correcting errors. The present invention uses an external particle swarm algorithm and an internal genetic algorithm to optimize global and local parameters respectively, and can more comprehensively explore and utilize the data space, thereby improving the prediction accuracy and reliability of the model. When an accident occurs, the present invention reconstructs the accident scene according to the accident data, which can better understand the fault mechanism and provide a basis for subsequent troubleshooting and system improvement. The present invention adjusts the grid structure and component data according to the accident scene, which can quickly respond to and adapt to system changes and improve the stability and reliability of the power system. The present invention provides decision makers with more accurate references through optimized and reconstructed simulation data, which helps to formulate more effective operation and maintenance strategies. The present invention can improve the system's ability to respond to emergencies and uncertain factors and enhance the resilience of the overall system through real-time modeling and optimization. In summary, the present invention can not only improve the performance of the power system, but also provide important data support for future technological development. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of Example 1; Figure 2 is a system diagram of Example 2; Figure 3 is a system diagram of Example 3; Figure 4 This is a system diagram of Example 9. DETAILED DESCRIPTION

[0021] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0022] Embodiment 1: See also Figure 1 , the electrical real-time modeling method based on the source-grid-load-storage mode includes the following steps: S1, obtain real-time data of power generation equipment.

[0023] S2, preprocesses the received data to remove invalid data and noise.

[0024] S3, analyzes the preprocessed data, generates simulation data after error detection and data integration.

[0025] S4, optimizes the global parameters of the simulation data through the external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; optimizes the local parameters of the simulation data through the internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and combines the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm to obtain the optimized simulation data.

[0026] S5, analyzing the optimized simulation data, if the data includes power generation equipment accident data, reconstructing the accident scenario according to the power generation equipment accident data; otherwise, re-analyzing the simulation data.

[0027] S6, adjust the grid structure and component data of the power generation equipment according to the accident scenario.

[0028] Embodiment 2: See also Figure 2 , an electrical real-time modeling system based on source-grid-load-storage mode, including: A data acquisition module, used to acquire real-time data of power generation equipment; A preprocessing module is used to preprocess the received data and remove invalid data and noise; The detection and integration module is used to analyze the preprocessed data and generate simulation data after error detection and data integration; The optimization module is used to optimize the global parameters of the simulation data by using an external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; optimize the local parameters of the simulation data by using an internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and combine the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm to obtain the optimized simulation data; The accident scene reconstruction module is used to analyze the optimized simulation data. If the data includes power generation equipment accident data, the accident scene is reconstructed based on the power generation equipment accident data; otherwise, the simulation data is analyzed again; The data adjustment module is used to adjust the grid structure and component data of the power generation equipment according to the accident scenario.

[0029] Embodiment 3: See also Figure 3 , an electrical real-time modeling system based on source-grid-load-storage mode, including: The simulation master station is used to receive data from the simulation substation, coordinate the simulation substation to perform simulation processing, and perform functions such as accident inversion based on the received data. The simulation master station is a server and can be deployed in a data center or a dispatch center.

[0030] The simulation master station includes: The data receiving module is used to receive data from each simulation substation.

[0031] The data processing module is used to clean, transform and integrate the received data.

[0032] The real-time monitoring module is used to provide a graphical interface to display the real-time status of the power grid.

[0033] The accident inversion module is used to reconstruct accident scenarios based on historical data and analyze the causes of accidents.

[0034] The collaborative control module is used to adjust the grid structure and component data according to real-time data to achieve real-time optimization and adjustment.

[0035] The simulation substations are distributed in different locations of the network, such as wind farms, photovoltaic power stations or energy storage stations. They can be used as a distributed simulation server alone, or they can be connected to the main station to form part of the large power grid simulation, responsible for the collection, processing and uploading of local data.

[0036] The simulation substation includes the power generation unit intelligent data collection terminal, the station intelligent data collection terminal and the substation server.

[0037] The power generation unit intelligent data acquisition terminal is used to collect real-time data of power generation equipment. The power generation unit intelligent data acquisition terminal supports multiple communication interfaces (such as RS-485, Ethernet) to connect to different sensors and devices.

[0038] The intelligent data collection terminal of the site is used to collect on-site data of the wind farm, photovoltaic power station or energy storage station to reduce the amount of data transmission. The intelligent data collection terminal of the site is set in the wind farm, photovoltaic power station or energy storage station.

[0039] The substation server is used to store and manage local data, perform preliminary data analysis and processing tasks, send data to the simulation master station through 104 protocol or FTP, and independently simulate the site as a simulation server.

[0040] This embodiment uses IEC 60870-5-104 (104 protocol) and FTP protocol for data communication. The 104 protocol is used for real-time data exchange, such as telemetry and telesignaling data, and FTP is used for non-real-time or batch data transmission, such as historical data archiving.

[0041] Embodiment 4: When preprocessing the received data, the specific method is as follows: The received data is classified according to different power generation equipment, and outliers and noise are removed from each type of data, and missing values ​​are filled to obtain first data; the first data is standardized and normalized, and then encoded to generate second data in the required format. The second data of each type is preprocessed data.

[0042] In this embodiment, classification processing can ensure that the data characteristics of each power generation equipment are fully understood, thereby improving the consistency and reliability of the overall data set. Removing outliers and noise makes the data clearer, reduces the adverse effects on subsequent analysis and modeling, and improves the accuracy of the model. By filling in missing values, the integrity of the data set is ensured, so that the model can make full use of all available information and avoid deviations caused by missing data. These processing steps make the data on the same scale, facilitate comparison between different data types, and promote the convergence speed and effect of the algorithm.

[0043] Embodiment 5: The specific method of analyzing the preprocessed data, generating simulation data through error detection and data integration is as follows: The preprocessed data is subjected to time series analysis to filter out mutation data; the data that has been filtered out of mutations in all classes are integrated to obtain a unified data set as simulation data.

[0044] This embodiment screens mutation data to ensure that the dataset used reflects real and stable system behavior, thereby enhancing the reliability of model prediction. Time series analysis helps identify trends and periodicity in the data, providing more comprehensive background information for the model and improving prediction accuracy. Integrating the screened data from all classes to form a unified dataset reduces the complexity of data processing and makes subsequent analysis more efficient.

[0045] Embodiment 6: The specific method of optimizing the global parameters of simulation data through external particle swarm algorithm is as follows: Obtain the global parameter set that needs to be optimized in the simulation data, and set the parameters of the particle swarm algorithm according to the global parameter set; For each particle in the particle swarm algorithm, the trust region reflection method is used to evaluate it and generate solutions and fitness values; According to the fitness value, the individual optimal solution and the global optimal solution are updated. If the individual optimal solution and the global optimal solution meet the requirements, the global optimal solution and its objective function value are output; otherwise, the speed and position of the particles in the parameters of the particle swarm algorithm are updated, and each particle in the particle swarm algorithm is re-evaluated using the trust region reflection method until the individual optimal solution and the global optimal solution meet the requirements, and the data optimized by the external particle swarm algorithm is obtained.

[0046] Specific: Step 1: Initialize parameters: Determine the set of global parameters that need correction.

[0047] Set the parameters of the particle swarm algorithm, such as the number of particles, maximum number of iterations, inertia weight, acceleration factor, etc.

[0048] Set the global optimal solution and the individual optimal solution.

[0049] Set parameter judgment threshold .

[0050] The initial population is randomly generated, where the particles are denoted as , number of iterations .

[0051] Step 2: Particle evaluation and update: For each particle , using it as the initial value and solving it using the trust region reflection method, we get a solution and its fitness value .

[0052] Update Particles for .

[0053] like , then go to step five.

[0054] Step 3: Update individual optimal and global optimal: Update individual optimum and global optimum according to particle fitness.

[0055] Step 4: Update particle speed and position: Update the speed and position of each particle. , go to step 2.

[0056] Step 5: Output the global optimal solution: Output the global optimal solution and its objective function value.

[0057] Embodiment 7: The specific method of optimizing the local parameters of simulation data through the internal genetic algorithm is as follows: Obtaining a local parameter set that needs to be optimized in the simulation data, and setting the parameters of the genetic algorithm according to the local parameter set; Evaluate the deviation of the local parameter set from the actual data; Simulate each parameter in the evaluation local parameter set, calculate the fitness value of each parameter, and select parameters whose fitness values ​​are within a preset range; Perform crossover and mutation processing on the selected parameters to generate new offspring data; Repeated evaluation, selection, crossover and mutation processing are performed on the offspring data until the current parameter reaches the maximum number of iterations or the fitness converges, and the data optimized by the internal genetic algorithm is obtained.

[0058] Specific: Step 1: Initialize parameters: Determine the set of local parameters that need to be corrected.

[0059] Set the parameters of the genetic algorithm, such as population size, crossover probability, mutation probability, maximum number of iterations, etc.

[0060] Step 2: Define the fitness function: Select an appropriate fitness function to evaluate the quality of each set of local parameters.

[0061] Error functions, such as mean square error (MSE) or root mean square error (RMSE), are usually used to measure the difference between local simulation results and actual data.

[0062] Step 3: Population initialization: Initial local parameter values ​​are randomly generated for each individual.

[0063] Step 4: Individual assessment and selection: The local parameter settings corresponding to each individual are simulated to obtain local simulation results.

[0064] Calculate the fitness value.

[0065] Use roulette wheel selection or other selection strategies to pick better performing individuals as parents.

[0066] Step 5: Genetic operation: Crossover operation: Randomly select two individuals from the parent generation for crossover to produce new offspring.

[0067] Mutation operation: mutate the newly generated offspring to increase the diversity of the population.

[0068] Step 6: Iterative optimization: The process of individual evaluation, selection, and genetic operation is repeated until the maximum number of iterations is reached or the fitness value converges.

[0069] Step 7, result output: Select the final optimal local parameter set.

[0070] Embodiment 8: If the data includes power generation equipment accident data, the specific method for reconstructing the accident scene based on the power generation equipment accident data is as follows: Obtain the power generation equipment accident data in the data; pre-process the power generation equipment accident data and eliminate outliers; establish a mathematical model of the power grid based on the power generation equipment and structure and equipment characteristics, and set model parameters based on the real-time data of the power generation equipment; input the pre-processed power generation equipment accident data into the mathematical model of the power grid to obtain a reconstructed accident scenario.

[0071] This embodiment ensures the quality of accident data by preprocessing and removing outliers, making the reconstructed accident scene closer to the actual situation. Using real-time data to set model parameters can improve the adaptability of the model to specific accidents, thereby enhancing the accuracy of prediction and simulation. The established mathematical model helps analyze the causes and effects of accidents and provides important clues for subsequent troubleshooting. Reconstructing accident scenes can help decision makers quickly understand the impact of accidents and provide a scientific basis for formulating emergency measures and recovery plans.

[0072] Embodiment 9: See also Figure 4 As shown, the present invention also provides an electronic device 100 for an electrical real-time modeling method based on a source-grid-load-storage mode; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0073] The memory 101 can be used to store the computer program 103, and the processor 102 implements the steps of the electrical real-time modeling method based on the source-grid-load-storage mode described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0074] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0075] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a real-time electrical modeling method based on a source-grid-load-storage mode, and the processor 102 can execute the plurality of instructions to implement: Obtain real-time data of power generation equipment; Preprocess the received data to remove invalid data and noise; Analyze the preprocessed data and generate simulation data after error detection and data integration; The global parameters of the simulation data are optimized by the external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; the local parameters of the simulation data are optimized by the internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and the optimized simulation data are obtained by combining the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm; Analyze the optimized simulation data. If the data includes power generation equipment accident data, reconstruct the accident scenario based on the power generation equipment accident data; otherwise, re-analyze the simulation data; According to the accident scenario, the grid structure and component data of the power generation equipment are adjusted.

[0076] Embodiment 10: If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0077] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. The electrical real-time modeling method based on the source-grid-load-storage mode is characterized by: The following steps are involved: Obtain real-time data of power generation equipment; Preprocess the received data to remove invalid data and noise; Analyze the preprocessed data and generate simulation data after error detection and data integration; The global parameters of the simulation data are optimized by the external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; the local parameters of the simulation data are optimized by the internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and the optimized simulation data are obtained by combining the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm; Analyze the optimized simulation data, and if the data includes power generation equipment accident data, reconstruct the accident scenario based on the power generation equipment accident data; Otherwise, reanalyze the simulation data; According to the accident scenario, the grid structure and component data of the power generation equipment are adjusted.

2. The electrical real-time modeling method based on source-grid-load-storage mode according to claim 1 is characterized in that: When preprocessing the received data, the specific method is as follows: The received data is classified according to different power generation equipment, outliers and noise are removed from each type of data, and missing values ​​are filled to obtain first data; The first data is subjected to standardization and normalization processing, and then encoded to generate second data in a required format, and each type of second data is pre-processed data.

3. The electrical real-time modeling method based on source-grid-load-storage mode according to claim 1 is characterized in that: The specific method of analyzing the preprocessed data, generating simulation data through error detection and data integration is as follows: Perform time series analysis on the preprocessed data to filter out mutation data; The data with mutations filtered out from all classes are integrated to obtain a unified data set as simulation data.

4. The electrical real-time modeling method based on source-grid-load-storage mode according to claim 1 is characterized in that: The specific method of optimizing the global parameters of simulation data through external particle swarm algorithm is as follows: Obtain the global parameter set that needs to be optimized in the simulation data, and set the parameters of the particle swarm algorithm according to the global parameter set; For each particle in the particle swarm algorithm, the trust region reflection method is used to evaluate it and generate solutions and fitness values; Update the individual optimal solution and the global optimal solution according to the fitness value. If the individual optimal solution and the global optimal solution meet the requirements, output the global optimal solution and its objective function value. Otherwise, update the speed and position of the particles in the parameters of the particle swarm algorithm, and re-evaluate each particle in the particle swarm algorithm using the trust region reflection method until the individual optimal solution and the global optimal solution meet the requirements, and obtain the data optimized by the external particle swarm algorithm.

5. The electrical real-time modeling method based on source-grid-load-storage mode according to claim 1 is characterized in that: The specific method of optimizing the local parameters of simulation data through the internal genetic algorithm is as follows: Obtaining a local parameter set that needs to be optimized in the simulation data, and setting the parameters of the genetic algorithm according to the local parameter set; Evaluate the deviation of the local parameter set from the actual data; Simulate each parameter in the evaluation local parameter set, calculate the fitness value of each parameter, and select parameters whose fitness values ​​are within a preset range; Perform crossover and mutation processing on the selected parameters to generate new offspring data; Repeated evaluation, selection, crossover and mutation processing are performed on the offspring data until the current parameter reaches the maximum number of iterations or the fitness converges, and the data optimized by the internal genetic algorithm is obtained.

6. The electrical real-time modeling method based on source-grid-load-storage mode according to claim 1 is characterized in that: If the data includes power generation equipment accident data, the specific method for reconstructing the accident scene based on the power generation equipment accident data is as follows: Obtaining power generation equipment accident data from the data; Pre-process the power generation equipment accident data and remove outliers; According to the characteristics of power generation equipment, structure and equipment, a mathematical model of the power grid is established, and the model parameters are set according to the real-time data of the power generation equipment; The preprocessed power generation equipment accident data is input into the mathematical model of the power grid to obtain the reconstructed accident scenario.

7. The electrical real-time modeling system based on the source-grid-load-storage mode is characterized by: include: A data acquisition module, used to acquire real-time data of power generation equipment; A preprocessing module is used to preprocess the received data and remove invalid data and noise; The detection and integration module is used to analyze the preprocessed data and generate simulation data after error detection and data integration; The optimization module is used to optimize the global parameters of the simulation data by using an external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; optimize the local parameters of the simulation data by using an internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and combine the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm to obtain the optimized simulation data; The accident scene reconstruction module is used to analyze the optimized simulation data. If the data includes power generation equipment accident data, the accident scene is reconstructed based on the power generation equipment accident data; otherwise, the simulation data is analyzed again; The data adjustment module is used to adjust the grid structure and component data of the power generation equipment according to the accident scenario.

8. The electrical real-time modeling system based on the source-grid-load-storage mode is characterized by: include: A data receiving module is used to obtain real-time data of power generation equipment; A data processing module is used to pre-process the received data and remove invalid data and noise; Analyze the preprocessed data, generate simulation data after error detection and data integration; optimize the global parameters of the simulation data by using the external particle swarm algorithm to obtain the data optimized by the external particle swarm algorithm; optimize the local parameters of the simulation data by using the internal genetic algorithm to obtain the data optimized by the internal genetic algorithm, and combine the data optimized by the external particle swarm algorithm and the data optimized by the internal genetic algorithm to obtain the optimized simulation data; The accident inversion module is used to analyze the optimized simulation data. If the data includes power generation equipment accident data, the accident scene is reconstructed based on the power generation equipment accident data; otherwise, the simulation data is analyzed again; The collaborative control module is used to adjust the grid structure and component data of the power generation equipment according to the accident scenario.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the electrical real-time modeling method based on the source-grid-load-storage mode described in any one of claims 1 to 6 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the electrical real-time modeling method based on the source-grid-load-storage mode according to any one of claims 1 to 6 are implemented.

Images