Power system dynamic analysis method and device, equipment, storage medium and program product

Abstract

The invention relates to a power system dynamic analysis method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a plurality of operation data of a power system, and dividing each operation data into a plurality of operation data groups; detecting an importance index and a stability index of each operation data; detecting the data weight of each operation data based on the importance index and the stability index of each operation data, and evaluating the comprehensive score of each operation data group; based on the comprehensive score of each operation data group and the data weight of each operation data, screening out a target operation data group from each operation data group; and optimizing the dynamic analysis simulation model of the power system based on the operation data in each target operation data group, wherein the dynamic analysis simulation model of the power system is used for dynamically analyzing the power system. The method can improve the dynamic analysis accuracy of the power system.

Description

Technical Field

[0001] The present application relates to the technical field of power system analysis, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for dynamic analysis of a power system. Background Art

[0002] In modern power systems, with the access of renewable energy, the growth of distributed generation and the development of smart grids, the grid topology is becoming more and more complex and changeable. In order to ensure the stability and reliability of the system, it is essential to accurately analyze the changes in the grid topology. By building a simulation model and simulating the grid topology change process of the power system, the current grid status can be reflected efficiently and accurately, but the accuracy of the simulation is highly dependent on the quality of the training data.

[0003] In traditional technology, the model training process becomes very complicated and time-consuming due to the large amount of training data. Therefore, in order to improve the efficiency of model training, domain experts or data analysts usually screen the training data based on their experience and select the most useful data for model training.

[0004] However, the selection criteria of traditional methods rely on personal experience and judgment, and the quality of training data mainly depends on the subjective judgment of the screener. Subjective judgment can easily lead to potentially unnecessary data being included in the model analysis, while data carrying key details are not selected. This will lead to poor training effects of the simulation model and thus low accuracy of dynamic analysis of the power system. Summary of the invention

[0005] Based on this, it is necessary to provide a power system dynamic analysis method, device, computer equipment, computer readable storage medium and computer program product that can improve the accuracy of power system dynamic analysis in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for dynamic analysis of a power system, comprising:

[0007] Acquire multiple operation data of the power system, and divide each operation data into multiple operation data groups;

[0008] Detect the importance index and stability index of each operating data;

[0009] Based on the importance index and stability index of each operating data, the data weight of each operating data is detected, and the comprehensive score of each operating data group is evaluated;

[0010] Based on the comprehensive scores of each operation data group and the data weights of each operation data, a target operation data group is selected from each operation data group;

[0011] The power system dynamic analysis simulation model is optimized based on the operating data in each target operating data group, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0012] In one embodiment, based on the importance index and stability index of each operation data, a comprehensive score of each operation data group is evaluated, including:

[0013] Detecting the importance comprehensive index of each operation data group based on the importance index of each operation data, detecting the stability comprehensive index of each operation data group based on the stability index of each operation data, and detecting the comprehensive weight of each operation data group based on the data weight of each operation data;

[0014] Based on the comprehensive importance index, comprehensive stability index and comprehensive weight of each operating data group, as well as the data weight of each operating data, each operating data group is scored to obtain a comprehensive score for each operating data group.

[0015] In one embodiment, based on the importance comprehensive index, stability comprehensive index and comprehensive weight of each operation data group, and the data weight of each operation data, each operation data group is scored to obtain a comprehensive score of each operation data group, including:

[0016] According to the data weight of each operating data in each operating data group, the average value of the data weight corresponding to each operating data group is calculated;

[0017] The comprehensive importance index, comprehensive stability index, comprehensive weight and data weight average of each operating data group are weighted and aggregated to obtain a comprehensive score for each operating data group.

[0018] In one embodiment, based on the importance index and stability index of each operation data, detecting the data weight of each operation data includes:

[0019] Calculate the ratio of the importance index and stability index corresponding to each operating data;

[0020] Through linear mapping, the ratio corresponding to each running data is converted into the data weight of each running data.

[0021] In one embodiment, based on the comprehensive scores of the operation data groups and the data weights of the operation data groups, the target operation data group is screened out from the operation data groups, including:

[0022] Compare the comprehensive score of each operation data group with the preset comprehensive score threshold, and determine the operation data group with a comprehensive score greater than or equal to the preset comprehensive score threshold as the candidate data group;

[0023] Based on the data weight of each operating data in each candidate data group, detecting the quantity ratio of the target operating data in each candidate data group, wherein the target operating data is the operating data whose data weight exceeds the preset data weight threshold;

[0024] The candidate data group whose quantity proportion of target operation data is greater than or equal to a preset quantity proportion threshold is determined as the target operation data group.

[0025] In one embodiment, detecting the importance index of each operation data includes:

[0026] Detect the correlation between each operation data and the simulation result of the power system dynamic analysis simulation model to obtain the correlation coefficient;

[0027] Each correlation coefficient is normalized to obtain the importance index of each operating data;

[0028] And / or, detecting the stability index of each operation data, including:

[0029] Obtaining a stability assessment data set within a preset time range for each operating data;

[0030] Calculate the standard deviation corresponding to each stability assessment data set;

[0031] Each standard deviation is normalized to obtain the stability index of each operating data.

[0032] In a second aspect, the present application also provides a power system dynamic analysis device, comprising:

[0033] An acquisition module, used for acquiring a plurality of operation data of the power system and dividing each operation data into a plurality of operation data groups;

[0034] The first detection module is used to detect the importance index and stability index of each operation data;

[0035] The second detection module is used to detect the data weight of each operation data based on the importance index and stability index of each operation data, and evaluate the comprehensive score of each operation data group;

[0036] A screening module, used to screen out a target operation data group from each operation data group based on the comprehensive score of each operation data group and the data weight of each operation data;

[0037] The optimization module is used to optimize the power system dynamic analysis simulation model based on the operating data in each target operating data group. The power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Acquire multiple operation data of the power system, and divide each operation data into multiple operation data groups;

[0040] Detect the importance index and stability index of each operating data;

[0041] Based on the importance index and stability index of each operating data, the data weight of each operating data is detected, and the comprehensive score of each operating data group is evaluated;

[0042] Based on the comprehensive scores of each operation data group and the data weights of each operation data, a target operation data group is selected from each operation data group;

[0043] The power system dynamic analysis simulation model is optimized based on the operating data in each target operating data group, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0045] Acquire multiple operation data of the power system, and divide each operation data into multiple operation data groups;

[0046] Detect the importance index and stability index of each operating data;

[0047] Based on the importance index and stability index of each operating data, the data weight of each operating data is detected, and the comprehensive score of each operating data group is evaluated;

[0048] Based on the comprehensive scores of each operation data group and the data weights of each operation data, a target operation data group is selected from each operation data group;

[0049] The power system dynamic analysis simulation model is optimized based on the operating data in each target operating data group, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0050] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0051] Acquire multiple operation data of the power system, and divide each operation data into multiple operation data groups;

[0052] Detect the importance index and stability index of each operating data;

[0053] Based on the importance index and stability index of each operating data, the data weight of each operating data is detected, and the comprehensive score of each operating data group is evaluated;

[0054] Based on the comprehensive scores of each operation data group and the data weights of each operation data, a target operation data group is selected from each operation data group;

[0055] The power system dynamic analysis simulation model is optimized based on the operating data in each target operating data group, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0056] The above-mentioned power system dynamic analysis method, device, computer equipment, computer-readable storage medium and computer program product first obtain multiple operating data of the power system, and divide each operating data into multiple operating data groups. By grouping the operating data and performing data screening in groups, the data screening efficiency can be effectively improved; then the importance index and stability index of each operating data are detected, and based on the importance index and stability index of each operating data, the data weight of each operating data is detected, and the comprehensive score of each operating data group is evaluated, and then based on the comprehensive score of each operating data group and the data weight of each operating data, the target operating data group is screened out from each operating data group, and the evaluation of the data group from two dimensions of data and data group is realized, which can simultaneously improve the precision and accuracy of data screening, effectively reduce the inclusion of non-essential data in the model analysis, and improve the comprehensiveness and accuracy of the training data, and then optimize the power system dynamic analysis simulation model based on the operating data in each target operating data group. The power system dynamic analysis simulation model is used to perform dynamic analysis on the power system. In this way, since more comprehensive and accurate training data are used for model training, the model training effect can be effectively improved, thereby improving the accuracy of the power system dynamic analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a flow chart of a power system dynamic analysis method in one embodiment;

[0059] Figure 2 is a flow chart of a power system dynamic analysis method in another embodiment;

[0060] Figure 3 is a structural block diagram of a power system dynamic analysis device in one embodiment;

[0061] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] In an exemplary embodiment, Figure 1 As shown, a method for dynamic analysis of a power system is provided. This embodiment takes the method applied to a terminal as an example, wherein the terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. It can be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and may be implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S10-S50. Among them:

[0064] Step S10: acquiring a plurality of operation data of the power system, and dividing each operation data into a plurality of operation data groups.

[0065] The operation data may refer to various types of data generated in real-time or historical operation processes in various links of the power system such as power generation, transmission, distribution and power consumption, and may include one of voltage, current, temperature, circuit breaker switch state, disconnector state, load data, etc. It is understandable that the operation data of the power system may be of multiple types, and for each type of operation data, the corresponding target operation data group may be screened out according to the method of this embodiment, for example, the target voltage data group may be screened out from the voltage data, and the target circuit breaker switch state data group may be screened out from the circuit breaker switch state data, etc. For ease of understanding, this embodiment is described by taking any type of operation data as an example.

[0066] In some feasible implementations, based on the actual needs of the power system dynamic analysis simulation model, at least one target type of operating data used for model training can be determined, and then the operating data corresponding to each target type can be screened separately, and the target operating data groups corresponding to each screened target type can be used to optimize and update the power system dynamic analysis simulation model.

[0067] Exemplarily, the operation data generated by the power system in real time within a period of time can be collected through a data collection device, or the operation data generated and stored by the power system in the historical time period can be obtained from the memory; then, the multiple operation data obtained can be divided into multiple operation data groups according to the preset grouping rules. Among them, the number of operation data and the preset grouping rules can be determined in advance according to actual conditions and test results, and the preset grouping rules may include whether to divide evenly, whether to maintain time series continuity, the lower limit and upper limit of the amount of data in each operation data group, etc. In a feasible implementation, the preset grouping rule can be to randomly and evenly distribute the operation data to a preset number of operation data groups. For example, the number of operation data obtained is predetermined to be N1, and the number of operation data groups is N2. The preset grouping rule can be to randomly and evenly distribute N1 data to N2 operation data groups.

[0068] Step S20, detecting the importance index and stability index of each operation data.

[0069] Among them, the importance index can be used to characterize the influence of the operation data on the simulation analysis of the power system dynamic analysis simulation model. If the operation data has a greater influence on the simulation analysis of the power system dynamic analysis simulation model, its importance index is higher, and if the operation data has a smaller influence on the simulation analysis of the power system dynamic analysis simulation model, its importance index is lower. The stability index can be used to characterize the degree of stability of the operation data over time.

[0070] Exemplarily, the importance index corresponding to each operating data can be obtained by performing correlation analysis on each operating data and the simulation results of the power system dynamic analysis simulation model. Simultaneously, for each operating data, other operating data within a preset time period to which the operating data belongs can be obtained, and the operating data and the other operating data are combined into a stability assessment data set. Based on the stability assessment data set, the stability of the operating data is analyzed to obtain the stability index corresponding to the operating data.

[0071] Step S30: based on the importance index and stability index of each operation data, detect the data weight of each operation data and evaluate the comprehensive score of each operation data group.

[0072] Among them, the data weight is used to characterize the influence of the operating data on the simulation analysis results of the power system dynamic analysis simulation model. If the data weight is higher, it means that the operating data has a greater influence on the simulation analysis results of the power system dynamic analysis simulation model. Conversely, if the data weight is lower, it means that the operating data has a smaller influence on the simulation analysis results of the power system dynamic analysis simulation model.

[0073] Exemplarily, the importance index and stability index corresponding to each operating data can be brought into the preset data weight function to calculate the data weight of each operating data. The preset data weight function is a function of the data weight, the importance index and the stability index, which can be determined based on the actual situation and actual test results, for example, it can be determined based on historical data fitting, and this is not limited in this embodiment; each operating data group can also be scored based on the importance index, comprehensive index and data weight of each operating data in each operating data group through a preset scoring model to obtain a comprehensive score for each operating data group, wherein the preset scoring model can be a mathematical statistical model or an artificial intelligence model, etc., which can be determined based on the actual situation and test results, etc., and this is not limited in this embodiment.

[0074] Step S40 , based on the comprehensive scores of the operation data groups and the data weights of the operation data, a target operation data group is selected from the operation data groups.

[0075] Exemplarily, according to preset screening rules, based on the comprehensive score of each operating data group and the data weight of each operating data in each operating data group, a target operating data group that meets the preset screening rules can be screened out from each operating data group.

[0076] Among them, the preset screening rules can be determined in advance according to actual conditions and test results, etc. For example, corresponding valid ranges can be set for the comprehensive score and data weight respectively, and the operation data group whose comprehensive score and data weight are both within the corresponding valid range can be determined as the target operation data group; or, the comprehensive score and data weight can be combined to set comprehensive conditions, such as the comprehensive score is higher than S1 and the data weight is higher than W1, or the comprehensive score is higher than S2 but less than S1, and the data weight is higher than W2, or the comprehensive score is higher than S3, and the data weight is higher than W3 but less than W1, etc., and the operation data group that meets the comprehensive conditions is determined as the target operation data group; etc.

[0077] Step S50, optimizing the power system dynamic analysis simulation model based on the operation data in each target operation data group, the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0078] The power system dynamic analysis simulation model can be a mathematical model based on physical laws and engineering principles. The power system dynamic analysis simulation model can simulate the behavior of various components in the power system and the interactions between them through numerical methods. The components include at least one of generators, transformers, transmission lines, loads, etc. The power system dynamic analysis simulation model is intended to capture the process of the internal state variables of the power system changing over time, including but not limited to at least one of voltage, current, frequency, power angle, etc.

[0079] Exemplarily, the operating data in each target operating data group is used as the operating data corresponding to this type, and can be used alone or together with the operating data corresponding to other types to optimize the power system dynamic analysis simulation model and update the model parameters of the power system dynamic analysis simulation model. The optimized power system dynamic analysis simulation model can be used to perform dynamic simulation analysis on the power system.

[0080] In the above-mentioned power system dynamic analysis method, firstly, multiple operation data of the power system are obtained, and each operation data is divided into multiple operation data groups. By grouping the operation data and performing data screening in groups, the data screening efficiency can be effectively improved; then, the importance index and stability index of each operation data are detected, and based on the importance index and stability index of each operation data, the data weight of each operation data is detected, and the comprehensive score of each operation data group is evaluated, and then based on the comprehensive score of each operation data group and the data weight of each operation data, the target operation data group is screened out from each operation data group, and the evaluation of the data group from two dimensions of data and data group is realized, which can simultaneously improve the precision and accuracy of data screening, effectively reduce the inclusion of unnecessary data in the model analysis, and improve the comprehensiveness and accuracy of the training data, and then optimize the power system dynamic analysis simulation model based on the operation data in each target operation data group. The power system dynamic analysis simulation model is used to perform dynamic analysis on the power system. In this way, since more comprehensive and accurate training data are used for model training, the model training effect can be effectively improved, thereby improving the accuracy of the power system dynamic analysis.

[0081] In an exemplary embodiment, based on the importance index and stability index of each operation data, the comprehensive score of each operation data group is evaluated, including steps S311 to S312.

[0082] Step S311, based on the importance index of each operating data, detect the comprehensive importance index of each operating data group, based on the stability index of each operating data, detect the comprehensive stability index of each operating data group, and based on the data weight of each operating data, detect the comprehensive weight of each operating data group.

[0083] Exemplarily, for each operation data group, the importance index of each operation data in the operation data group is aggregated to obtain the importance comprehensive index of the operation data group, the stability index of each operation data in the operation data group is aggregated to obtain the stability comprehensive index of the operation data group, and the data weight of each operation data in the operation data group is aggregated to obtain the comprehensive weight of the operation data group. The aggregation method may include at least one of averaging, summing, weighted averaging, and weighted summing, which may be determined based on actual conditions and test results, and is not limited in this embodiment.

[0084] Step S312, based on the comprehensive importance index, comprehensive stability index and comprehensive weight of each operation data group, and the data weight of each operation data, each operation data group is scored to obtain a comprehensive score for each operation data group.

[0085] Exemplarily, a preset scoring model can be used to score each operation data group based on the comprehensive importance index, comprehensive stability index and comprehensive weight of each operation data group, as well as the data weight of each operation data in each operation data group, to obtain a comprehensive score for each operation data group. The preset scoring model can be a mathematical statistical model or an artificial intelligence model, etc., which can be determined based on actual conditions and test results, etc., and this embodiment is not limited to this.

[0086] In this embodiment, the accuracy of the overall evaluation of the operating data group can be improved through the importance comprehensive index, stability comprehensive index and comprehensive weight. Combined with the data weight, the individual information of the data is retained, and the evaluation of the data group from two dimensions of data and data group is realized. The precision and accuracy of data screening can be improved at the same time, and the inclusion of unnecessary data in the model analysis can be effectively reduced, and the comprehensiveness and accuracy of the training data can be improved.

[0087] In an exemplary embodiment, based on the importance comprehensive index, stability comprehensive index and comprehensive weight of each operation data group, and the data weight of each operation data, each operation data group is scored to obtain a comprehensive score of each operation data group, including steps S3121 to S3122. Among them:

[0088] Step S3121, according to the data weight of each operation data in each operation data group, calculate the average data weight corresponding to each operation data group.

[0089] Exemplarily, the data weights of the various operating data in each operating data group are combined and averaged to obtain the average data weight corresponding to each operating data group.

[0090] Step S3122, weighted aggregation is performed on the importance comprehensive index, stability comprehensive index, comprehensive weight and data weight average of each operation data group to obtain a comprehensive score for each operation data group.

[0091] Exemplarily, the comprehensive importance index, comprehensive stability index, comprehensive weight and data weight average of each operating data group are weighted and aggregated to obtain a comprehensive score for each operating data group, wherein the weighted aggregation method includes at least one of weighted average, weighted summation, etc., which can be specifically determined based on actual conditions and test results, etc., and this embodiment is not limited to this.

[0092] In some feasible implementations, the comprehensive score S of the jth group of operation data of the i-th category of operation data is ij It can be expressed as:

[0093]

[0094] Among them, I ijk I' is the importance index of the kth operation data in the jth operation data group included in the i-th type of operation data; ij is the comprehensive importance index of the jth group of operation data contained in the i-th type of operation data; P ijk is the stability index of the kth operating data in the jth operating data group contained in the i-th type of operating data; P' ij is the comprehensive stability index of the jth group of operating data contained in the i-th type of operating data; W ijk is the weight of the kth operation data in the jth operation data group included in the i-th type of operation data; W' ij is the comprehensive weight of the jth group of operation data contained in the i-th type of operation data; m ij is the number of operating data in the jth operating data group contained in the i-th type of operating data; α, β and γ are balancing factors, and satisfy 0<α, β, γ<1 and α+β+γ=1.

[0095] In this embodiment, by evaluating the data group from two dimensions, data and data group, the precision and accuracy of data screening can be improved simultaneously, the inclusion of unnecessary data in the model analysis can be effectively reduced, and the comprehensiveness and accuracy of the training data can be improved.

[0096] In an exemplary embodiment, based on the importance index and stability index of each operation data, the data weight of each operation data is detected, including steps S321 to S322. In which:

[0097] Step S321, calculating the ratio of the importance index and the stability index corresponding to each operation data.

[0098] Step S322: convert the ratio corresponding to each operating data into the data weight of each operating data through linear mapping.

[0099] Exemplarily, the numerical range of the ratio of the importance index and the stability index can be determined in advance based on historical data, or the numerical range of the importance index and the stability index, and then a linear mapping model can be established based on the numerical range of the ratio and the numerical range of the data weight; then, when actually performing the linear mapping, the ratio of the importance index to the stability index of each operating data can be calculated first, and then the ratio can be input into the linear mapping model, and the ratio can be converted into the corresponding data weight through the linear mapping model, so that the ratio of the importance index to the stability index of each operating data can be converted to obtain the data weight of each operating data.

[0100] In this embodiment, the data weight is characterized by the ratio of the importance index and the stability index, so that operating data with a greater impact on the simulation results and higher stability can be selected for model training, and unnecessary data can be effectively and accurately removed, thereby improving the training efficiency and training effect of the power system dynamic analysis simulation model.

[0101] In an exemplary embodiment, Figure 2 As shown, based on the comprehensive scores of each operation data group and the data weights of each operation data, a target operation data group is screened out from each operation data group, including steps S41 to S43. Among them:

[0102] Step S41 , comparing the comprehensive score of each operation data group with a preset comprehensive score threshold, and determining the operation data group with a comprehensive score greater than or equal to the preset comprehensive score threshold as the candidate data group.

[0103] Exemplarily, after the comprehensive score of the operating data group is detected, the comprehensive score of each operating data group is compared with a preset comprehensive score threshold, and the operating data group with a comprehensive score greater than or equal to the preset comprehensive score threshold is determined as the alternative data group.

[0104] Step S42, based on the data weight of each operating data in each candidate data group, detecting the quantity ratio of the target operating data in each candidate data group, wherein the target operating data is the operating data whose data weight exceeds the preset data weight threshold.

[0105] Exemplarily, after determining the alternative data groups, the data weights of each operating data in each alternative data group are compared with the preset data weight threshold, and the operating data whose data weight exceeds the preset data weight threshold is determined as the target operating data. Then, the number of target operating data in each alternative data group is counted, and the ratio of the number of target operating data in each alternative data group to the total number of all operating data in the alternative data group is calculated to obtain the proportion of the number of target operating data in each alternative data group.

[0106] Step S43: determine the candidate data group whose quantity proportion of target operation data is greater than or equal to a preset quantity proportion threshold as the target operation data group.

[0107] Exemplarily, the quantity ratio of the target operating data in each alternative data group is compared with a preset quantity ratio threshold, and the alternative data group whose quantity ratio of the target operating data is greater than or equal to the preset quantity ratio threshold is determined as the target operating data group.

[0108] In this embodiment, by means of simple numerical calculation and numerical comparison, the time for screening the target operation data group can be effectively reduced and the data screening efficiency can be improved.

[0109] In an exemplary embodiment, detecting the importance index of each operation data includes steps S211 to S212. In which:

[0110] Step S211 , detecting the correlation between each operating data and the simulation result of the power system dynamic analysis simulation model to obtain a correlation coefficient.

[0111] The correlation coefficient may be a Pearson correlation coefficient, a Spearman rank correlation coefficient, a Kendall rank correlation coefficient, etc. The specific calculation method of the correlation coefficient is similar to the prior art, and this embodiment will not be described in detail.

[0112] Exemplarily, multiple other operating data within a preset time range are obtained for each operating data, and the operating data and other operating data are combined into a correlation evaluation data set, wherein the preset time range can be a preset time range before and after the central time point with the timestamp corresponding to the operating data as the central time point; then the correlation evaluation data sets are respectively brought into the power system dynamic analysis simulation model, and other parameters in the power system dynamic analysis simulation model are kept unchanged to obtain a correlation evaluation simulation result set, the correlation evaluation simulation result set including the correlation evaluation simulation results corresponding to each data in the correlation evaluation data set; then based on the correlation evaluation data set and the correlation evaluation simulation result set, the correlation coefficient is calculated.

[0113] Step S212, normalizing each correlation coefficient to obtain an importance index of each operating data.

[0114] Exemplarily, after the correlation coefficients are obtained, each correlation coefficient may be normalized, the numerical range of the correlation coefficient may be transformed to between [0, 1], and the normalized correlation coefficient may be determined as the importance index of each operation data.

[0115] In this embodiment, through correlation analysis, the degree of influence of each operating data on the simulation results of the power system dynamic analysis simulation model can be determined, so as to select the operating data with a greater impact on the simulation results of the power system dynamic analysis simulation model for model training, which can effectively improve the training efficiency and training effect of the model training.

[0116] In an exemplary embodiment, detecting the stability index of each operation data includes steps S221 to S223. In which:

[0117] Step S221, obtaining a stability evaluation data set within a preset time range to which each operating data belongs.

[0118] Exemplarily, multiple other operating data within a preset time range are obtained for each operating data, and the operating data and other operating data are combined into a stability evaluation data set, wherein the preset time range can be a preset time range before and after the central time point with the timestamp corresponding to the operating data as the central time point. It can be understood that the stability evaluation data set and the correlation evaluation data set can be the same or different, which can be determined according to actual conditions, and this embodiment does not limit this.

[0119] Step S222, calculating the standard deviation corresponding to each stability assessment data set.

[0120] Step S223, normalizing each standard deviation to obtain a stability index of each operating data.

[0121] Exemplarily, after determining the stability assessment data set, the standard deviation of each stability assessment data set can be calculated, and then the calculated standard deviations of all stability assessment data sets can be normalized, the numerical range of the standard deviation can be transformed to between [0, 1], and the normalized standard deviation can be determined as the stability index of each operating data.

[0122] In this embodiment, operating data with good stability shows relatively consistent characteristics and patterns in different time periods and conditions. Using such data for training can help the model better learn the inherent laws in the data, rather than accidental phenomena specific to a certain time period or condition, thereby improving the model training effect.

[0123] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0124] Based on the same inventive concept, the embodiment of the present application also provides a power system dynamic analysis device for implementing the power system dynamic analysis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power system dynamic analysis device embodiments provided below can refer to the limitations of the power system dynamic analysis method above, and will not be repeated here.

[0125] In an exemplary embodiment, Figure 3 As shown, a power system dynamic analysis device is provided, including: an acquisition module 302, a first detection module 304, a second detection model 306, a screening module 308 and an optimization module 310, wherein:

[0126] An acquisition module 302 is used to acquire a plurality of operation data of the power system and divide each operation data into a plurality of operation data groups;

[0127] The first detection module 304 is used to detect the importance index and stability index of each operation data;

[0128] A second detection module 306 is used to detect the data weight of each operation data based on the importance index and stability index of each operation data, and evaluate the comprehensive score of each operation data group;

[0129] A screening module 308 is used to screen out a target operation data group from each operation data group based on the comprehensive score of each operation data group and the data weight of each operation data;

[0130] The optimization module 310 is used to optimize the power system dynamic analysis simulation model based on the operation data in each target operation data group, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

[0131] In an exemplary embodiment, the second detection module 306 is further configured to:

[0132] Detecting the importance comprehensive index of each operation data group based on the importance index of each operation data, detecting the stability comprehensive index of each operation data group based on the stability index of each operation data, and detecting the comprehensive weight of each operation data group based on the data weight of each operation data;

[0133] Based on the comprehensive importance index, comprehensive stability index and comprehensive weight of each operating data group, as well as the data weight of each operating data, each operating data group is scored to obtain a comprehensive score for each operating data group.

[0134] In an exemplary embodiment, the second detection module 306 is further configured to:

[0135] According to the data weight of each operating data in each operating data group, the average value of the data weight corresponding to each operating data group is calculated;

[0136] The comprehensive importance index, comprehensive stability index, comprehensive weight and data weight average of each operating data group are weighted and aggregated to obtain a comprehensive score for each operating data group.

[0137] In an exemplary embodiment, the second detection module 306 is further configured to:

[0138] Calculate the ratio of the importance index and stability index corresponding to each operating data;

[0139] Through linear mapping, the ratio corresponding to each running data is converted into the data weight of each running data.

[0140] In an exemplary embodiment, the screening module 308 is further configured to:

[0141] Compare the comprehensive score of each operation data group with the preset comprehensive score threshold, and determine the operation data group with a comprehensive score greater than or equal to the preset comprehensive score threshold as the candidate data group;

[0142] Based on the data weight of each operating data in each candidate data group, detecting the quantity ratio of the target operating data in each candidate data group, wherein the target operating data is the operating data whose data weight exceeds the preset data weight threshold;

[0143] The candidate data group whose quantity proportion of target operation data is greater than or equal to a preset quantity proportion threshold is determined as the target operation data group.

[0144] In an exemplary embodiment, the first detection module 304 is further configured to:

[0145] Detect the correlation between each operation data and the simulation result of the power system dynamic analysis simulation model to obtain the correlation coefficient;

[0146] Each correlation coefficient is normalized to obtain the importance index of each operating data.

[0147] In an exemplary embodiment, the first detection module 304 is further configured to:

[0148] Obtaining a stability assessment data set within a preset time range for each operating data;

[0149] Calculate the standard deviation corresponding to each stability assessment data set;

[0150] Each standard deviation is normalized to obtain the stability index of each operating data.

[0151] Each module in the above-mentioned power system dynamic analysis device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0152] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for dynamic analysis of a power system is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0153] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0154] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0155] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0156] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0157] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0158] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0159] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0160] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for dynamic analysis of a power system, characterized in that: The method comprises: Acquire a plurality of operation data of the power system, and divide each of the operation data into a plurality of operation data groups; Detecting the importance index and stability index of each of the operating data; Based on the importance index and stability index of each of the operating data, detecting the data weight of each operating data, and evaluating the comprehensive score of each operating data group; Based on the comprehensive scores of the operation data groups and the data weights of the operation data groups, a target operation data group is selected from the operation data groups; The power system dynamic analysis simulation model is optimized based on the operation data in each of the target operation data groups, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

2. The method according to claim 1, characterized in that Based on the importance index and stability index of each of the operating data, a comprehensive score of each operating data group is evaluated, including: Detecting the importance comprehensive index of each operation data group based on the importance index of each operation data, detecting the stability comprehensive index of each operation data group based on the stability index of each operation data, and detecting the comprehensive weight of each operation data group based on the data weight of each operation data; Based on the comprehensive importance index, comprehensive stability index and comprehensive weight of each operation data group, as well as the data weight of each operation data, each operation data group is scored to obtain a comprehensive score for each operation data group.

3. The method according to claim 2, characterized in that The scoring of each operation data group based on the importance comprehensive index, stability comprehensive index and comprehensive weight of each operation data group and the data weight of each operation data to obtain a comprehensive score of each operation data group includes: According to the data weight of each operating data in each operating data group, the average value of the data weight corresponding to each operating data group is calculated; The importance comprehensive index, stability comprehensive index, comprehensive weight and data weight average of each operation data group are weighted and aggregated to obtain a comprehensive score for each operation data group.

4. The method according to claim 1, characterized in that: The detecting the data weight of each operation data based on the importance index and the stability index of each operation data comprises: Calculate the ratio of the importance index and stability index corresponding to each operating data; The ratio corresponding to each operating data is converted into the data weight of each operating data through linear mapping.

5. The method according to claim 1, characterized in that The step of selecting a target operation data group from each of the operation data groups based on the comprehensive scores of each of the operation data groups and the data weights of each of the operation data groups comprises: Compare the comprehensive scores of the operation data groups with the preset comprehensive score thresholds, and determine the operation data groups with comprehensive scores greater than or equal to the preset comprehensive score thresholds as candidate data groups; Based on the data weight of each of the operating data in each of the candidate data groups, detecting the quantity ratio of the target operating data in each of the candidate data groups, wherein the target operating data is the operating data whose data weight exceeds a preset data weight threshold; The candidate data group whose quantity proportion of the target operation data is greater than or equal to a preset quantity proportion threshold is determined as the target operation data group.

6. The method according to any one of claims 1 to 5, characterized in that: Detecting the importance index of each of the operating data includes: Detecting the correlation between each of the operating data and the simulation results of the power system dynamic analysis simulation model to obtain a correlation coefficient; Normalizing the correlation coefficients to obtain the importance index of the operation data; And / or, detecting the stability index of each of the operating data, comprising: Obtaining a stability assessment data set within a preset time range to which each of the operating data belongs; Calculating the standard deviation corresponding to each of the stability assessment data sets; Each standard deviation is normalized to obtain a stability index of each operating data.

7. A power system dynamic analysis device, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of operation data of the power system, and dividing each of the operation data into a plurality of operation data groups; A first detection module, used to detect the importance index and stability index of each of the operating data; A second detection module is used to detect the data weight of each operation data based on the importance index and stability index of each operation data, and evaluate the comprehensive score of each operation data group; A screening module, configured to screen out a target operation data group from each of the operation data groups based on a comprehensive score of each of the operation data groups and a data weight of each of the operation data; The optimization module is used to optimize the power system dynamic analysis simulation model based on the operation data in each of the target operation data groups, and the power system dynamic analysis simulation model is used to perform dynamic analysis on the power system.

8. A computer 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 method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images