Transformer area line loss abnormity identification method and device, storage medium and electronic equipment

Abstract

The invention discloses a transformer area line loss abnormity identification method and device, a storage medium and electronic equipment. The method comprises the steps that a predetermined sliding window is adopted to collect operation data of a target transformer area, and the operation data comprises first operation data of a current date and second operation data of a plurality of historical dates before the current date; performing calculation based on the first operation data, the second operation data, a preset confidence coefficient and a conventional boundary value of a line loss rate of a predetermined transformer area to obtain a first line loss abnormal dynamic threshold value and a second line loss abnormal dynamic threshold value of the current date; based on the first line loss abnormity dynamic threshold value, the second line loss abnormity dynamic threshold value and the operation data, line loss abnormity evaluation is carried out on the target station area, and initial evaluation results corresponding to different evaluation indexes are obtained; and based on each initial evaluation result, carrying out transformer area line loss abnormity comprehensive identification to obtain a line loss abnormity comprehensive identification result of the target transformer area. According to the method, the accuracy of line loss identification can be improved.

Description

Technical Field

[0001] The present invention relates to the field of abnormal line loss identification in a transformer substation, and in particular to a method, device, storage medium and electronic equipment for abnormal line loss identification in a transformer substation. Background Art

[0002] In the current power grid operation and management landscape, with socioeconomic development, electricity demand continues to rise, and the scale of the power grid is also expanding. Substations, as the fundamental units of the power supply system, are numerous and widely distributed, and their operational status directly impacts the stability and energy efficiency of the power system. The overall development trend of the power industry has necessitated the adoption of intelligent and refined management models, which raises the bar for accurate and scientific line loss management in substations. Substation operation is influenced by a variety of complex factors. Load characteristics vary significantly across substations. Substations primarily used by industrial users experience significant load fluctuations, with large peak-to-valley variations; whereas substations primarily used by residential users experience more concentrated periods of time. Furthermore, the user base is complex and diverse, with commercial, residential, and industrial users exhibiting distinct differences in their electricity usage patterns and needs. Furthermore, variations in line layout, such as line length, conductor material, and transformer configuration, can affect substation line losses to varying degrees. However, existing methods for identifying abnormal substation line losses present numerous challenges. On the one hand, the criteria for determining abnormal line losses are overly simplistic, relying primarily on a single metric, the "line loss rate indicator," to identify abnormal line losses. This completely ignores the diversity and complexity of substation operations. Line loss situations inherently vary from substation to substation due to differences in load characteristics, user mix, and line layout. A single metric cannot accurately reflect the true operational status of a substation. On the other hand, misjudgments and omissions are prominent. In some substations, due to seasonal electricity demand or the consumption patterns of specific user groups, line loss rates fluctuate during specific periods, making it easy to mistakenly identify abnormal line losses. Meanwhile, in some substations with potential line loss issues, their potential problems go unnoticed because the line loss rates are within the so-called "normal range." This makes it difficult for staff to accurately pinpoint the problem, resulting in a waste of human and material resources and severely restricting improvements in grid operational efficiency and economic benefits, failing to meet the actual needs of refined grid management. Summary of the Invention

[0003] In view of this, the present invention provides a method, device, storage medium and electronic device for identifying abnormal line loss in a substation area, the main purpose of which is to solve the problem of low accuracy of the current method for identifying abnormal line loss in a substation area.

[0004] To solve the above problems, the present application provides a method for identifying abnormal line loss in a transformer area, comprising:

[0005] Using a predetermined sliding window to collect operating data of a target substation, the operating data includes first operating data of a current date and second operating data corresponding to a plurality of historical dates before the current date;

[0006] Calculating and processing based on the first operating data and each of the second operating data, a preset confidence coefficient, and a traditional boundary value of a predetermined area line loss rate, to obtain a first line loss abnormal dynamic threshold value and a second line loss abnormal dynamic threshold value for the current date;

[0007] Performing a line loss anomaly assessment on the target substation based on the first line loss anomaly dynamic threshold, the second line loss anomaly dynamic threshold, and the operating data to obtain initial assessment results corresponding to different assessment indicators;

[0008] Based on each of the initial evaluation results, a comprehensive identification of line loss anomalies in the substation area is performed to obtain a comprehensive identification result of line loss anomalies in the target substation area.

[0009] To solve the above problems, the present application provides a device for identifying abnormal line loss in a transformer area, comprising:

[0010] A collection module, configured to collect operation data of a target substation using a predetermined sliding window, wherein the operation data includes first operation data of a current date and second operation data corresponding to a plurality of historical dates before the current date;

[0011] A calculation module, configured to calculate and process the first and second line loss abnormal dynamic thresholds for the current date based on the first and second operating data, a preset confidence coefficient, and a traditional boundary value of a predetermined substation line loss rate;

[0012] an abnormality assessment module, configured to perform a line loss abnormality assessment on the target substation based on the first line loss abnormality dynamic threshold, the second line loss abnormality dynamic threshold, and the operation data, and obtain initial assessment results corresponding to different assessment indicators;

[0013] The comprehensive identification module is used to perform comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0014] In order to solve the above problems, the present application provides a storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the above-mentioned method for identifying line loss anomalies in a substation area.

[0015] To solve the above problems, the present application provides an electronic device, which includes at least a memory and a processor, wherein a computer program is stored on the memory, and the processor implements the steps of the above-mentioned method for identifying line loss anomalies in a substation when executing the computer program on the memory.

[0016] The beneficial effects of this application are as follows: By collecting rich data such as daily line loss rate, daily power loss, and daily data integrity rate within a predetermined sliding window in the past, this application deeply mines data associations to calculate fluctuation data. On this basis, a model for calculating abnormal thresholds for line loss rates in substations based on sliding window adaptive energy clustering and confidence intervals is constructed. This model breaks through the limitations of traditional fixed thresholds and dynamically adjusts abnormal thresholds based on traditional boundaries and the substation's recent line loss operation. For example, when faced with substations where line loss rates fluctuate due to seasonal electricity consumption or the electricity consumption patterns of special user groups, the model can accurately determine the actual line loss situation, significantly improving the accuracy of identifying abnormal substations and avoiding misjudgments and omissions caused by a single standard. The dynamic threshold adjustment model and multi-dimensional evaluation index system of the present invention fully account for the diversity and complexity of substation operations. Regardless of the complexity of the substation, dynamic thresholds and multi-dimensional evaluation can accurately determine line loss abnormalities. For example, for substations that are significantly affected by seasonality, dynamic thresholds can be used to promptly adjust the judgment criteria. For substations with complex line layouts, the multi-dimensional evaluation mechanism can comprehensively consider various factors for judgment. Therefore, the present invention has wide adaptability and can meet the line loss management needs of different substations.

[0017] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0019] Figure 1 A schematic diagram showing a flow chart of a method for identifying abnormal line loss in a transformer area provided in an embodiment of the present application is shown;

[0020] Figure 2 A schematic diagram showing a flow chart of a method for identifying abnormal line loss in an area provided by another embodiment of the present application is shown;

[0021] Figure 3 A structural block diagram of a device for identifying abnormal line loss in a transformer area provided in another embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0023] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0024] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0025] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0026] It should also be understood that although the present application has been described with reference to certain specific examples, those skilled in the art will readily be able to implement many other equivalent forms of the present application.

[0027] The above and other aspects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0028] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments described are merely examples of the present application and may be implemented in a variety of ways. Familiar and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details described herein are not intended to be limiting, but rather serve merely as a basis and representative basis for the claims to teach those skilled in the art to variously utilize the present application with substantially any suitable detailed structure.

[0029] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may all refer to one or more of the same or different embodiments according to the present application.

[0030] The present application embodiment provides a method for identifying abnormal line loss in a transformer area, such as Figure 1 As shown, including:

[0031] Step S101: using a predetermined sliding window to collect operating data of a target substation, the operating data including first operating data of the current date and second operating data corresponding to a plurality of historical dates before the current date;

[0032] In the specific implementation process of this step, the first operating data and the second operating data include: daily line loss rate Daily power loss W t loss , daily data completeness rate γt , the sampling interval is one day, and the historical data sliding window used for analysis covers N days T , N T It can be taken as 30 days, t represents the tth day in history, and the line loss rate of the substation area is traditionally on the upper limit. and the lower boundary

[0033] Step S102: Calculating and processing based on the first operating data and each of the second operating data, a preset confidence coefficient, and a traditional boundary value of a predetermined substation line loss rate to obtain a first line loss abnormal dynamic threshold value and a second line loss abnormal dynamic threshold value for the current date;

[0034] During the specific implementation of this step, calculations are performed based on the first operating data and each of the second operating data to obtain the line loss rate mean and the line loss rate standard deviation; calculations are performed based on the line loss rate mean, the line loss rate standard deviation, the preset confidence coefficient, and the traditional boundary value of the line loss rate in the predetermined substation to obtain the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold corresponding to the current date.

[0035] Step S103: performing a line loss abnormality assessment on the target substation based on the first line loss abnormality dynamic threshold, the second line loss abnormality dynamic threshold, and the operating data, to obtain initial assessment results corresponding to different assessment indicators;

[0036] During the specific implementation of this step, the daily line loss rate of the current date in the operating data is compared with the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold, respectively, to obtain an initial evaluation result corresponding to the evaluation index of the abnormal category of line loss risk in the substation area;

[0037] Based on the daily line loss rate corresponding to each date in the operating parameters, an adaptive energy clustering method is used to perform calculation and processing, and an initial evaluation result corresponding to the substation line loss rate volatility anomaly category evaluation index is obtained; based on the daily line loss rate of the current date and the daily line loss rate corresponding to the historical dates in the neighborhood of the current date, the initial evaluation result corresponding to the substation line loss aggravation anomaly category evaluation index is determined; based on the daily line loss rate corresponding to each date in the operating parameters, the preset line loss rate upper limit, the preset line loss rate lower limit and the initial evaluation result corresponding to the substation line loss risk anomaly category evaluation index, calculation and processing are performed to obtain an initial evaluation result corresponding to the substation long-term anomaly category evaluation index; based on the daily data completeness rate of the current date in the operating parameters, the substation long-term anomaly category evaluation function is used to perform calculation and processing to obtain an initial evaluation result corresponding to the substation computability anomaly category evaluation index.

[0038] Step S104: performing comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0039] During the specific implementation of this step, a comprehensive identification of line loss anomalies in the substation is performed based on the initial evaluation results, and the sudden high loss anomalies, sudden negative loss anomalies, long-term high loss anomalies, long-term negative loss anomalies, aggravated high loss anomalies, aggravated negative loss anomalies, general high loss anomalies, general negative loss anomalies, and missing number anomalies in the substation are identified in turn to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0040] This application collects rich data, including daily line loss rates, daily power losses, and daily data integrity rates, within a predefined sliding window within a substation area. This data is then mined to correlate and calculate fluctuation data. Based on this data, a model for calculating abnormal line loss rate thresholds in substation areas is constructed using sliding window adaptive energy clustering and confidence intervals. This model transcends the limitations of traditional fixed thresholds by dynamically adjusting the abnormality thresholds based on traditional boundaries and the substation area's recent line loss operation. For example, in substations with seasonal electricity consumption or the electricity usage patterns of specific user groups, the model can accurately determine the true line loss situation, significantly improving the accuracy of identifying abnormal substation areas and avoiding misjudgments and omissions caused by a single criterion. The dynamic threshold adjustment model and multi-dimensional evaluation index system of this invention fully account for the diversity and complexity of substation operations. Regardless of the complexity of the substation, dynamic thresholds and multi-dimensional evaluation can accurately determine line loss anomalies. For example, for substations significantly affected by seasonality, dynamic thresholds can be used to promptly adjust the judgment criteria. For substations with complex line layouts, the multi-dimensional evaluation mechanism can comprehensively consider various factors for judgment. Therefore, this invention has broad adaptability and can meet the line loss management needs of different substations.

[0041] Another embodiment of the present application provides another method for identifying abnormal line loss in a transformer area, such as Figure 2 As shown, including:

[0042] Step S201: using a predetermined sliding window to collect operating data of a target substation, the operating data including first operating data of the current date and second operating data corresponding to a plurality of historical dates before the current date;

[0043] In the specific implementation process of this step, the first operation data and the second operation data include: daily line loss rate Daily power loss W t loss , daily data completeness rate γ t , the sampling interval is one day, and the historical data sliding window used for analysis covers N days T , N TIt can be taken as 30 days, t represents the tth day in history, and the line loss rate of the substation area is traditionally on the upper limit. and the lower boundary

[0044] Step S202: performing calculations based on the first operating data and each of the second operating data to obtain a line loss rate mean and a line loss rate standard deviation;

[0045] During the specific implementation of this step, the average value of the daily line loss rate in the first operation data and each of the second operation data is calculated to obtain the average line loss rate; the calculation formula is as shown in the following formula (1):

[0046]

[0047] The line loss rate standard deviation is obtained by performing calculation based on the daily line loss rate and the average line loss rate in the first operation data and each of the second operation data. The calculation formula is shown in the following formula (2):

[0048]

[0049] in, is the average line loss rate of the substation area; δ sum is the standard deviation of the line loss rate in the substation area; N T The number of days covered by the historical data time window used for analysis, which can be set to 30 days, etc.

[0050] Step S203: performing calculations based on the line loss rate mean, the line loss rate standard deviation, a preset confidence coefficient, and a predetermined area line loss rate traditional boundary value to obtain the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold corresponding to the current date;

[0051] During the specific implementation of this step, a first boundary function is used to perform calculation based on the line loss rate mean, the line loss rate standard deviation, the preset confidence coefficient, and the traditional boundary value of the line loss rate in the predetermined area to obtain a first line loss abnormal dynamic threshold value; the mathematical expression of the first boundary function can be expressed as the following formula (3):

[0052]

[0053] in, is the first line loss abnormal dynamic threshold of the t-th rooftop area, representing the upper threshold of the line loss abnormal dynamic; k is the confidence coefficient, considering the 95% confidence level, the value can be 1.95; The second line loss abnormal dynamic threshold is obtained by using a second boundary function to calculate the line loss rate mean, the line loss rate standard deviation, the preset confidence coefficient, and the traditional boundary value of the predetermined line loss rate in the substation area. The mathematical expression of the second boundary function can be expressed as follows:

[0054]

[0055] in, is the second abnormal dynamic threshold of line loss in the t-th rooftop area, representing the lower threshold of abnormal dynamic line loss; is the traditional lower boundary of the line loss rate in the substation area; λ is the dynamic lower threshold adjustment coefficient, which can be taken as 0.01.

[0056] Step S204: comparing the daily line loss rate of the current date in the operation data with the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold, respectively, to obtain an initial evaluation result corresponding to the evaluation index of the substation line loss risk abnormality category;

[0057] During the specific implementation of this step, the daily line loss rate of the current date in the operating data is compared with the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold respectively to obtain the initial evaluation results corresponding to the evaluation index of the line loss risk abnormality category of the substation area, and the line loss risk abnormality evaluation of the substation area is performed. The judgment standard is shown in the following formula (5):

[0058]

[0059] Among them, M1 is the abnormal line loss risk category of the substation area, including high loss, negative loss, and normal; is the line loss rate of the station area at that time; The upper threshold value of abnormal dynamic line loss in the substation area; It is the lower threshold value of the abnormal dynamic line loss in the substation; specifically, when the daily line loss rate on the current date is greater than the first line loss abnormal dynamic threshold value, the initial evaluation result corresponding to the evaluation index of the abnormal line loss risk category of the substation is a high loss result; when the daily line loss rate on the current date is less than the second line loss abnormal dynamic threshold value, the initial evaluation result corresponding to the evaluation index of the abnormal line loss risk category of the substation is a negative loss result; when the daily line loss rate on the current date is greater than or equal to the second line loss abnormal dynamic threshold value and less than or equal to the first line loss abnormal dynamic threshold value, the initial evaluation result corresponding to the evaluation index of the abnormal line loss risk category of the substation is a normal result.

[0060] Step S205: Calculating and processing the daily line loss rate corresponding to each date in the operating parameters using an adaptive energy clustering method to obtain an initial evaluation result corresponding to an evaluation index of abnormal category of fluctuation of line loss rate in the substation area;

[0061] During the specific implementation of this step, calculation is performed based on the daily line loss rate in the operating parameters to obtain the line loss rate fluctuation value corresponding to each date. The mathematical formula for calculating the line loss rate fluctuation value can be expressed as follows:

[0062]

[0063] in, It is the fluctuation of daily loss rate between the tth day and the t-1th day in the history of the Taiwan area.

[0064] Based on each of the line loss rate fluctuation values, an adaptive energy clustering method is used to determine whether the first operating data is outliers, and an outlier index value is obtained. Specifically, based on the daily power loss data in the operating parameters corresponding to each of the dates, calculation processing is performed to obtain a silhouette coefficient corresponding to the operating parameters on each date. The mathematical formula for calculating the silhouette coefficient can be expressed as follows:

[0065]

[0066] Among them, s t The power loss data W for the sample day t loss Silhouette coefficient; a t The power loss data W for the sample day t loss The average distance to other points in the same cluster; b t The power loss data W for the sample day t loss Average distance to the nearest cluster; Daily power loss data W t loss The average distance a to other points in the same cluster t The mathematical expression of can be expressed as follows:

[0067]

[0068] Among them, W loss Belongs to cluster C i Other sample points of C i is the i-th cluster; For cluster C i The number of sample points, including W t loss ; Sample day power loss data W t loss The average distance b to the nearest other cluster t The mathematical formula for calculating can be expressed as follows:

[0069]

[0070] in, For cluster C l The number of sample points; W t loss Belongs to cluster C i but not of cluster C l ;

[0071] Based on each of the silhouette coefficients, a first optimization model with the goal of maximizing the global silhouette coefficient is solved to obtain the optimal number of clusters, thereby obtaining clusters with the optimal number of clusters. The mathematical expression of the first optimization model can be expressed as follows:

[0072]

[0073] Among them, S k is the global silhouette coefficient; s t is the silhouette coefficient of the sample; k is the number of current clusters; N T The number of days covered by the sliding window of historical data used for analysis; K max is the maximum number of clusters to be traversed, which can be set according to actual needs and can be 3. Based on the daily power loss data in the operating parameters, the second optimization model with the goal of minimizing the sum of the square distances to the cluster centers is solved to obtain the centroid corresponding to each cluster. The mathematical expression of the second optimization model can be expressed as follows:

[0074]

[0075] Among them, J is the minimum intra-class mean square sum, that is, the sum of the square distances of all data points to the center of the cluster to which they belong; k is the number of clusters; μ i is the center of the i-th cluster, that is, the mass value, which is the value to be solved by the second optimization model. If k = 2, it means that there are two cluster centers in this cluster solution;

[0076] The daily line loss rate of the current date in the operation data and each of the centroids are used for calculation and processing to obtain a first distance value. The calculation formula of the first distance value can be expressed as the following formula (12):

[0077]

[0078] Among them, d i,m is the first distance value from the mth sample point to the center in cluster i; is the daily power loss value of the mth sample point in cluster i; μ i is the center of the i-th cluster;

[0079] Based on the daily power loss data and the centroid of the same cluster, the distance standard deviation corresponding to the same cluster is obtained; the calculation formula of the distance standard deviation can be expressed as the following formula (13):

[0080]

[0081] Among them, δ i is the standard deviation of the intra-cluster distance of cluster i; d i,m is the distance from the mth sample point to the center in cluster i; is the mean distance between each point in cluster i and the cluster; For cluster C i The number of sample points is calculated based on the first distance value and the distance standard deviation, and the outlier index value is obtained. Specifically, the target distance from the current day's daily power loss value to the center of each cluster is obtained based on the first distance value and the distance standard deviation. The mathematical formula for calculating the target distance can be expressed as follows:

[0082] d i,t =|W t loss -μ i | (14)

[0083] Among them, d i,t is the current date sample W t loss The target distance to the center of the i-th cluster; W t loss is the daily power loss; μ i is the center of the i-th cluster. The mathematical expression of the outlier index value can be expressed as follows:

[0084]

[0085] Among them, outlier(W t loss ) is the outlier judgment result of the sample on the current date. When it is 1, it means the sample is outlier, and when it is 0, it means the sample is not outlier; d i,t is the current date sample W t loss The distance to the center of the i-th cluster; δ i is the standard deviation of the intra-cluster distance of cluster i.

[0086] Based on the line loss rate fluctuation values, the average value is calculated to obtain the average absolute value of the line loss rate fluctuation. The mathematical formula for calculating the average absolute value of the line loss rate fluctuation can be expressed as follows:

[0087]

[0088] in, is the absolute mean of line loss rate fluctuations; The fluctuation of daily loss rate on day t compared with day t-1 in the station area;

[0089] Based on the line loss rate fluctuation value and the mean of the absolute value of the line loss rate fluctuation, a calculation process is performed to obtain the line loss rate fluctuation standard deviation. The calculation formula of the line loss rate fluctuation standard deviation can be expressed as the following formula (17):

[0090]

[0091] in, is the standard deviation of historical line loss rate fluctuations.

[0092] Based on the outlier index value, the line loss rate fluctuation standard deviation, and the line loss rate fluctuation value, the initial evaluation result corresponding to the abnormal category evaluation index of the line loss rate volatility of the substation area is determined. The abnormality of the line loss volatility is judged according to the evaluation index of the line loss rate volatility coefficient of the substation area, and the judgment mathematical formula is shown in the following formula (18):

[0093]

[0094] Among them, M2 is the abnormal category of line loss rate fluctuation in the substation area, including sudden abnormality and normal; outlier (W t loss ) is the outlier judgment result of the sample on the current date. When it is 1, it means the sample is outlier, and when it is 0, it means the sample is not outlier.

[0095] Step S206: determining an initial evaluation result corresponding to an evaluation index for an abnormal category of aggravated line loss in a substation area based on the daily line loss rate of the current date and the daily line loss rates corresponding to historical dates adjacent to the current date;

[0096] During the specific implementation of this step, the discreteness evaluation of the line loss rate is carried out. The discreteness evaluation is divided into aggravated anomaly evaluation and long-term anomaly evaluation. The aggravated anomaly evaluation is judged based on the amplitude of the line loss rate on the current day and the historical dates of the neighborhood: the neighborhood date can be selected from the historical dates of the past three days. The mathematical expression of the evaluation index of the aggravated anomaly category of the substation line loss is determined based on the daily line loss rate of the current date and the daily line loss rate corresponding to the historical dates of the neighborhood of the current date. It can be shown in the following formula (19):

[0097]

[0098] Among them, M 31 It is the category of abnormal aggravation of line loss in the substation area, including abnormal aggravation and normal; It is the line loss rate of the substation on the current day and the previous 1-3 days.

[0099] Step S207: Calculating and processing the daily line loss rate, the preset line loss rate upper limit, the preset line loss rate lower limit, and the initial evaluation results corresponding to the substation line loss risk abnormality category evaluation index based on the operating parameters corresponding to each date, to obtain the initial evaluation results corresponding to the substation long-term abnormality category evaluation index;

[0100] In the specific implementation process of this step, the number of daily line loss rates greater than the preset line loss rate upper limit is counted to obtain a first number value N T,up ; Count the number of daily line loss rates that are less than the preset line loss rate lower limit to obtain a second number value N T,down ; Based on the first quantity value and the number of days for collecting data in the predetermined sliding window, the high-loss anomaly ratio is calculated; based on the second quantity value and the number of days for collecting data in the predetermined sliding window, the negative-loss anomaly ratio is calculated; the mathematical expression can be expressed as the following formula (20):

[0101]

[0102] Among them, α up and α down are the proportion of high loss anomalies and the proportion of negative loss anomalies respectively; N T,up and N T,down The past N T The number of days when the line loss rate exceeds the upper limit and the lower limit; N T The number of days covered by the sliding window of historical data used for analysis can be 30 days;

[0103] Based on the high-loss abnormality ratio, the negative-loss abnormality ratio, and the initial evaluation results corresponding to the substation line loss risk abnormality category evaluation index, a long-term abnormality evaluation judgment is performed to obtain the initial evaluation results corresponding to the substation long-term abnormality category evaluation index. The mathematical expression can be expressed as the following formula (21):

[0104]

[0105] Among them, M 32 It is the long-term abnormal category of the substation, including long-term high loss, long-term negative loss and normal.

[0106] Step S208: Calculate and process the daily data integrity rate of the current date in the operating parameters using the long-term abnormality category evaluation function of the substation to obtain an initial evaluation result corresponding to the substation computability abnormality category evaluation index;

[0107] During the specific implementation of this step, the computability of the line loss rate is evaluated. For the current date t = 1 day, the mathematical expression of the judgment standard can be expressed as the following formula (22):

[0108]

[0109] Among them, M4 is the category of countability anomaly of the substation area, including missing data anomaly and normal; γ is the data completeness rate of the substation area.

[0110] Step S209: performing comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0111] The specific implementation of this step includes the following steps:

[0112] Step 1: When the initial evaluation result corresponding to the abnormal category evaluation index of the substation line loss risk is a high loss result, execute step 2; when the initial evaluation result corresponding to the abnormal category evaluation index of the substation line loss risk is a negative loss result, execute step 3; when the initial evaluation result corresponding to the abnormal category evaluation index of the substation line loss risk is a normal result, execute step 4; combine the multi-dimensional evaluation results of the substation line loss anomaly for coupling processing, first determine whether the evaluation result of the data on the day satisfies M1=high loss, if so, jump to step 2, if not, further determine whether M1=negative loss is satisfied, if so, jump to step 3, if not, jump to step 4;

[0113] Step 2. When the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation is a long-term high-loss result, the comprehensive identification result of the line loss abnormality of the target substation is a long-term high-loss abnormal result; when the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation does not meet the long-term high-loss result and the initial evaluation result corresponding to the line loss aggravation abnormality category evaluation index of the substation is an aggravated abnormality, the comprehensive identification result of the line loss abnormality of the target substation is a high-loss aggravated abnormal result; when the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation does not meet the long-term high-loss result and the initial evaluation result corresponding to the line loss aggravation abnormality category evaluation index of the substation does not meet the aggravated abnormality When the initial evaluation result corresponding to the evaluation index of the line loss rate fluctuation abnormality category of the substation is a sudden abnormal result, the comprehensive identification result of the line loss abnormality of the target substation is a sudden high loss abnormal result; when the initial evaluation result corresponding to the evaluation index of the long-term abnormality category of the substation does not meet the long-term high loss result, the initial evaluation result corresponding to the evaluation index of the line loss aggravation abnormality category of the substation does not meet the aggravation abnormal result, and the initial evaluation result corresponding to the evaluation index of the line loss rate fluctuation abnormality category of the substation does not meet the sudden abnormal result, the comprehensive identification result of the line loss abnormality of the target substation is a general high loss abnormal result; specifically, it is judged whether the data evaluation result of the day meets M 32 = Long-term high loss, if it meets the requirement, the “Long-term high loss abnormality” recognition result is output and the recognition process ends; if it does not meet the requirement, M32 = long-term high loss, then further determine whether M 31 = aggravated abnormality, if it is satisfied, the “high loss aggravated abnormality” recognition result is output and the recognition process ends; if it is not satisfied, M 31 = aggravated abnormality, it is further determined whether M2 = sudden abnormality is satisfied. If so, the recognition result of "sudden high-loss abnormality" is output and the process ends; if M2 = sudden abnormality is not satisfied, the recognition result of "general high-loss abnormality" is output and the process ends.

[0114] Step three, when the initial evaluation result corresponding to the abnormal category evaluation index of line loss risk in the substation is a long-term negative loss result, the comprehensive identification result of line loss abnormality in the target substation is a long-term negative loss abnormality; when the initial evaluation result corresponding to the abnormal category evaluation index of line loss risk in the substation does not meet the long-term loss result and the initial evaluation result corresponding to the abnormal category evaluation index of line loss aggravation in the substation is a severe abnormality result, the comprehensive identification result of line loss abnormality in the target substation is a negative loss aggravation abnormality; when the initial evaluation result corresponding to the abnormal category evaluation index of line loss risk in the substation does not meet the long-term loss result and the initial evaluation result corresponding to the abnormal category evaluation index of line loss aggravation in the substation is not When the aggravated abnormal result is met and the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss rate volatility in the substation is a sudden abnormal result, the comprehensive identification result of the line loss abnormality in the target substation is a sudden negative loss abnormal result; when the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss risk in the substation does not meet the long-term negative loss result, the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss aggravation in the substation does not meet the aggravated abnormal result, and the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss rate volatility in the substation does not meet the sudden abnormal result, the comprehensive identification result of the line loss abnormality in the target substation is a general negative loss abnormal result; specifically, it is judged whether the evaluation result of the data on the day meets M 32 = long-term negative damage, if it meets the requirement, the “long-term negative damage abnormality” recognition result is output and the recognition process ends; if it does not meet the requirement, M 32 = long-term loss, then further determine whether M 31 = aggravated abnormality, if it is satisfied, the “damage aggravated abnormality” recognition result is output and the recognition process ends; if it is not satisfied, M 31 = aggravated abnormality, then further determine whether M2 = sudden abnormality is satisfied. If so, output the recognition result of "sudden negative loss abnormality" and end the process; if M2 = sudden abnormality is not satisfied, output the recognition result of "general negative loss abnormality" and end the process;

[0115] Step 4: When the initial evaluation result corresponding to the evaluation index for the computability anomaly category of the substation is a missing data anomaly, the comprehensive identification result for the line loss anomaly in the target substation is a missing data anomaly result; when the initial evaluation result corresponding to the evaluation index for the computability anomaly category of the substation is a normal result, the comprehensive identification result for the line loss anomaly in the target substation is a normal result. Determine whether the evaluation result for the data on that day satisfies M4 = missing data anomaly. If so, output a "missing data anomaly" identification result and terminate the identification process; if not, output a "normal" identification result and terminate the identification process.

[0116] This application collects rich data, including daily line loss rates, daily power losses, and daily data integrity rates, within a predefined sliding window within a substation area. This data is then mined to correlate and calculate fluctuation data. Based on this data, a model for calculating abnormal line loss rate thresholds in substation areas is constructed using sliding window adaptive energy clustering and confidence intervals. This model transcends the limitations of traditional fixed thresholds by dynamically adjusting the abnormality thresholds based on traditional boundaries and the substation area's recent line loss operation. For example, in substations with seasonal electricity consumption or the electricity usage patterns of specific user groups, the model can accurately determine the true line loss situation, significantly improving the accuracy of identifying abnormal substation areas and avoiding misjudgments and omissions caused by a single criterion. The dynamic threshold adjustment model and multi-dimensional evaluation index system of this invention fully account for the diversity and complexity of substation operations. Regardless of the complexity of the substation, dynamic thresholds and multi-dimensional evaluation can accurately determine line loss anomalies. For example, for substations significantly affected by seasonality, dynamic thresholds can be used to promptly adjust the judgment criteria. For substations with complex line layouts, the multi-dimensional evaluation mechanism can comprehensively consider various factors for judgment. Therefore, this invention has broad adaptability and can meet the line loss management needs of different substations.

[0117] Another embodiment of the present application provides a device for identifying abnormal line loss in a transformer area, such as Figure 3 As shown, including:

[0118] Collection module 1, used for collecting operation data of the target substation using a predetermined sliding window, wherein the operation data includes first operation data of the current date and second operation data corresponding to a plurality of historical dates before the current date;

[0119] Calculation module 2, configured to calculate and process the first and second line loss abnormal dynamic thresholds for the current date based on the first and second operating data, a preset confidence coefficient, and a traditional boundary value of the line loss rate in a predetermined substation area;

[0120] Anomaly assessment module 3, configured to perform line loss anomaly assessment on the target substation based on the first line loss anomaly dynamic threshold, the second line loss anomaly dynamic threshold, and the operation data, and obtain initial assessment results corresponding to different assessment indicators;

[0121] The comprehensive identification module 4 is used to perform comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0122] During the specific implementation process, the calculation module 2 is specifically used to: perform calculations based on the first operating data and each of the second operating data to obtain the line loss rate mean and the line loss rate standard deviation; perform calculations based on the line loss rate mean, the line loss rate standard deviation, the preset confidence coefficient and the traditional boundary value of the line loss rate in the predetermined substation to obtain the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold corresponding to the current date.

[0123] During the specific implementation process, the abnormality assessment module 3 is specifically used to: use the daily line loss rate of the current date in the operating data to compare with the first line loss abnormality dynamic threshold and the second line loss abnormality dynamic threshold respectively, and obtain the initial evaluation result corresponding to the substation line loss risk abnormality category evaluation index; based on the daily line loss rate corresponding to each date in the operating parameters, an adaptive energy clustering method is used for calculation and processing to obtain the initial evaluation result corresponding to the substation line loss rate volatility abnormality category evaluation index; based on the daily line loss rate of the current date and the daily line loss rate corresponding to the historical dates in the neighborhood of the current date, the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index is determined; based on the daily line loss rate corresponding to each date in the operating parameters, the preset line loss rate upper limit, the preset line loss rate lower limit and the initial evaluation result corresponding to the substation line loss risk abnormality category evaluation index, calculation and processing are performed to obtain the initial evaluation result corresponding to the substation long-term abnormality category evaluation index; based on the daily data completeness rate of the current date in the operating parameters, the substation long-term abnormality category evaluation function is used for calculation and processing to obtain the initial evaluation result corresponding to the substation computability abnormality category evaluation index.

[0124] During the specific implementation process, the abnormality assessment module 3 is also used to: perform calculations based on the daily line loss rates in the operating parameters to obtain the line loss rate fluctuation values ​​corresponding to each date; use an adaptive energy clustering method based on each of the line loss rate fluctuation values ​​to determine whether the first operating data is outliers to obtain an outlier index value; perform mean calculations based on each of the line loss rate fluctuation values ​​to obtain the mean of the absolute values ​​of the line loss rate fluctuations; perform calculations based on the line loss rate fluctuation values ​​and the mean of the absolute values ​​of the line loss rate fluctuations to obtain the standard deviation of the line loss rate fluctuations; determine the initial evaluation result corresponding to the evaluation index of the abnormal category of the line loss rate fluctuation of the substation based on the outlier index value, the standard deviation of the line loss rate fluctuations and the line loss rate fluctuation values.

[0125] During the specific implementation process, the abnormality assessment module 3 is also used to: perform calculations based on the daily power loss data in the operating parameters corresponding to each of the dates to obtain the contour coefficient corresponding to the operating parameters on each date; solve the first optimization model with the global contour coefficient as the goal to be the largest based on each of the contour coefficients to obtain the optimal number of clusters, so as to obtain the cluster clusters with the optimal number of clusters; solve the second optimization model with the sum of the square distances to the centers of the clusters as the goal to be the smallest based on the daily power loss data in the operating parameters to obtain the centroid corresponding to each of the cluster clusters; use the daily line loss rate of the current date in the operating data and each of the centroids to perform calculations to obtain a first distance value; perform calculations based on the daily power loss data and the centroid in the same cluster cluster to obtain the distance standard deviation corresponding to the same cluster cluster; compare the first distance values ​​with the distance standard deviation to obtain the outlier index value.

[0126] During the specific implementation process, the abnormality assessment module 3 is also used to: count the number of daily line loss rates that are greater than the preset line loss rate upper limit to obtain a first quantity value; count the number of daily line loss rates that are less than the preset line loss rate lower limit to obtain a second quantity value; perform calculations based on the first quantity value and the predetermined sliding window collection days to obtain the high-loss abnormality ratio; perform calculations based on the second quantity value and the predetermined sliding window collection days to obtain the negative-loss abnormality ratio; perform long-term abnormality evaluation and judgment based on the high-loss abnormality ratio, the negative-loss abnormality ratio and the initial evaluation results corresponding to the substation line loss risk abnormality category evaluation indicators to obtain the initial evaluation results corresponding to the substation long-term abnormality category evaluation indicators.

[0127] In the specific implementation process, the comprehensive identification module 4 is specifically used for: step 1, when the initial evaluation result corresponding to the abnormal category evaluation index of the line loss risk of the substation is a high loss result, executing step 2; when the initial evaluation result corresponding to the abnormal category evaluation index of the line loss risk of the substation is a negative loss result, executing step 3; when the initial evaluation result corresponding to the abnormal category evaluation index of the line loss risk of the substation is a normal result, executing step 4; step 2, when the initial evaluation result corresponding to the long-term abnormal category evaluation index of the substation is a long-term high loss result, the comprehensive identification result of the line loss abnormality of the target substation is a long-term high loss abnormal result; when the long-term abnormal category evaluation index of the substation is When the initial evaluation result corresponding to the normal category evaluation index does not meet the long-term high loss result and the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index is aggravated abnormality, the comprehensive identification result of the line loss abnormality of the target substation is a high loss aggravated abnormality result; when the initial evaluation result corresponding to the substation long-term abnormality category evaluation index does not meet the long-term high loss result, the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index does not meet the aggravated abnormality result and the initial evaluation result corresponding to the substation line loss rate fluctuation abnormality category evaluation index is a sudden abnormality result, the comprehensive identification result of the line loss abnormality of the target substation is a sudden high loss abnormality. Normal result; when the initial evaluation result corresponding to the long-term abnormal category evaluation index of the substation does not meet the long-term high loss result, the initial evaluation result corresponding to the line loss aggravation abnormal category evaluation index of the substation does not meet the aggravation abnormal result and the initial evaluation result corresponding to the line loss rate volatility abnormal category evaluation index of the substation does not meet the sudden abnormal result, the comprehensive identification result of the line loss abnormality of the target substation is a general high loss abnormal result; Step three, when the initial evaluation result corresponding to the line loss risk abnormal category evaluation index of the substation is a long-term negative loss result, the comprehensive identification result of the line loss abnormality of the target substation is a long-term loss abnormality; when the line loss risk abnormal category of the substation When the initial evaluation result corresponding to the evaluation index does not meet the long-term negative loss result and the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index is a severe abnormality result, the comprehensive identification result of the line loss abnormality in the target substation is negative loss aggravation abnormality; when the initial evaluation result corresponding to the substation line loss risk abnormality category evaluation index does not meet the long-term negative loss result, the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index does not meet the aggravation abnormality result and the initial evaluation result corresponding to the substation line loss rate volatility abnormality category evaluation index is a sudden abnormality result, the comprehensive identification result of the line loss abnormality in the target substation is sudden negative loss abnormality;When the initial evaluation result corresponding to the substation line loss risk abnormality category evaluation index does not meet the long-term negative loss result, the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index does not meet the aggravation abnormality result, and the initial evaluation result corresponding to the substation line loss rate volatility abnormality category evaluation index does not meet the sudden abnormality result, the comprehensive identification result of the line loss abnormality of the target substation is obtained as a general negative loss abnormality; Step 4: When the initial evaluation result corresponding to the substation computability abnormality category evaluation index is a missing number abnormality, the comprehensive identification result of the line loss abnormality of the target substation is obtained as a missing number abnormality result; when the initial evaluation result corresponding to the substation computability abnormality category evaluation index is a normal result, the comprehensive identification result of the line loss abnormality of the target substation is obtained as a normal result.

[0128] This application collects rich data, including daily line loss rates, daily power losses, and daily data integrity rates, within a predefined sliding window within a substation area. This data is then mined to correlate and calculate fluctuation data. Based on this data, a model for calculating abnormal line loss rate thresholds in substation areas is constructed using sliding window adaptive energy clustering and confidence intervals. This model transcends the limitations of traditional fixed thresholds by dynamically adjusting the abnormality thresholds based on traditional boundaries and the substation area's recent line loss operation. For example, in substations with seasonal electricity consumption or the electricity usage patterns of specific user groups, the model can accurately determine the true line loss situation, significantly improving the accuracy of identifying abnormal substation areas and avoiding misjudgments and omissions caused by a single criterion. The dynamic threshold adjustment model and multi-dimensional evaluation index system of this invention fully account for the diversity and complexity of substation operations. Regardless of the complexity of the substation, dynamic thresholds and multi-dimensional evaluation can accurately determine line loss anomalies. For example, for substations significantly affected by seasonality, dynamic thresholds can be used to promptly adjust the judgment criteria. For substations with complex line layouts, the multi-dimensional evaluation mechanism can comprehensively consider various factors for judgment. Therefore, this invention has broad adaptability and can meet the line loss management needs of different substations.

[0129] Another embodiment of the present application provides a storage medium storing a computer program. When the computer program is executed by a processor, the following method steps are implemented:

[0130] Step 1: using a predetermined sliding window to collect operation data of the target substation, the operation data including first operation data of the current date and second operation data corresponding to a plurality of historical dates before the current date;

[0131] Step 2: Calculate and process the first and second line loss abnormal dynamic thresholds for the current date based on the first and second operating data, a preset confidence coefficient, and a traditional boundary value of the line loss rate in a predetermined substation area;

[0132] Step 3: Based on the first line loss abnormal dynamic threshold, the second line loss abnormal dynamic threshold, and the operating data, perform line loss abnormality assessment on the target substation to obtain initial assessment results corresponding to different assessment indicators;

[0133] Step 4: Perform comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0134] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. 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 memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0135] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0136] The specific implementation process of the above method steps can be found in the above-mentioned embodiment of the method for identifying abnormal line loss in any substation area, and this embodiment will not be repeated here.

[0137] This application collects rich data, including daily line loss rates, daily power losses, and daily data integrity rates, within a predefined sliding window within a substation area. This data is then mined to correlate and calculate fluctuation data. Based on this data, a model for calculating abnormal line loss rate thresholds in substation areas is constructed using sliding window adaptive energy clustering and confidence intervals. This model transcends the limitations of traditional fixed thresholds by dynamically adjusting the abnormality thresholds based on traditional boundaries and the substation area's recent line loss operation. For example, in substations with seasonal electricity consumption or the electricity usage patterns of specific user groups, the model can accurately determine the true line loss situation, significantly improving the accuracy of identifying abnormal substation areas and avoiding misjudgments and omissions caused by a single criterion. The dynamic threshold adjustment model and multi-dimensional evaluation index system of this invention fully account for the diversity and complexity of substation operations. Regardless of the complexity of the substation, dynamic thresholds and multi-dimensional evaluation can accurately determine line loss anomalies. For example, for substations significantly affected by seasonality, dynamic thresholds can be used to promptly adjust the judgment criteria. For substations with complex line layouts, the multi-dimensional evaluation mechanism can comprehensively consider various factors for judgment. Therefore, this invention has broad adaptability and can meet the line loss management needs of different substations.

[0138] Another embodiment of the present application provides an electronic device, which may be a server, and the electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client via a network connection. When the electronic device program is executed by the processor, it implements the functions or steps on the server side of a method for identifying abnormal line loss in a substation area.

[0139] In one embodiment, an electronic device is provided, which may be a client. The electronic device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic 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 computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server via a network connection. When the electronic device program is executed by the processor, it implements the functions or steps on the client side of a method for identifying abnormal line loss in a substation area.

[0140] Another embodiment of the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the following method steps when executing the computer program in the memory:

[0141] Step 1: using a predetermined sliding window to collect operation data of the target substation, the operation data including first operation data of the current date and second operation data corresponding to a plurality of historical dates before the current date;

[0142] Step 2: Calculate and process the first and second line loss abnormal dynamic thresholds for the current date based on the first and second operating data, a preset confidence coefficient, and a traditional boundary value of the line loss rate in a predetermined substation area;

[0143] Step 3: Based on the first line loss abnormal dynamic threshold, the second line loss abnormal dynamic threshold, and the operating data, perform line loss abnormality assessment on the target substation to obtain initial assessment results corresponding to different assessment indicators;

[0144] Step 4: Perform comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

[0145] The specific implementation process of the above method steps can be found in the above-mentioned embodiment of the method for identifying abnormal line loss in any substation area, and this embodiment will not be repeated here.

[0146] This application collects rich data, including daily line loss rates, daily power losses, and daily data integrity rates, within a predefined sliding window within a substation area. This data is then mined to correlate and calculate fluctuation data. Based on this data, a model for calculating abnormal line loss rate thresholds in substation areas is constructed using sliding window adaptive energy clustering and confidence intervals. This model transcends the limitations of traditional fixed thresholds by dynamically adjusting the abnormality thresholds based on traditional boundaries and the substation area's recent line loss operation. For example, in substations with seasonal electricity consumption or the electricity usage patterns of specific user groups, the model can accurately determine the true line loss situation, significantly improving the accuracy of identifying abnormal substation areas and avoiding misjudgments and omissions caused by a single criterion. The dynamic threshold adjustment model and multi-dimensional evaluation index system of this invention fully account for the diversity and complexity of substation operations. Regardless of the complexity of the substation, dynamic thresholds and multi-dimensional evaluation can accurately determine line loss anomalies. For example, for substations significantly affected by seasonality, dynamic thresholds can be used to promptly adjust the judgment criteria. For substations with complex line layouts, the multi-dimensional evaluation mechanism can comprehensively consider various factors for judgment. Therefore, this invention has broad adaptability and can meet the line loss management needs of different substations.

[0147] The above embodiments are merely exemplary embodiments of the present application and are not intended to limit the scope of the present application. The scope of protection of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and scope of protection of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present application.

Claims

1. A method for identifying abnormal line loss in a transformer area, characterized in that: include: Using a predetermined sliding window to collect operating data of a target substation, the operating data includes first operating data of a current date and second operating data corresponding to a plurality of historical dates before the current date; Calculating and processing based on the first operating data and each of the second operating data, a preset confidence coefficient, and a traditional boundary value of a predetermined area line loss rate, to obtain a first line loss abnormal dynamic threshold value and a second line loss abnormal dynamic threshold value for the current date; Performing a line loss anomaly assessment on the target substation based on the first line loss anomaly dynamic threshold, the second line loss anomaly dynamic threshold, and the operating data to obtain initial assessment results corresponding to different assessment indicators; Based on each of the initial evaluation results, a comprehensive identification of line loss anomalies in the substation area is performed to obtain a comprehensive identification result of line loss anomalies in the target substation area.

2. The method according to claim 1, wherein The calculating and processing based on the first operating data and each of the second operating data, a preset confidence coefficient, and a predetermined traditional boundary value of the line loss rate of the substation area to obtain the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold for the current date specifically includes: Performing calculations based on the first operating data and each of the second operating data to obtain a line loss rate mean and a line loss rate standard deviation; Based on the line loss rate mean, the line loss rate standard deviation, the preset confidence coefficient and the traditional boundary value of the line loss rate in the predetermined substation, calculation and processing are performed to obtain the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold corresponding to the current date.

3. The method according to claim 1, wherein The performing of line loss anomaly assessment on the target substation based on the first line loss anomaly dynamic threshold, the second line loss anomaly dynamic threshold, and the operation data to obtain initial evaluation results corresponding to different evaluation indicators specifically includes: Comparing the daily line loss rate of the current date in the operating data with the first line loss abnormal dynamic threshold and the second line loss abnormal dynamic threshold, respectively, to obtain an initial evaluation result corresponding to the evaluation index of the abnormal category of the substation line loss risk; Based on the daily line loss rate corresponding to each date in the operating parameters, an adaptive energy clustering method is used to calculate and process the line loss rate, and an initial evaluation result corresponding to the abnormal category evaluation index of the line loss rate fluctuation of the substation area is obtained; Determine an initial evaluation result corresponding to an evaluation index for an aggravated abnormality category of a transformer area line loss based on the daily line loss rate of the current date and the daily line loss rates corresponding to historical dates adjacent to the current date; Calculate and process the daily line loss rate, the preset line loss rate upper limit, the preset line loss rate lower limit, and the initial evaluation result corresponding to the abnormal category evaluation index of the substation line loss risk based on the operating parameters corresponding to each date, and obtain the initial evaluation result corresponding to the long-term abnormal category evaluation index of the substation; The daily data completeness rate of the current date in the operating parameters is calculated and processed using the long-term abnormality category evaluation function of the substation to obtain the initial evaluation result corresponding to the computability abnormality category evaluation index of the substation.

4. The method according to claim 3, wherein The adaptive energy clustering method is used to calculate and process the daily line loss rate corresponding to each date in the operating parameters to obtain the initial evaluation results corresponding to the abnormal category evaluation index of the line loss rate fluctuation of the substation area, specifically including: Calculate and process the daily line loss rate in the operating parameters to obtain the line loss rate fluctuation value corresponding to each date; Based on each of the line loss rate fluctuation values, an adaptive energy clustering method is used to determine whether the first operating data is outliers, and an outlier index value is obtained; Performing mean calculation based on the line loss rate fluctuation values ​​to obtain the mean of the absolute values ​​of the line loss rate fluctuations; Calculating and processing based on the line loss rate fluctuation value and the mean of the absolute value of the line loss rate fluctuation to obtain a line loss rate fluctuation standard deviation; An initial evaluation result corresponding to an evaluation index of an abnormal category of line loss rate fluctuation in a substation is determined based on the outlier index value, the line loss rate fluctuation standard deviation, and the line loss rate fluctuation value.

5. The method according to claim 4, wherein The step of determining whether the first operating data is outliers by using an adaptive energy clustering method based on each of the line loss rate fluctuation values ​​to obtain an outlier index value specifically includes: Calculating and processing the daily power loss data in the operating parameters corresponding to each of the dates to obtain a contour coefficient corresponding to the operating parameters on each date; Solving a first optimization model with the goal of maximizing the global silhouette coefficient based on each of the silhouette coefficients to obtain an optimal number of clusters, thereby obtaining clusters with an optimal number of clusters; Solving a second optimization model with the goal of minimizing the sum of squared distances to the cluster centers based on the daily power loss data in the operating parameters, and obtaining the centroid corresponding to each cluster; Calculating and processing the daily line loss rate of the current date and each of the centroids in the operation data to obtain a first distance value; Calculating and processing the daily power loss data and the centroid of the same cluster to obtain the distance standard deviation corresponding to the same cluster; An outlier index value is obtained based on a comparison between each of the first distance values ​​and the distance standard deviation.

6. The method according to claim 4, wherein The calculation and processing based on the daily line loss rate, the preset line loss rate upper limit, the preset line loss rate lower limit and the initial evaluation result corresponding to the abnormal category evaluation index of the substation line loss risk in the operating parameters corresponding to each date are performed to obtain the initial evaluation result corresponding to the long-term abnormal category evaluation index of the substation, specifically including: Counting the number of times that the daily line loss rate exceeds the preset line loss rate upper limit, to obtain a first number value; Counting the number of days where the line loss rate is less than the preset line loss rate lower limit, to obtain a second number value; Calculating and processing based on the first quantity value and the predetermined number of days of collection within the sliding window to obtain a high-loss anomaly ratio; Calculating and processing based on the second quantity value and the predetermined number of sliding window collection days to obtain a negative loss anomaly ratio; Based on the high-loss abnormality ratio, the negative-loss abnormality ratio and the initial evaluation results corresponding to the substation line loss risk abnormality category evaluation index, a long-term abnormality evaluation judgment is performed to obtain the initial evaluation results corresponding to the substation long-term abnormality category evaluation index.

7. The method according to claim 4, wherein The step of performing comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation specifically includes: Step 1: When the initial evaluation result corresponding to the abnormal category evaluation index of the transformer area line loss risk is a high loss result, execute step 2; When the initial evaluation result corresponding to the abnormal category evaluation index of the transformer area line loss risk is a negative loss result, executing step three; When the initial evaluation result corresponding to the abnormal category evaluation index of the transformer area line loss risk is a normal result, executing step 4; Step 2: When the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation is a long-term high loss result, the comprehensive identification result of the line loss abnormality of the target substation is a long-term high loss abnormal result; When the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation does not meet the long-term high loss result and the initial evaluation result corresponding to the line loss aggravated abnormality category evaluation index of the substation is aggravated abnormality, the comprehensive identification result of the line loss abnormality of the target substation is a high loss aggravated abnormality result; When the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation does not meet the long-term high loss result, the initial evaluation result corresponding to the aggravated line loss abnormality category evaluation index of the substation does not meet the aggravated abnormality result, and the initial evaluation result corresponding to the line loss rate fluctuation abnormality category evaluation index of the substation is a sudden abnormality result, the comprehensive identification result of the line loss abnormality of the target substation is a sudden high loss abnormality result; When the initial evaluation result corresponding to the long-term abnormality category evaluation index of the substation does not meet the long-term high loss result, the initial evaluation result corresponding to the aggravated line loss abnormality category evaluation index of the substation does not meet the aggravated abnormality result, and the initial evaluation result corresponding to the line loss rate fluctuation abnormality category evaluation index of the substation does not meet the sudden abnormality result, the comprehensive identification result of the line loss abnormality of the target substation is a general high loss abnormality result; Step 3: When the initial evaluation result corresponding to the evaluation index of the line loss risk anomaly category of the substation is a long-term negative loss result, the comprehensive identification result of the line loss anomaly of the target substation is obtained as a long-term negative loss anomaly; When the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss risk in the substation does not meet the long-term negative loss result and the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss aggravation in the substation is a severe abnormal result, the comprehensive identification result of the line loss anomaly in the target substation is a negative loss aggravation anomaly; When the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss risk in the substation does not meet the long-term negative loss result, the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss aggravation in the substation does not meet the aggravated abnormal result, and the initial evaluation result corresponding to the evaluation index of the abnormal category of line loss rate volatility in the substation is a sudden abnormal result, the comprehensive identification result of the line loss abnormality in the target substation is a sudden negative loss abnormality; When the initial evaluation result corresponding to the substation line loss risk abnormality category evaluation index does not meet the long-term negative loss result, the initial evaluation result corresponding to the substation line loss aggravation abnormality category evaluation index does not meet the aggravation abnormality result, and the initial evaluation result corresponding to the substation line loss rate volatility abnormality category evaluation index does not meet the sudden abnormality result, the comprehensive identification result of the line loss abnormality of the target substation is obtained as a general negative loss abnormality; Step 4: When the initial evaluation result corresponding to the evaluation index of the abnormal category of the computability of the substation is a missing number abnormality, the comprehensive identification result of the line loss abnormality of the target substation is a missing number abnormality result; When the initial evaluation result corresponding to the evaluation index of the abnormal category of the computability of the substation is a normal result, the comprehensive identification result of the line loss abnormality of the target substation is a normal result.

8. A device for identifying abnormal line loss in a transformer area, characterized in that: include: A collection module, configured to collect operation data of a target substation using a predetermined sliding window, wherein the operation data includes first operation data of a current date and second operation data corresponding to a plurality of historical dates before the current date; A calculation module, configured to calculate and process the first and second line loss abnormal dynamic thresholds for the current date based on the first and second operating data, a preset confidence coefficient, and a traditional boundary value of a predetermined substation line loss rate; an abnormality assessment module, configured to perform a line loss abnormality assessment on the target substation based on the first line loss abnormality dynamic threshold, the second line loss abnormality dynamic threshold, and the operation data, and obtain initial assessment results corresponding to different assessment indicators; The comprehensive identification module is used to perform comprehensive identification of line loss anomalies in the substation based on the initial evaluation results to obtain a comprehensive identification result of line loss anomalies in the target substation.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for identifying abnormal line loss in a substation area according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The system comprises at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method for identifying abnormal line loss in a substation area as described in any one of claims 1 to 7 when executing the computer program on the memory.

Images