Out-of-limit prediction method and device for transformer area voltage, electronic equipment and storage medium

Abstract

The invention discloses a transformer area voltage out-of-limit prediction method and device, electronic equipment and a storage medium. The method comprises the steps that an original voltage sequence of a preset transformer area in a power supply area is acquired, and original voltage sequence data is used for representing data of collected voltage data of the preset transformer area changing along with a time sequence; performing modal decomposition on the original voltage sequence to obtain a plurality of modal components which are used for representing time-frequency characteristic information of the original voltage sequence; using a preset time sequence prediction model to predict the voltage condition of the preset transformer area based on the plurality of modal components to obtain a voltage prediction result; and on the basis of the voltage prediction result and a preset standard voltage range, an out-of-limit prediction result of the preset transformer area is determined, and the out-of-limit prediction result is used for representing the probability that the voltage out-of-limit condition occurs in the preset transformer area. According to the invention, the technical problem that the out-of-limit prediction efficiency of the voltage of the transformer area is low in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of voltage over-limit prediction, and in particular to a method, device, electronic equipment and storage medium for predicting over-limit voltage in a transformer substation. Background Art

[0002] By monitoring and analyzing the voltage data in the substation power grid, the voltage over-limit situation that may occur within a period of time can be predicted, that is, the voltage over-limit prediction of the substation voltage can be made. By predicting the voltage over-limit, the power system operator can take measures in advance to adjust the power grid operation status to prevent the voltage over-limit from causing damage to the power grid equipment and users, which can improve the stability and reliability of the power grid operation and ensure the quality of power supply.

[0003] At present, the relevant technologies for predicting over-limit voltage in substations have poor prediction results when processing nonlinear and non-stationary signals, and are difficult to meet actual needs; some prediction methods require a large amount of parameter adjustment and training, resulting in a high model complexity that is not conducive to practical application; the relevant prediction methods have a slow calculation speed when processing large amounts of data, and are difficult to meet the requirements of real-time prediction, resulting in low efficiency in predicting over-limit voltage in substations.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, electronic device and storage medium for predicting over-limit of a transformer substation voltage, so as to at least solve the technical problem of low efficiency in predicting over-limit of a transformer substation voltage in the related art.

[0006] According to one aspect of an embodiment of the present invention, a method for predicting an over-limit voltage in a substation is provided, comprising: obtaining an original voltage sequence of a preset substation in a power supply area, wherein the preset substation is used to characterize a power supply sub-area in a preset power supply area, and the original voltage sequence data is used to represent data of the voltage data of the preset substation collected changing with time series; performing modal decomposition on the original voltage sequence to obtain a plurality of modal components, wherein the plurality of modal components are used to characterize time-frequency characteristic information of the original voltage sequence; predicting the voltage condition of the preset substation based on the plurality of modal components using a preset time series prediction model to obtain a voltage prediction result; determining an over-limit prediction result of the preset substation based on the voltage prediction result and a preset standard voltage range, wherein the over-limit prediction result is used to characterize the probability of a voltage over-limit condition occurring in the preset substation.

[0007] Optionally, the preset time series prediction model includes an encoder module, a self-attention module and a decoder module; the preset time series prediction model is used to predict the voltage condition of the preset substation based on multiple modal components to obtain a voltage prediction result, including: using the encoder module to extract features of multiple modal components to obtain multiple sequence features; using the self-attention module to perform weight prediction on multiple modal components to obtain self-attention weights; using the decoder module to fuse multiple sequence features and self-attention weights to obtain a voltage prediction result.

[0008] Optionally, based on the voltage prediction result and the preset standard voltage range, the over-limit prediction result of the preset substation is determined, including: obtaining voltage over-limit data of the preset substation when the voltage is over-limit; determining the voltage over-limit factor weight of the preset substation when the voltage is over-limit based on the voltage over-limit data, wherein the voltage over-limit factor weight is used to characterize the weight of each influencing factor when the preset substation is in the voltage over-limit situation; determining the over-limit prediction result based on the voltage over-limit parameter weight, the voltage prediction result and the preset standard voltage range.

[0009] Optionally, the method also includes: obtaining normal voltage data of the power supply area when the voltage is not exceeding the limit and the geographical location information of the preset substation; determining the initial standard voltage range based on the normal voltage data; matching the geographical location information with the initial standard voltage range to obtain the preset standard voltage range.

[0010] Optionally, determining an initial standard voltage range based on normal voltage data includes: obtaining the maximum value, minimum value, variance and standard deviation of the normal voltage data; determining an upper limit percentage of voltage floating based on a first difference between the maximum value and the variance; determining a lower limit percentage of voltage floating based on a second difference between the minimum value and the variance; and determining an initial standard voltage range based on the standard deviation, the upper limit percentage of voltage floating and the lower limit percentage of voltage floating.

[0011] Optionally, performing modal decomposition on the original voltage sequence to obtain multiple modal components includes: performing empirical modal decomposition on the original voltage sequence to obtain multiple initial modal components; performing variational modal decomposition on the multiple initial modal components to obtain multiple modal components.

[0012] According to another aspect of an embodiment of the present invention, a device for predicting an over-limit voltage in a substation is provided, comprising: an acquisition module for acquiring an original voltage sequence of a preset substation in a power supply area, wherein the preset substation is used to characterize a power supply sub-area in a preset power supply area, and the original voltage sequence data is used to represent data of the voltage data of the preset substation collected changing with time series; a decomposition module for performing modal decomposition on the original voltage sequence to obtain a plurality of modal components, wherein the plurality of modal components are used to characterize time-frequency characteristic information of the original voltage sequence; a prediction module for predicting the voltage condition of the preset substation based on the plurality of modal components using a preset time series prediction model to obtain a voltage prediction result; a determination module for determining an over-limit prediction result of the preset substation based on the voltage prediction result and a preset standard voltage range, wherein the over-limit prediction result is used to characterize the probability of a voltage over-limit condition occurring in the preset substation.

[0013] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0014] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0017] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0018] In an embodiment of the present invention, a method for predicting an over-limit voltage in a substation is provided, comprising: obtaining an original voltage sequence of a preset substation in a power supply area, wherein the preset substation is used to characterize a power supply sub-area in a preset power supply area, and the original voltage sequence data is used to represent data of the voltage data of the preset substation collected changing with a time series; performing modal decomposition on the original voltage sequence to obtain a plurality of modal components, wherein the plurality of modal components are used to characterize the time-frequency characteristic information of the original voltage sequence; predicting the voltage condition of the preset substation based on the plurality of modal components using a preset time series prediction model to obtain a voltage prediction result; determining an over-limit prediction result of the preset substation based on the voltage prediction result and a preset standard voltage range, wherein the over-limit prediction result is used to characterize the probability of a voltage over-limit condition occurring in the preset substation. It is easy to notice that the present application utilizes modal decomposition to process the original voltage sequence, which can better extract the time-frequency characteristic information in the original data and decompose the complex voltage data into multiple simple modal components, which is conducive to more accurate analysis and prediction of voltage change trends. The preset time series prediction model is used to make predictions based on multiple modal components, which can more comprehensively consider the temporal and spatial characteristics of the voltage data and improve the accuracy and stability of the prediction. By setting a preset standard voltage range and combining the voltage prediction results, the voltage over-limit situation of the preset substation can be timely discovered and predicted, thereby effectively improving the safety and stability of the power grid operation. The advantages of modal decomposition and prediction models are utilized to conduct in-depth analysis and prediction of voltage data, thereby improving the accuracy and reliability of the prediction, and thus solving the technical problem of low efficiency in predicting over-limit of substation voltage in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 is a flow chart of a method for predicting voltage over-limit in a transformer substation according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of an optional method for predicting voltage over-limit in a transformer area according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of a plurality of optional initial modal components according to an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of an optional modal function clustering according to an embodiment of the present invention;

[0024] Figure 5is a schematic diagram of an optional method of optimizing the number of variational mode decomposition iterations by using an improved sparrow search algorithm according to an embodiment of the present invention;

[0025] Figure 6 is a flow chart of another optional method for predicting over-limit voltage in a transformer area according to an embodiment of the present invention;

[0026] Figure 7 The figure is a schematic diagram of a device for predicting voltage over-limit in a transformer substation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to one aspect of an embodiment of the present invention, a method for predicting an over-limit of a transformer substation voltage is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 1 is a flow chart of a method for predicting voltage over-limit in a substation according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0031] Step S102, obtaining an original voltage sequence of a preset substation in the power supply area.

[0032] The preset area is used to characterize the power supply area within the preset power supply area, and the original voltage series data is used to represent the data of the collected voltage data of the preset area changing with the time series.

[0033] The above-mentioned preset area can be a preset power supply sub-area within the power supply area. The selection of the preset area can be determined according to actual needs and is not limited here.

[0034] In an optional embodiment, in the process of predicting the voltage over-limit of the substation, the original voltage sequence of the preset substation in the power supply area can be obtained. Specifically, the power supply area range can be determined, and the power supply area range for which voltage over-limit prediction needs to be performed can be determined. The area can be a city, a township or a community, etc. Then, the substation can be selected as the preset substation according to the actual situation. A voltage sensor or monitoring equipment can be installed in each preset substation to monitor the voltage data of the substation in real time. The voltage data of each preset substation is collected by the voltage monitoring equipment and stored in a database to form an original voltage sequence, which may include information such as voltage value and collection time. The collected original voltage sequence data can be cleaned and processed, including removing outliers, supplementing missing values, and smoothing data to ensure the accuracy and continuity of the data. The processed voltage data can be standardized and converted into a unified data format and range for subsequent data analysis and modeling. Through the above steps, the original voltage sequence of the preset substation in the power supply area can be obtained, providing a data basis for the subsequent establishment and application of a voltage over-limit prediction model.

[0035] Step S104: performing modal decomposition on the original voltage sequence to obtain multiple modal components.

[0036] Among them, multiple modal components are used to characterize the time-frequency characteristic information of the original voltage series.

[0037] In an optional embodiment, in the specific implementation process of modal decomposition of the original voltage sequence, an empirical mode decomposition (EMD) method can be used to decompose the original voltage sequence into multiple intrinsic mode functions (IMFs), each of which represents different time-frequency feature information in the original sequence. Specifically, the original voltage sequence can be subjected to data preprocessing, including noise removal, smoothing, etc., to ensure the stability and accuracy of the sequence. The preprocessed sequence can be decomposed by empirical mode decomposition. The empirical mode decomposition method connects the local extreme points in the sequence into upper and lower envelopes, and calculates the average value of the envelopes, and then subtracts the average value from the original sequence to obtain a set of local extreme points. The process is continuously iterated until the intrinsic mode function is obtained; it is determined whether the obtained intrinsic mode function meets the definition of the intrinsic mode function, that is, it oscillates up and down on the entire sequence and has the same number of extreme points. If not, iterative processing is performed until the condition is met; the original sequence is decomposed by an empirical mode decomposition to obtain the first round of intrinsic mode functions, and the original sequence is subtracted from the first round of intrinsic mode functions to obtain a residual sequence, and the residual sequence is decomposed by the next round of empirical mode decomposition to obtain more intrinsic mode functions; the above steps are repeated until the number of intrinsic mode functions that meet the conditions is obtained or the residual sequence can no longer be decomposed, and the multiple intrinsic mode functions finally obtained can be used as multiple modal components, each modal component represents different time-frequency feature information in the original sequence, which can be used to further analyze and predict voltage over-limit situations. The above modal decomposition process can also be implemented in combination with modal decomposition methods such as variational mode decomposition. The method of determining multiple modal components can be carried out according to actual needs and is not limited here.

[0038] Step S106, using a preset time series prediction model based on multiple modal components, predicting the voltage condition of the preset substation to obtain a voltage prediction result.

[0039] The above-mentioned preset time series prediction model may refer to a pre-selected model or algorithm that can perform time series prediction on multiple modal components. The preset time series prediction model may adopt a time series prediction model (Transformer) and the like. The preset time series prediction model may be specifically determined according to actual needs and is not limited here.

[0040] In an optional embodiment, a preset time series prediction model can be used to predict the voltage condition of a preset substation based on multiple modal components. Specifically, a time series prediction model suitable for predicting voltage over-limit can be selected, and the selected model can be trained using historical data to adjust model parameters to improve prediction accuracy. The performance of the model can be evaluated using methods such as cross-validation. The trained model can be used to predict the voltage in a future period of time to obtain a voltage prediction result. Control measures can be taken in advance based on the prediction results to avoid voltage over-limit. The prediction results can be evaluated, and the difference between the predicted value and the actual value can be compared to evaluate the accuracy and reliability of the model. The model parameters can be adjusted or the model algorithm can be improved based on the evaluation results. Through the above steps, the preset time series prediction model can be used to accurately predict the voltage condition of the preset substation based on multiple modal components, and the possibility of voltage over-limit can be discovered in advance to ensure the safe and stable operation of the power grid.

[0041] Step S108, determining the over-limit prediction result of the preset substation based on the voltage prediction result and the preset standard voltage range.

[0042] Among them, the over-limit prediction result is used to characterize the probability of voltage over-limit situation occurring in the preset substation.

[0043] The above-mentioned preset standard voltage range is used to represent a predetermined normal voltage range that is not in a voltage over-limit situation. The preset standard voltage range can be determined according to actual needs and is not limited here.

[0044] In an optional embodiment, a standard voltage range for a preset substation can be determined based on the actual needs of the power industry, which may include an upper limit and a lower limit. The voltage prediction result predicted by the model can be compared with the preset standard voltage range to determine whether there is a voltage over-limit situation, and then the over-limit prediction result of the preset substation can be determined. The prediction result can be verified and adjusted based on the preset standard voltage range and actual conditions. Through the above steps, the over-limit prediction result of the preset substation can be determined based on the voltage prediction result and the preset standard voltage range, and then the probability of voltage over-limit situation in the preset substation can be characterized, providing data support for power system operation and management.

[0045] In an embodiment of the present invention, a method for predicting an over-limit voltage in a substation is provided, comprising: obtaining an original voltage sequence of a preset substation in a power supply area, wherein the preset substation is used to characterize a power supply sub-area in a preset power supply area, and the original voltage sequence data is used to represent data of the voltage data of the preset substation collected changing with a time series; performing modal decomposition on the original voltage sequence to obtain a plurality of modal components, wherein the plurality of modal components are used to characterize the time-frequency characteristic information of the original voltage sequence; predicting the voltage condition of the preset substation based on the plurality of modal components using a preset time series prediction model to obtain a voltage prediction result; determining an over-limit prediction result of the preset substation based on the voltage prediction result and a preset standard voltage range, wherein the over-limit prediction result is used to characterize the probability of a voltage over-limit condition occurring in the preset substation. It is easy to notice that the present application utilizes modal decomposition to process the original voltage sequence, which can better extract the time-frequency characteristic information in the original data and decompose the complex voltage data into multiple simple modal components, which is conducive to more accurate analysis and prediction of voltage change trends. The preset time series prediction model is used to make predictions based on multiple modal components, which can more comprehensively consider the temporal and spatial characteristics of the voltage data and improve the accuracy and stability of the prediction. By setting a preset standard voltage range and combining the voltage prediction results, the voltage over-limit situation of the preset substation can be timely discovered and predicted, thereby effectively improving the safety and stability of the power grid operation. The advantages of modal decomposition and prediction models are utilized to conduct in-depth analysis and prediction of voltage data, thereby improving the accuracy and reliability of the prediction, and thus solving the technical problem of low efficiency in predicting over-limit of substation voltage in related technologies.

[0046] Optionally, the preset time series prediction model includes an encoder module, a self-attention module and a decoder module; the preset time series prediction model is used to predict the voltage condition of the preset substation based on multiple modal components to obtain a voltage prediction result, including: using the encoder module to extract features of multiple modal components to obtain multiple sequence features; using the self-attention module to perform weight prediction on multiple modal components to obtain self-attention weights; using the decoder module to fuse multiple sequence features and self-attention weights to obtain a voltage prediction result.

[0047] In an optional embodiment, data of multiple modal components can be input into an encoder module. The encoder module can adopt a structure such as a recurrent neural network or a convolutional neural network to extract features of the input data. The encoder module can encode the data of each modal component into a feature vector to obtain multiple sequence features. Then, the self-attention module can be used to perform weight prediction on the features of the multiple modal components. The self-attention mechanism can help the model automatically focus on the parts that are more important to the current task during the learning process. By calculating the weight of each feature at different time steps, the associated information in the sequence data can be better captured. Finally, the decoder module can be used to fuse the multiple sequence features and the self-attention weights to obtain a voltage prediction result. The decoder module can be used to decode the fused feature vector into a final prediction result. The output of the decoder module is the voltage prediction result for the preset substation voltage condition. Through the above steps, the preset time series prediction model can effectively predict the over-limit situation of the substation voltage and obtain accurate voltage prediction results.

[0048] Optionally, based on the voltage prediction result and the preset standard voltage range, the over-limit prediction result of the preset substation is determined, including: obtaining voltage over-limit data of the preset substation when the voltage is over-limit; determining the voltage over-limit factor weight of the preset substation when the voltage is over-limit based on the voltage over-limit data, wherein the voltage over-limit factor weight is used to characterize the weight of each influencing factor when the preset substation is in the voltage over-limit situation; determining the over-limit prediction result based on the voltage over-limit parameter weight, the voltage prediction result and the preset standard voltage range.

[0049] In an optional embodiment, voltage over-limit data of a preset substation in a voltage over-limit situation can be obtained, and historical substation voltage data, including voltage value, time and other information, can be collected and sorted. By analyzing these data, the situation of the substation voltage over-limit, that is, the influencing factors of the voltage value exceeding the preset standard voltage range, can be identified; then, the weight of the voltage over-limit factor of the preset substation in the voltage over-limit situation can be determined. In the case of voltage over-limit, it may be affected by various factors, such as load changes, power supply system failures, etc. By analyzing the historical data, the degree of influence of these factors on the voltage over-limit can be determined, and then the weight of each factor can be determined; finally, the over-limit prediction result can be determined. Based on the voltage prediction result and the preset standard voltage range, combined with the weight of the voltage over-limit factor, an over-limit prediction can be performed. For example, based on the predicted load change and the power supply system status, it is predicted whether the voltage of the substation will exceed the limit at a certain moment in the future. If the prediction result shows that the voltage may exceed the limit, it is necessary to take corresponding measures to prevent the voltage from exceeding the limit. By analyzing and modeling the historical data, the over-limit prediction result of the preset substation can be determined, so that timely measures can be taken to ensure the stability and safety of the power grid operation.

[0050] Optionally, the method also includes: obtaining normal voltage data of the power supply area when the voltage is not exceeding the limit and the geographical location information of the preset substation; determining the initial standard voltage range based on the normal voltage data; matching the geographical location information with the initial standard voltage range to obtain the preset standard voltage range.

[0051] In an optional embodiment, taking into account that there may be differences in the preset standard voltage ranges corresponding to different power supply areas, the present application proposes that normal voltage data of the power supply area when the voltage is not over-limit and geographical location information of the preset substation can be obtained, and historical voltage data of the power supply area can be collected and sorted, including voltage data of each substation, which can be voltage data under normal conditions, that is, no voltage over-limit situation occurs, and geographical location information of each substation can be obtained, including longitude and latitude and other information; then, the initial standard voltage range can be determined based on the normal voltage data, and the normal voltage range of each substation can be determined by analyzing the historical voltage data, and a reasonable standard voltage range can be determined by calculating the average voltage value of each substation and the standard deviation of the voltage. Quasi-voltage range, the voltage range can be set to the average value plus or minus a reasonable standard deviation; finally, the geographic location information can be matched with the initial standard voltage range to obtain a preset standard voltage range, the geographic location information of each substation can be matched with its corresponding standard voltage range, and the preset standard voltage range of each substation can be obtained. Different standard voltage ranges can be determined according to different geographic locations for subsequent voltage over-limit prediction and monitoring. Through the above steps, it is possible to obtain normal voltage data in the power supply area when the voltage is not over-limit and the geographic location information of the preset substation, and determine the initial standard voltage range based on these data, and finally match the geographic location information with the initial standard voltage range to obtain the preset standard voltage range.

[0052] Optionally, determining an initial standard voltage range based on normal voltage data includes: obtaining the maximum value, minimum value, variance and standard deviation of the normal voltage data; determining an upper limit percentage of voltage floating based on a first difference between the maximum value and the variance; determining a lower limit percentage of voltage floating based on a second difference between the minimum value and the variance; and determining an initial standard voltage range based on the standard deviation, the upper limit percentage of voltage floating and the lower limit percentage of voltage floating.

[0053] In an optional embodiment, an initial standard voltage range can be determined. Specifically, the maximum value, minimum value, variance and standard deviation of normal voltage data can be obtained, the normal voltage data of the substation can be collected and sorted, and the maximum value, minimum value, variance and standard of these data can be calculated; the voltage floating upper limit percentage can be determined based on the first difference between the maximum value and the variance, the product of the maximum value and the variance can be calculated, and then the result is divided by 100 to obtain the voltage floating upper limit percentage; the voltage floating lower limit percentage can be determined based on the second difference between the minimum value and the variance, the product of the minimum value and the variance can be calculated, and then the result is divided by 100 to obtain the voltage floating lower limit percentage; finally, the initial standard voltage range can be determined based on the standard deviation, the voltage floating upper limit percentage and the voltage floating lower limit percentage, and the initial standard voltage range can be calculated according to the calculated standard deviation, the voltage floating upper limit percentage and the voltage floating lower limit percentage with the average value of the normal voltage data respectively. Through the above steps, the initial standard voltage range can be determined based on the normal voltage data, thereby providing basic data and reference range for the over-limit prediction of the substation voltage.

[0054] Optionally, performing modal decomposition on the original voltage sequence to obtain multiple modal components includes: performing empirical modal decomposition on the original voltage sequence to obtain multiple initial modal components; performing variational modal decomposition on the multiple initial modal components to obtain multiple modal components.

[0055] In an optional embodiment, the original voltage sequence can be subjected to empirical mode decomposition (EMD), and the local extreme value points of the original voltage sequence can be searched, that is, the maximum and minimum points in the sequence are found, and then, the upper and lower envelopes of the sequence are obtained by connecting the maximum and minimum values ​​into upper and lower envelopes, and then, the average value of the sequence is calculated, that is, the average value of the upper and lower envelopes is taken as the average value of the sequence, and finally, the original sequence is subtracted from its average value to obtain the remaining part of the sequence, and the above steps are repeated until the remaining part is a stationary sequence, that is, the initial modal component is obtained; the multiple initial modal components are subjected to variational mode decomposition (Variational Mode Decomposition). Decomposition (VMD) can determine the parameters of variational modal decomposition, such as the number of decomposition layers, regularization parameters, etc. Then, by solving the optimization problem, the initial modal component is decomposed into multiple modal components, so that each modal component is as close as possible to a certain frequency band of the original signal. Then, the optimization problem is solved in an iterative manner to obtain multiple modal components. Finally, the obtained multiple modal components are reconstructed to obtain the predicted voltage over-limit situation. Through the above steps, the original voltage sequence can be modally decomposed to obtain multiple modal components, and then the over-limit prediction of the substation voltage can be performed.

[0056] The technical solution proposed in the present application is described below in combination with an optional application scenario. The present application proposes a method of using empirical mode decomposition-improved sparrow search algorithm-variational mode decomposition (EMD-ISSA-VMD) and a model (Informer) to predict voltage over-limit in a substation. First, the pre-processed data is subjected to EMD processing to achieve preliminary decomposition of the data, obtain multiple initial modal components, calculate the permutation entropy value of each modal component, and perform cluster analysis on these permutation entropy values ​​through the K-means clustering method, in order to simplify the dimension of the input feature sequence; for the high-frequency sequence existing after the preliminary decomposition, the VMD optimized by ISSA is used for further decomposition, and is spliced ​​with the low-frequency sequence obtained by the preliminary decomposition to form a new modal component, that is, to obtain the above-mentioned multiple modal components; the model (Informer) is used to predict each modal component obtained, and the prediction results are superimposed; based on the voltage over-limit data, the key factors affecting the voltage over-limit are extracted to provide important input information for predicting future voltage over-limit. The prediction algorithm provided by the present application can predict the probability of voltage over-limit events in the future period so that corresponding preventive measures can be taken.

[0057] The present application proposes a method of using empirical mode decomposition-improved sparrow search algorithm-variational mode decomposition (EMD-ISSA-VMD) and a model (Informer) to predict voltage over-limit in a substation, and predict the probability of occurrence of voltage over-limit events in a future period of time, so as to take corresponding preventive measures. The method may include the following steps: collecting historical voltage time series data and weather data of a substation, or the above-mentioned original voltage series; in view of the non-stationarity of the voltage signal and in order to extract the characteristics of the voltage data, the EMD can be used to pre-process the voltage data to obtain a series of intrinsic mode functions IMFs and a residual, each IMFs represents a component of different frequencies in the voltage data, and the residual can reveal the overall trend of the voltage data; calculating the permutation entropy of the above-mentioned IMFs and residuals, and then executing the K-means clustering algorithm to identify and screen out the time series of high-frequency components. In order to further simplify the structure of the screened high-frequency signal, a secondary decomposition strategy can be used to perform additional mode decomposition processing on the high-frequency signal sequence. In this process, the high-frequency sequence can be processed using the optimized variational mode decomposition (VMD) method, and then merged with the original low-frequency sequence to construct a new modal component, that is, to obtain multiple modal components. This series of operations aims to improve the resolution of time series data and the accuracy of the prediction model.

[0058] Next, a prediction model based on the model (Informer) can be constructed, which can be the preset time series prediction model mentioned above, and the previously obtained multiple modal components are used as input features. First, the training set data is imported into the model (Informer) to obtain the prediction output of each modal component. Subsequently, these prediction components are superimposed to form a comprehensive prediction result, that is, the voltage prediction result mentioned above; then, the comprehensive prediction result can be compared with the actual measurement value, the prediction error can be calculated, and the prediction error can be evaluated according to the defined loss function and the gradient information can be calculated accordingly, and then the model parameters can be optimized and adjusted through the gradient descent algorithm.

[0059] This application can use the trained model to predict the test set data, superimpose the prediction results of each component, and use MAE, RMSE and R 2 Evaluation indicators are used to evaluate the accuracy of model prediction. Then, voltage data during normal operation are collected, and the variance of the data is calculated as the standard voltage. The percentage difference between the maximum value and the variance is the upper limit percentage of voltage fluctuation, and the percentage difference between the minimum value and the variance is the lower limit percentage of voltage fluctuation. According to the above process, the normal operating voltage range is defined, and exceeding this range is defined as voltage over-limit.

[0060] This application can summarize the records of historical voltage over-limit events, including over-limit voltage values, power load conditions, ambient temperature, relative humidity, holiday signs, and other abnormal events. By statistically analyzing these data, the relative contribution ratio of each influencing factor in each voltage over-limit event is calculated. Subsequently, the key information of the future time period of the substation is monitored and collected in real time, and this information is integrated and input into the voltage over-limit prediction model. Based on this, the model will predict the probability of voltage over-limit events in the future time period to assist decision makers in taking corresponding preventive measures and emergency response strategies.

[0061] The voltage data of the substations in different time periods as well as the corresponding weather conditions and load conditions can be collected, and the data can be preprocessed. The z-score method can be used to remove outliers in the voltage data, the median filter can be used to remove noise, and the missing values ​​can be processed by interpolation. Finally, the data can be standardized and divided into training and test sets.

[0062] For the preprocessed data, we can first use EMD to perform a preliminary decomposition to obtain multiple modal components, then calculate the permutation entropy of the modal components, and perform K-means clustering on the permutation entropy values ​​to select high-frequency sequences. In order to reduce the complexity of the time series, we use the optimized VMD to decompose the high-frequency sequences again. After decomposition, we recalculate the permutation entropy and concatenate the modal component sequences with similar permutation entropy to reduce the number of input feature sequences and improve computational efficiency.

[0063] The calculation formula for calculating the permutation entropy and reconstructing the signal into m-dimensional space can be expressed as:

[0064]

[0065] Wherein, t is the delay time; m is the embedding dimension; R is the number of reconstructed vectors, R = n-(m-1)t.

[0066] The row vector of the matrix S can be defined as the reconstruction vector D(l), and each reconstruction component can be rearranged in ascending order. The calculation formula can be expressed as:

[0067] D(l)={k 1 ,k 2 ,…,k m}, l = 1, 2, ..., v, and v ≤ m;

[0068] The probability of occurrence of each symbol sequence can be calculated {P 1 ,P 2 ,…,P v}; According to the calculation formula of Shannon entropy, the calculation formula of the permutation entropy of the time series x(i) can be obtained

[0069]

[0070] In the parameter optimization process for variational mode decomposition (VMD), this application adopts an advanced improved sparrow search algorithm (ISSA). The initial step involves defining the key parameters of VMD, including the number of modes, penalty factors, and noise tolerance. Subsequently, the relevant parameters of the improved sparrow search algorithm are set in detail, covering factors such as population size, maximum number of iterations, and the ratio of discoverers to joiners and vigilants. On this basis, the parameters of VMD are encoded and mapped to the sparrow positions in ISSA, where each position vector represents a set of VMD parameter configurations. By designing a fitness function, the fitness value of each position vector is calculated to evaluate the performance of the parameter configuration. During the iteration process, the positions of the discoverer, joiner, and vigilant are updated according to the algorithm rules. In order to balance the global search and local utilization, adaptive control parameters can be introduced to optimize the position distribution of sparrows in the population and gradually converge to the optimal VMD parameters. The iterative process continues until the predetermined maximum number of iterations is reached, at which time the algorithm stops iterating and outputs the optimized VMD parameters as the final result. This process ensures the efficiency and optimality of parameter configuration and improves the application performance of VMD in signal processing.

[0071] ISSA optimizes the decomposition mode number K and the balance constraint weight Alpha of VMD. The decomposition mode number K value of VMD is optimized to be 7 and the balance constraint weight Alpha value is 101. The optimization objective function can be expressed as:

[0072]

[0073] The minimum envelope entropy can be used as a fitness function.

[0074] In the prediction process of executing the Informer model, the new modal component sequence obtained by the secondary modal decomposition can first be imported into the prediction model as input data. Subsequently, the encoder unit processes the input modal component sequence to extract the key features in the sequence. In this process, a self-attention mechanism consisting of multiple multi-headed probabilistic sparse self-attention (ProbSparse Self-Attention) modules and an attention distillation mechanism is introduced to focus on the key information in the sequence. Next, the decoder module synthesizes the predicted values ​​of future time steps based on the output results of the encoder and the corresponding attention weights. In view of the fact that the data is standardized before prediction, the present application implements an inverse normalization step for the output prediction results of the model to ensure that the predicted values ​​are restored to the original data scale.

[0075] The mean absolute error (MAE) and root mean square error (RMSE) evaluation indicators are used to evaluate the accuracy of model prediction. MAE can give an intuitive measure of the error between the predicted value and the true value. Compared with MAE, RMSE gives higher weight to larger errors. When the error is large, RMSE will give a higher error value.

[0076]

[0077] Where n represents the number of data points, y i represents the i-th actual observation value, Represents the i-th predicted value.

[0078] The normal voltage range can be defined based on the normal voltage data. Any value beyond this range is defined as voltage over-limit. The voltage range in different geographical locations may be slightly different. The voltage data during normal operation is collected, and the variance of the data is calculated as the standard voltage. The percentage difference between the maximum value and the variance is the upper limit percentage of voltage floating, and the percentage difference between the minimum value and the variance is the lower limit percentage of voltage floating. The normal operating voltage range is defined according to the above process, and any value exceeding this range is defined as voltage over-limit.

[0079] Based on the voltage over-limit data, the key factors affecting the voltage over-limit can be extracted to provide important input information for predicting future voltage over-limit. Real-time monitoring and collection of key information of the substation in the future period can be integrated into the voltage over-limit prediction model. The model will predict the probability of voltage over-limit events in the future period to assist decision makers in taking corresponding preventive measures and emergency response strategies.

[0080] Figure 2 FIG. 1 is a flow chart of an optional method for predicting voltage over-limit in a transformer area according to an embodiment of the present invention. Figure 2 As shown, S202, obtaining the original voltage sequence of a preset substation in the power supply area; S204, performing modal decomposition on the original voltage sequence to obtain multiple modal components; S206, using a preset time series prediction model to predict the voltage condition of the preset substation based on multiple modal components to obtain a voltage prediction result; S208, obtaining the voltage over-limit data of the preset substation when it is in the voltage over-limit situation; determining the voltage over-limit factor weight of the preset substation when it is in the voltage over-limit situation based on the voltage over-limit data; determining the over-limit prediction result based on the voltage over-limit parameter weight, the voltage prediction result and the preset standard voltage range.

[0081] Figure 3 is a schematic diagram of a plurality of optional initial modal components according to an embodiment of the present invention, such as Figure 3 As shown, the abscissa represents time t / h, and the ordinate represents the original signal, that is, the original voltage sequence, and IMF1, IMF2, IMF3, IMF4, IMF5, IMF6, IMF7, IMF8, IMF9 and IMF10 obtained in the present application, that is, multiple initial modal components.

[0082] Figure 4 is a schematic diagram of an optional modal function clustering according to an embodiment of the present invention, such as Figure 4 As shown in the figure, the horizontal axis represents time, and the vertical axis represents Co-IMF1, Co-IMF2 and Co-IMF3, that is, the K-means clustering results of multiple initial modal components. Clustering is performed by calculating the permutation entropy value, and the modal components are divided into three categories: high-frequency components, medium-frequency components and low-frequency components, which can be used to determine multiple modal components later.

[0083] Figure 5 is a schematic diagram of an optional method of optimizing the number of variational mode decomposition iterations using an improved sparrow search algorithm according to an embodiment of the present invention, such as Figure 5 As shown, the horizontal axis represents the number of iterations, and the vertical axis represents the fitness value. It shows the number of iterations of optimizing the variational mode decomposition using the improved sparrow search algorithm. It can be seen that the fitness value decreases with the increase of the number of iterations.

[0084] Figure 6 FIG. 1 is a flow chart of another optional method for predicting voltage over-limit in a substation according to an embodiment of the present invention. Figure 6As shown, at the beginning of the process, EMD is performed on the original voltage sequence to obtain IMF0, IMF1...IMFk, etc., and PE clustering is performed on the obtained IMF0, IMF1...IMFk, etc. to obtain IMFj...IMFN, etc.; the parameters and population positions of VMD and ISSA are initialized, the fitness value is calculated to evaluate the initial population, the fitness value is calculated, the positions of the discoverer, the joiner and the sentinel are updated, the boundary is processed, the optimal solution is selected, and it is determined whether the maximum number of iterations has been reached. When the maximum number of iterations has not been reached, the fitness value is calculated, and when the maximum number of iterations has been reached, the optimal parameters are output, and the improved sparrow search algorithm is used to optimize the VMD secondary decomposition. The improved sparrow search algorithm is used to optimize the VMD secondary decomposition to process IMFj...IMFN, etc. to obtain imf0, imf1...imfk, etc., and Informer is used to process imf0, imf1...imfk, etc., the sequence is denormalized and superimposed, the error is evaluated, the voltage over-limit information is extracted, and the probability of voltage over-limit occurrence in the future is predicted, and the process ends.

[0085] The future voltage over-limit occurrence probability here may refer to the over-limit prediction result mentioned above.

[0086] According to another aspect of an embodiment of the present invention, a device for predicting an over-limit of a substation voltage is provided. The device can execute the method for predicting an over-limit of a substation voltage of the above embodiment. The specific implementation method and preferred application scenario are the same as those of the above embodiment and will not be described in detail here.

[0087] Figure 7 is a schematic diagram of a device for predicting voltage over-limit in a substation according to an embodiment of the present application, such as Figure 7 As shown, the apparatus includes the following: an acquisition module 702 , a decomposition module 704 , a prediction module 706 and a determination module 708 .

[0088] Among them, the acquisition module is used to obtain the original voltage sequence of the preset substation in the power supply area, wherein the preset substation is used to characterize the power supply sub-area in the preset power supply area, and the original voltage sequence data is used to represent the data of the voltage data of the preset substation collected changing with the time series; the decomposition module is used to perform modal decomposition on the original voltage sequence to obtain multiple modal components, wherein the multiple modal components are used to characterize the time-frequency characteristic information of the original voltage sequence; the prediction module is used to use the preset time series prediction model to predict the voltage condition of the preset substation based on multiple modal components to obtain the voltage prediction result; the determination module is used to determine the over-limit prediction result of the preset substation based on the voltage prediction result and the preset standard voltage range, wherein the over-limit prediction result is used to characterize the probability of voltage over-limit in the preset substation.

[0089] Among them, the preset time series prediction model includes an encoder module, a self-attention module and a decoder module; the prediction module is also used to use the encoder module to extract features of multiple modal components to obtain multiple sequence features; use the self-attention module to perform weight prediction on multiple modal components to obtain self-attention weights; use the decoder module to fuse multiple sequence features and self-attention weights to obtain voltage prediction results.

[0090] Among them, the determination module is also used to obtain voltage over-limit data when the preset substation is in a voltage over-limit situation; determine the voltage over-limit factor weight of the preset substation when the voltage is over-limit based on the voltage over-limit data, wherein the voltage over-limit factor weight is used to characterize the weight of each influencing factor when the preset substation is in a voltage over-limit situation; determine the over-limit prediction result based on the voltage over-limit parameter weight, the voltage prediction result and the preset standard voltage range.

[0091] Among them, the determination module is also used to obtain normal voltage data of the power supply area when the voltage is not exceeding the limit and the geographical location information of the preset substation; determine the initial standard voltage range based on the normal voltage data; match the geographical location information with the initial standard voltage range to obtain the preset standard voltage range.

[0092] Among them, the determination module is also used to obtain the maximum value, minimum value, variance and standard deviation of normal voltage data; determine the upper limit percentage of voltage floating based on the first difference between the maximum value and the variance; determine the lower limit percentage of voltage floating based on the second difference between the minimum value and the variance; determine the initial standard voltage range based on the standard deviation, the upper limit percentage of voltage floating and the lower limit percentage of voltage floating.

[0093] Among them, the decomposition module is also used to perform empirical mode decomposition on the original voltage sequence to obtain multiple initial mode components; and perform variational mode decomposition on the multiple initial mode components to obtain multiple mode components.

[0094] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0095] The above-mentioned memory may refer to a device inside a computer for storing data and programs, and may include memory, hard disk, etc., wherein the memory may be used to temporarily store running programs and data, the hard disk may be used to store programs and data for a long time, and the memory may be used to enable the computer to read and write data, and execute programs; the above-mentioned processor may be responsible for executing instructions in computer programs and performing data processing, and may be responsible for controlling and executing various operations, including arithmetic operations, logical operations, data transmission, etc.

[0096] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0097] The above-mentioned computer storage medium may refer to a medium in a computer memory used to store certain discontinuous physical quantities. Computer storage media mainly include semiconductors, magnetic cores, magnetic drums, magnetic tapes, laser disks, etc.; the stored program included in the computer-readable storage medium may be a set of instructions that can be recognized and executed by a computer, running on an electronic computer, and is an information tool that meets certain needs of people.

[0098] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0099] The above-mentioned computer program product may refer to a software program that has been written, tested and released and can be run on a computer or other device. The computer program product may include an application, an operating system, tool software, etc., which is used to implement specific functions or solve specific problems.

[0100] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0101] The above-mentioned non-volatile computer-readable storage medium may refer to a medium for storing data. The non-volatile computer-readable storage medium can keep the data from being lost when the power is off, and can be used to store long-term data, such as operating systems, applications, and user files. The non-volatile storage medium may include hard disk drives, solid-state drives, optical disks, and flash memory storage devices, etc.

[0102] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0103] The above-mentioned computer program may refer to a collection of instructions used to tell a computer to perform a specific task or operation. A computer program may be written by a programmer using a specific programming language and may include algorithms, data structures, logic, and control flows. A computer program may be used for a variety of purposes, including application software, operating systems, and the like.

[0104] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0107] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0108] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0109] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for predicting voltage over-limit in a substation, characterized in that: include: Acquire an original voltage sequence of a preset area in the power supply area, wherein the preset area is used to characterize a preset power supply area in the power supply area, and the original voltage sequence data is used to represent the data of the voltage data of the preset area collected changing with time series; Performing modal decomposition on the original voltage sequence to obtain multiple modal components, wherein the multiple modal components are used to characterize time-frequency characteristic information of the original voltage sequence; Using a preset time series prediction model to predict the voltage condition of the preset substation based on the multiple modal components, to obtain a voltage prediction result; Based on the voltage prediction result and a preset standard voltage range, an over-limit prediction result of the preset substation is determined, wherein the over-limit prediction result is used to characterize the probability of a voltage over-limit situation occurring in the preset substation.

2. The method for predicting over-limit voltage in a transformer substation according to claim 1, characterized in that: The preset time series prediction model includes an encoder module, a self-attention module and a decoder module; The voltage condition of the preset substation is predicted based on the multiple modal components using a preset time series prediction model to obtain a voltage prediction result, including: Using the encoder module to extract features from the multiple modal components to obtain multiple sequence features; Using the self-attention module to perform weight prediction on the multiple modal components to obtain self-attention weights; The decoder module is used to fuse the multiple sequence features and the self-attention weights to obtain the voltage prediction result.

3. The method for predicting voltage over-limit in a substation area according to claim 1, characterized in that: Determining the over-limit prediction result of the preset station area based on the voltage prediction result and the preset standard voltage range includes: Acquiring voltage over-limit data of the preset station area when the voltage is under the voltage over-limit condition; Determine, based on the voltage over-limit data, a voltage over-limit factor weight when the preset substation is in the voltage over-limit situation, wherein the voltage over-limit factor weight is used to characterize the weight of each influencing factor when the preset substation is in the voltage over-limit situation; The voltage over-limit prediction result is determined based on the voltage over-limit parameter weight, the voltage prediction result and the preset standard voltage range.

4. The method for predicting over-limit voltage in a transformer substation according to claim 1, characterized in that: The method further comprises: Acquire normal voltage data of the power supply area when the voltage is within the voltage limit and geographical location information of the preset substation area; Determine an initial standard voltage range based on the normal voltage data; The geographical location information is matched with the initial standard voltage range to obtain the preset standard voltage range.

5. The method for predicting over-limit voltage in a substation according to claim 4, characterized in that: Determining an initial standard voltage range based on the normal voltage data includes: Obtaining the maximum value, minimum value, variance and standard deviation of the normal voltage data; Determining a voltage floating upper limit percentage based on a first difference between the maximum value and the variance; Determining a voltage floating lower limit percentage based on a second difference between the minimum value and the variance; The initial standard voltage range is determined based on the standard deviation, the voltage floating upper limit percentage, and the voltage floating lower limit percentage.

6. The method for predicting over-limit voltage in a substation according to claim 5, characterized in that: The original voltage sequence is subjected to modal decomposition to obtain multiple modal components, including: Performing empirical mode decomposition on the original voltage sequence to obtain a plurality of initial mode components; The multiple initial modal components are subjected to variational modal decomposition to obtain the multiple modal components.

7. A device for predicting voltage over-limit in a transformer substation, characterized in that: include: An acquisition module is used to acquire an original voltage sequence of a preset area in a power supply region, wherein the preset area is used to characterize a preset power supply area in the power supply region, and the original voltage sequence data is used to represent the data of the voltage data of the preset area collected changing with time series; A decomposition module, used for performing modal decomposition on the original voltage sequence to obtain multiple modal components, wherein the multiple modal components are used to characterize the time-frequency characteristic information of the original voltage sequence; A prediction module, used to predict the voltage condition of the preset substation based on the multiple modal components using a preset time series prediction model to obtain a voltage prediction result; A determination module is used to determine the over-limit prediction result of the preset substation based on the voltage prediction result and a preset standard voltage range, wherein the over-limit prediction result is used to characterize the probability of voltage over-limit situation occurring in the preset substation.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein when the program is run, the method for predicting the voltage over-limit in a substation area as described in any one of claims 1 to 6 is executed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the method for predicting the voltage over-limit of a substation area as claimed in any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for predicting the voltage crossing of a substation according to any one of claims 1 to 6.

Images