300 results about "Power system simulation" patented technology

The invention discloses a medium and low voltage real type power distribution network defect simulation system and a test method thereof, and relates to the technical field of power system fault diagnosis and recovery, and the method comprises the steps: deploying a sensor to collect power distribution network operation data, carrying out the preprocessing, integrating a power distribution network data set, extracting a power distribution network fault feature vector from the power distribution network data set through FFT conversion, and carrying out the fault diagnosis and recovery; the method comprises the following steps: constructing a fault diagnosis model by using a support vector machine (SVM) based on a power distribution network fault feature vector, establishing a simulation model of a medium and low voltage power distribution network by using power system simulation software PSCAD, simulating a power distribution network fault in the simulation model, diagnosing the fault in the simulation model by using the fault diagnosis model, and formulating and implementing a recovery strategy according to a diagnosis result. Evaluating the effect of the recovery strategy, adjusting the recovery strategy according to the evaluation result, repeatedly testing in the simulation environment until the optimal recovery strategy is found, applying the optimal recovery strategy to the actual power distribution network, and continuously monitoring and improving the performance of the actual power distribution network.

The invention provides an electric power system transaction simulation method based on multi-agent agency, and belongs to the technical field of electric power system simulation, and the method comprises the steps: collecting the historical operation data of an electric power system, constructing a multi-agent system comprising a power generation agent, a flexible load agent and an electricity selling agent, and carrying out the Monte Carlo simulation and scene generation. According to the method, a deep reinforcement learning algorithm is adopted, a revenue function and a decision model of each agent are defined, market clearing calculation is executed, and transaction simulation is performed by constructing a verification scene library. The system can evaluate agent strategies, calculate market key indexes and feed market information back to agents, intelligence and dynamic optimization of electricity transaction decision are achieved, and the operation efficiency and transaction accuracy of the electricity market are effectively improved. The method provided by the invention solves the technical problem in the prior art that the interaction and learning mechanism between market participants are not fully considered, so that the simulation result and the actual market performance have large deviation.

The invention belongs to the technical field of power system simulation application, and particularly relates to a power system simulation optimization method based on data driving. Based on a data-driven dynamic adaptive space-time segmentation and cooperation model, a fast-varying electromagnetic transient process is mapped to a quantum processor, a slow-varying electromechanical transient process is reserved in a classical computer, a power grid node voltage is coded into quantum bit amplitude, a power grid is dynamically equivalent to quantum Hamiltonian, and a quantum Hamiltonian is obtained. And decoupling the quantum domain of the fast-changing electromagnetic transient state and the classical domain of the slow-changing electromechanical dynamic state to realize self-adaptive balance simulation precision and efficiency. Quantum calculation sparse codes and dynamic error correction are constructed, non-uniform code distance distribution is achieved, cross-scale data transmission errors are reduced, high-frequency harmonic distortion is avoided, high fault-tolerant simulation is achieved under limited quantum resources, code distances are dynamically adjusted through reinforcement learning of a DDPG strategy, noise fluctuation and power grid working condition changes are responded in real time, and resources and fault-tolerant balance are optimized.

The invention discloses an electric power system simulation scene modeling method based on big data, which comprises the following steps: collecting preset scene data and monitoring data of an electric power system, and preprocessing the preset scene data and related data; performing power distribution network aggregation on the monitoring data to obtain equivalent load node data, and performing high-dimensional classification on the equivalent load node data according to the preset scene data to obtain node classification; the node classification comprises a normal scene and an extreme scene; performing time sequence causal feature extraction on the equivalent load node data according to the node classification to obtain time sequence causal features, and constructing a power system simulation scene model based on a Bayesian network according to the time sequence causal features; and performing uncertainty evaluation on the power system simulation scene model according to a simulation error to obtain uncertainty, performing parameter layered online correction on the power system simulation scene model based on a physical model according to the uncertainty, and outputting a target model.

The invention relates to the technical field of power system simulation, in particular to a new energy power system simulation method, which comprises the following steps: S1, constructing a multi-dimensional information acquisition system, S2, constructing a new energy station model, S3, constructing a power grid control system model, S4, constructing a typical transient scene model, and S5, carrying out optimization solution and model correction. A full-chain model covering a new energy station, a power grid control system and a typical transient scene is constructed, and parameter optimization and a multi-objective decision technology are combined, so that the dynamic characteristics of the new energy power system are accurately simulated.

The invention provides a general electromechanical transient modeling method and system for a network-building converter, and relates to the technical field of electromechanical transient modeling, and the method comprises the steps: simplifying the electromagnetic transient models of network-building converters of different topologies into a grid-connected equivalent circuit of an electromechanical transient time scale; uniformly representing by using an internal potential series reactance model controlled by a power outer ring so as to establish an electromechanical transient general grid-connected interface model of the grid-forming converter; combining mathematical transformation of active power control with a reactive power control mode to form a general power outer loop control model of the network construction type converter; through a method based on internal potential reconstruction, reconstructing a new internal potential satisfying a current limiting constraint, and establishing a general current limiting model suitable for a network construction type electromechanical transient model; according to the method, various topological structures, various power outer loop control and various current limiting strategies can be simulated, flexible use of models in large-scale power system simulation is facilitated, and the complexity of model development and maintenance is reduced.

The invention discloses a load simulation loading system based on an engineering mechanical power system and a control method thereof, and relates to the technical field of mechanical power system simulation. The load simulation loading system comprises an engineering machinery power system, a load loading system, a whole vehicle control unit and an upper computer platform. The engineering machinery power system comprises a first oil tank, a main pump, a pilot pump, a pilot control handle, a signal control valve and a multi-way valve. The load loading system comprises a three-position four-way reversing valve, a proportional overflow valve, a first proportional throttle valve, a second proportional throttle valve, an electromagnetic valve, a third proportional throttle valve and a variable pump, wherein the three-position four-way reversing valve, the proportional overflow valve and the first proportional throttle valve are connected to the multi-way valve, the second proportional throttle valve and the electromagnetic valve are connected to an outlet of the proportional overflow valve, and the third proportional throttle valve is connected between the second proportional throttle valve and the second oil tank. And the three-position four-way reversing valve is constructed to enable an inlet of the proportional overflow valve to be communicated with one of the oil port A and the oil port B of the multi-way valve in a switching manner, and an outlet of the proportional overflow valve to be communicated with the other one of the oil port A and the oil port B in a switching manner.

The invention discloses a full-automatic intelligent simulation method and system for an electric power system driven by a large language model, and belongs to the field of electric power system simulation calculation. The simulation method comprises an offline optimization stage and an online application stage. An off-line optimization stage: acquiring a simulation parameter file of the power system and a modification range of each parameter, and designing a training command pool containing executable and non-executable commands; constructing a command generator and a cue word optimizer based on the large language model to form a generative adversarial framework; system cue word optimization is realized based on the framework, and an optimal cue word is obtained; the online application stage comprises the steps that after a user inputs a natural language command, a large language model recognizes the command and matches an optimal cue word, and the command is input into each parameter modifier to adjust simulation parameters; and verifying whether the parameters are within an allowable range, and if the verification is passed, calling simulation software to carry out power system simulation calculation. The simulation automation level and the intelligent interaction experience of the power system are remarkably improved, and the practical value is high.

The invention discloses an H-infinity intermittent sampling load frequency safety control method for a multi-region power system under spoofing attack, and belongs to the technical field of power system safety control. According to the method, the intermittent control signal is only used in the working interval, the control cost is effectively saved, the limited network bandwidth can be saved through sampling control, and the influence of spoofing attacks on the multi-area power system is effectively resisted through safety control. Firstly, according to the characteristics of intermittent control and sampling control, the influence of spoofing attack is considered at the same time, and a multi-region power system intermittent sampling load frequency safety control dynamic model under the spoofing attack is established. Secondly, a switching Lyapunov functional is provided, meanwhile, under the framework of an LMI, sufficient conditions for existence of an intermittent sampling load frequency safety controller are given, and the conditions guarantee that the index of a multi-area power system is stable and meet the H infinity performance; and finally, verifying the effectiveness of the H-infinity intermittent sampling load frequency safety controller through three-region power system simulation under spoofing attack.

The invention provides an electromagnetic transient simulation method and system for a magnetic valve type current transformer, and relates to the technical field of power system simulation, and the method specifically comprises the steps: collecting electromagnetic, magnetic field, control and environment data, extracting a flux density peak value, a flux density harmonic distortion rate and a current harmonic distortion rate, and constructing monitoring feature data; constructing a data prediction model, dynamically predicting electromagnetic parameters at the next moment, obtaining electromagnetic data, a flux density peak value, a flux density harmonic distortion rate and a current harmonic distortion rate correction value, performing electromagnetic transient simulation through a finite element-circuit coupling model, calculating an amplitude deviation rate and a phase deviation rate, and performing current harmonic distortion rate correction. And generating a running state comprehensive coefficient to judge the running state of the current transformer. Through multi-dimensional data acquisition, time sequence dynamic modeling and coupling simulation, the problems of poor adaptability of fixed parameters, insufficient time sequence characteristic capture and low simulation precision are solved, and the saturation characteristic simulation precision, the transient prediction accuracy and the secondary side current simulation precision are remarkably improved.

The invention discloses a simulation analysis method of a switching transformer overvoltage suppression method, and relates to power system simulation analysis. Comprising the following steps: performing dynamic feature extraction on preprocessed data, considering time sequence characteristics and a system topological structure, and fusing multi-source heterogeneous data; based on an improved long-short-term memory network (LSTM) and wavelet transform, a multi-scale overvoltage prediction model is constructed, and accurate prediction of overvoltage of different time scales is realized; designing a self-adaptive overvoltage suppression strategy generation algorithm according to a prediction result and dynamic characteristics of the system, and considering multiple factors such as system stability, equipment life and economy; and implementing an optimal suppression strategy in a simulation environment, and performing strategy evaluation and iterative optimization according to a simulation result. Through simulation verification and iterative optimization, the applicability and reliability of the method are further improved.

The invention discloses a micro-grid operation scheduling optimization method based on a double-layer adaptive energy management system, and the method proposes a double-layer adaptive energy management system based on a rolling horizon strategy, and achieves the optimization of short-term operation scheduling of a micro-grid. An upper planning layer is adopted for online operation scheduling, profit is maximized, meanwhile, near-real-time scheduling is executed by a lower layer, and correction measures generated by mismatching are predicted by minimizing input parameters. The upper planning layer utilizes the medium-term prediction information, considers market environment income / cost, peak electricity price, static and dynamic controllable loads and a battery energy storage system model, and solves through a mixed integer linear programming problem to obtain an initial scheduling plan of a controllable unit. And the lower scheduling layer operates on a shorter time step, an optimization algorithm is combined with power system simulation, network constraints are considered in real time, the deviation between the scheduling plan and the scheduling plan determined by the upper planning layer is minimized, and a real-time energy management strategy for stable and economic operation of the microgrid is realized.

The invention discloses a frequency response prediction method and system under an anticipated fault of a power system, and the method comprises the steps: generating sample data in different operation modes and fault scenes through the simulation of the power system, carrying out the normalization processing, and dividing the sample data into a training set and a test set; constructing and training a physical guidance neural network model; in an online state, inputting a power grid operation mode and anticipated fault information at a future moment into the trained physical guidance neural network model, predicting a system frequency response curve, and judging whether a frequency instability risk exists or not according to the frequency response curve; according to the method, the physical guidance neural network and the data driving method are combined, the problems that a traditional data driving model is poor in interpretability and depends on a large amount of data are effectively solved, accurate prediction of the power system frequency response under the anticipated fault is achieved, and prediction efficiency and reliability are remarkably improved.

The invention provides an electromechanical transient simulation model parameter adaptive correction method and device, and relates to the field of power system simulation. The method comprises the following steps: acquiring response data of a target power system in different operation states, and constructing an electromechanical transient observation response data set based on the response data; inputting the electromechanical transient observation response data set and the current electromechanical transient simulation model into a simulation engine to execute simulation operation, and generating a simulation response sequence corresponding to the disturbance process; performing difference analysis on the electromechanical transient observation response data set and the simulation response sequence, and constructing a target function for parameter correction based on a difference analysis result; based on the structure information of the current electromechanical transient simulation model, defining a corresponding to-be-corrected parameter set; and performing iterative optimization on the to-be-corrected parameter set based on the target function, and outputting a target corrected parameter set meeting an iteration condition. According to the method, the problem of low accuracy of model parameter correction in a dynamic scene in a traditional method is solved.

The invention discloses a photovoltaic power generation power prediction and power system scheduling method and a system for realizing the method. The method comprises four steps of data acquisition and preprocessing, similar day selection and training set construction, GA (Genetic Algorithm)-fuzzy RBF (Radial Basis Function) neural network modeling and power scheduling plan generation. The method comprises the following steps: selecting a meteorological variable with high correlation degree through a Spearman rank correlation coefficient, and constructing a time sequence feature; similar days are utilized to construct training samples, and the generalization ability of the model is improved; a fuzzy RBF network optimized by GA is adopted to enhance the nonlinear modeling precision; and inputting a prediction result into the power system simulation model, and generating an optimal scheduling instruction by adopting dynamic programming. According to the method, the photovoltaic power prediction accuracy and scheduling efficiency can be remarkably improved, the power grid stability is enhanced, and the new energy consumption capability is promoted.

The invention belongs to the technical field of power system planning, and discloses a comprehensive kilowatt-hour cost calculation method considering the flexibility cost of a power system. The method comprises the following specific use steps: S1, demand prediction and power supply combination scheme determination; S2, verification of investment, operation and maintenance and finance and tax costs of various power supplies and energy storage facilities; S3, determination of power supply utilization hours through power system simulation; S4, verification of actual annual average power generation of various power supplies; and calculating the LCOE and analyzing and evaluating the LCOE. According to the LCOEsys and LCOEadj kilowatt-hour cost calculation method, the LCOEadj method is used for accurately calculating the actual leveling kilowatt-hour cost of a power supply based on the actual operation data generating capacity or the utilization hour number of a certain type of power supply obtained through production simulation in combination with the investment and operation maintenance cost of the whole life cycle of the power supply.

The invention belongs to the technical field of voltage optimization, and particularly relates to a reactive voltage optimization control method suitable for a large-scale new energy collection area, and the method comprises the steps: constructing a node power distribution network topology based on a power system simulation platform, and obtaining a training label; mapping the power distribution network into a graph structure containing nodes and edges; executing graph convolution operation through a graph neural network, extracting single-moment spatial topological features, and arranging the single-moment spatial topological features according to a time sequence to form a spatial topological feature sequence; performing spatial-temporal dynamic modeling on the spatial topological feature sequence by using an improved Mamba model, and outputting a spatial-temporal time sequence feature sequence; introducing an attention mechanism, and outputting a reactive power prediction value of each controllable device as a control instruction of power distribution network dispatching; and outputting a control instruction of actual power distribution network dispatching by using the trained graph neural network and the improved Mama model. According to the invention, under the condition of ensuring voltage safety and reactive constraint, the voltage out-of-limit quantity is reduced, and the voltage qualification rate is improved.

The invention discloses a power system simulation analysis intelligent agent system and a simulation analysis method. According to the method, the power system simulation analysis intelligent agent system comprises an interface layer used for receiving a user instruction and feeding back a task result in multiple modes; the workflow layer comprises a main agent and is used for analyzing a user instruction and generating and driving workflow for executing simulation analysis according to the task knowledge base; the skill layer comprises a plurality of sub-agents and is used for packaging and executing specific sub-tasks in the workflow; the tool / knowledge layer is used for providing a standardized calling interface for external tools and storing data and knowledge required by task execution; and the business system layer comprises one or more existing power system simulation business systems and is used for providing basic data, computing services and interaction components for the tool / knowledge layer.

The invention provides an electric power system model important parameter group identification method based on trajectory feature clustering, relates to an electric power system simulation technology, and solves the problem that modeling is not performed due to time domain global error index coarse graining and parameter coupling in traditional electric power system important parameter identification. The parameters are used as to-be-identified high-sensitivity parameters; performing time domain difference on each group of simulation tracks and actually measured tracks to obtain difference tracks, and extracting difference track features; the method comprises the following steps: mapping high-dimensional data to a low-dimensional space through a nonlinear dimension reduction method, and executing K-Means clustering on the data in the low-dimensional space to obtain a cluster label of each sample; sensitivity calculation is carried out on all samples in the clusters, and a parameter combination with the highest occurrence frequency and the maximum contribution to dynamic differences in the clusters is screened out to serve as a final dominant parameter set. According to the scheme, the simulation frequency and the calculation burden can be remarkably reduced, and high-precision and interpretable discrimination of important parameters really influencing the system performance is realized.

The invention relates to the technical field of energy storage, and particularly discloses a digital-analog hybrid simulation electromechanical transient modeling method and system for an energy storage system, and the method comprises the steps: firstly, building a digital-analog hybrid simulation test model of the energy storage system, enabling the model circuit parameters to be consistent with the same-model energy storage system of an actual energy storage power station, and enabling the model circuit parameters to be consistent with the model circuit parameters of the actual energy storage power station; checking the correctness of the signal transmission system of the digital-analog hybrid simulation system; then, carrying out an electromechanical transient modeling working condition test of the energy storage system, recording a test result, applying regression analysis to obtain electromechanical transient model parameters of the energy storage system, and establishing an electromechanical transient simulation model of the energy storage system; and finally, comparing and analyzing test results of the electromechanical transient simulation model and the test model under typical operation conditions, and calculating errors. Based on a digital-analog hybrid simulation system, an electromechanical transient simulation model consistent with an actual energy storage system of the same model in performance can be established, and an accurate energy storage model is provided for simulation of a modern power system.

The invention provides a self-adaptive multi-resolution power system simulation method and device based on physical information, and relates to the technical field of power system simulation. The method comprises the following steps: acquiring model data and operation state data of a power system; constructing a simulation system corresponding to the power system based on the model data, the operation state data and the multi-level resolution model library; determining a target model resolution corresponding to each subsystem through a self-adaptive resolution control strategy and a multi-level resolution model library; and distributing the target model resolution to the corresponding subsystem, and performing simulation calculation on the subsystem of the simulation system based on the multi-level resolution model library and the adaptive resolution control strategy to obtain a simulation calculation result corresponding to the power system. According to the embodiment of the invention, by designing the adaptive resolution control strategy, the dynamic adjustment of the resolution of different regional models of the power system is realized, and the calculation efficiency can be greatly improved while the simulation precision is maintained.

Provided is an apparatus for power grid simulation, which includes: an editing module configured to generate a virtual power system based on a digital twin according to a user setting; and a simulation module configured to perform a safety diagnosis simulation on the virtual power system based on at least one state among a physical state, a time state, and a task state of the virtual power system.

According to a method to aid installation of large-scale BESS in a power network, a hyperparameter optimization engine generates a feasible configuration of BESS defined by location and sizing parameters subject to an installation constraint. A power system simulation engine conducts an energy market simulation for the power network with the generated configuration over a defined simulation horizon to determine a configuration value. The power system simulation engine comprises one or more subroutines characterizing the impact of the BESS on the market clearing mechanism, to compute an expected generation cost associated with the BESS. The configuration value is determined based on the expected generation cost and a total installation cost of the BESS. The hyperparameter optimization engine is iteratively executed to generate an updated configuration based on the configuration values of previous configurations, to determine a final configuration of BESS defined by a set of optimal location and sizing parameters.

The invention provides a wind and light storage modular modeling method and system oriented to an electromechanical transient state of a power system, relates to the technical field of power system simulation, and aims to solve the problems that in the prior art, the requirements of a user on modular recombination and customized adaptation of a model cannot be met, the model reuse rate is low, the flexibility is poor, and the modeling efficiency is high. And a unified modeling standard system is not formed yet, so that the development requirement of a novel power system is difficult to adapt. Comprising the following steps: based on energy form decoupling, carrying out modular decomposition and reconstruction on a wind and light storage dynamic model, decomposing the model into three links of energy conversion and control, energy buffering and energy output and control, and constructing a hierarchical integrated architecture; and based on the hierarchical integrated architecture, modular sub-models corresponding to the fan, the photovoltaic device and the energy storage device are constructed respectively, and dynamic combination is carried out to obtain a modeling result. According to the method, the problems in the prior art are solved, the model reuse rate and flexibility are improved, and the model simulation precision and efficiency are improved.

The invention discloses a wind power plant electromagnetic transient simulation model parameter correction method and device, terminal equipment and a storage medium, and belongs to the field of power system simulation. The method comprises the following steps: acquiring transient simulation electrical parameters of a to-be-corrected wind power plant station in a preset time period; respectively constructing an electrical parameter time sequence according to the transient simulation electrical parameters and a preset time interval; calculating according to the electrical parameter time sequence to obtain an influence factor of the transient simulation electrical parameter at each moment on the next moment; according to the electrical parameter time sequence and the influence factor, predicting to obtain a transient simulation electrical parameter prediction value at the target prediction moment; calculating a transient parameter deviation index according to the transient simulation electrical parameter predicted value; and when the transient parameter deviation index is greater than or equal to a preset first judgment threshold value, correcting transient simulation electrical parameters of the electromagnetic transient simulation model according to a preset proportion. By implementing the method, the problem that all operation conditions of the wind power plant cannot be covered in the prior art can be solved.

The invention discloses a method for evaluating voltage unbalance of a following / construction network type hybrid wind power collection system. The method is suitable for a hybrid wind power plant grid-connected scene comprising a construction network type converter (GFM) and a following network type converter (GFL). The method comprises the following steps: firstly, constructing fundamental frequency negative sequence impedance models in different access modes, and establishing a negative sequence equivalent circuit model by combining system electrical topology; secondly, the voltage unbalance degree of each confluence node is calculated through sequence component analysis; secondly, analyzing the influence rule of factors such as the number proportion of the network-forming type units, the access voltage level and the space layout on the voltage imbalance; and finally, verifying the evaluation method through a power system simulation platform to ensure the accuracy and applicability of the result. The method can be used for electric energy quality evaluation and optimal configuration analysis under the regional-level and multi-wind-power-plant grid-connected condition.

The invention relates to the technical field of electric power system simulation and automatic control, and discloses an automatic scoring method and system for a thermal generator set simulation operation desk, and the method comprises the steps: collecting an operation instruction stream and physical parameter monitoring data through a multi-source sensor, and carrying out the time-space alignment and abnormality cleaning of the collected multi-source data, then constructing a space-time four-dimensional tensor model representing the running state of the unit, wherein the dimensions of the space-time four-dimensional tensor model comprise a time axis, a space subsystem, running parameters and equipment health degree; constructing a meta reinforcement learning framework, generating a dynamic scoring weight vector by using the space-time four-dimensional tensor, and performing real-time scoring in combination with an attenuation factor in the equipment health degree; through TSN protocol dynamic priority distribution and a multi-source data synchronous compensation technology, microsecond-level space-time alignment of operation instruction streams, physical sensing parameters and virtual data is realized, the bottleneck of time sequence mismatch caused by a traditional heterogeneous protocol is broken through, and the problem of feature modeling distortion caused by a multi-source data island is solved.

The invention discloses a feature data screening method and device for power grid fault assessment, and belongs to the field of power systems, and the method comprises the steps: firstly obtaining a local bus set of a power grid and a candidate feature set corresponding to the set; performing a fault simulation experiment on the power grid according to a preset power system simulation platform to obtain characteristic quantity data corresponding to each characteristic quantity and form a characteristic quantity data set; according to a Mahalanobis distance principle and a Spearman level correlation coefficient calculation method, sorting each characteristic quantity data in the characteristic quantity data set to obtain an intermediate candidate characteristic set; screening each intermediate candidate feature in the intermediate candidate feature set by adopting an incremental feature subset strategy to obtain a plurality of final candidate features; and finally, performing fault assessment on the power grid according to each final candidate feature and the local bus set, and outputting a fault assessment result, so that the accuracy of power grid fault assessment can be improved through implementation of the method.

The present invention provides a method for simulating power system transactions based on multi-agent agents, which belongs to the technical field of power system simulation, and includes: collecting historical operation data of the power system, constructing a multi-agent system including power generation, flexible load and power sales agents, and performing Monte Carlo simulation and scenario generation. The method adopts a deep reinforcement learning algorithm, defines the profit function and decision model of each agent, performs market clearing calculations, and performs transaction simulation by constructing a verification scenario library. The system can evaluate agent strategies, calculate key market indicators, and feed back market information to the agent, realizing intelligent and dynamic optimization of power transaction decisions, and effectively improving the operational efficiency and transaction accuracy of the power market. The method of the present invention solves the technical problem that the existing technology generally does not fully consider the interaction and learning mechanism between market participants, resulting in a large deviation between the simulation results and the actual market performance.

The application discloses a large language model driven full-automatic intelligent simulation method and system of a power system, and belongs to the field of power system simulation calculation. The simulation method comprises an offline optimization stage and an online application stage. In the offline optimization stage, a simulation parameter file of the power system and a modification range of each parameter are acquired, and a training command pool containing executable and non-executable commands is designed. A command generator and a prompt word optimizer are constructed based on a large language model, forming a generative adversarial framework. The optimization of system prompt words is realized based on the framework, and the optimal prompt words are obtained. In the online application stage, after a natural language command is input by a user, the large language model identifies the command and matches the optimal prompt words, and inputs the command to each parameter modifier to adjust the simulation parameters. Whether the parameters are within the allowed range is verified, and if the verification is passed, the simulation software is called to perform power system simulation calculation. The power system simulation automation level and intelligent interaction experience are significantly improved, and the method has strong practical value.