Methods, devices, and processors for determining high-voltage transmission line loss branches.

Abstract

This invention discloses a method, apparatus, and processor for determining line loss branches in high-voltage transmission lines. The method includes: verifying the line-transformer relationship of the line to be evaluated based on basic electricity consumption information and obtaining the verification result; assessing the line loss of the line to be evaluated based on the verification result and obtaining the line loss time interval, wherein the line loss time interval is the time interval during which line loss occurs in the line to be evaluated; detecting abnormal electricity consumption of the line to be evaluated based on the line loss time interval and obtaining a set of abnormal electricity consumption nodes; training a machine learning model using an electricity consumption sample set to obtain an abnormal electricity consumption detection model, wherein the electricity consumption sample set includes at least: a set of abnormal electricity consumption nodes, a line loss time interval, and basic electricity consumption information; and inputting the current basic electricity consumption information into the abnormal electricity consumption detection model to obtain the target line loss branch. This invention solves the technical problem of low efficiency in methods for finding line loss branches during high-voltage transmission in related technologies.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more specifically, to a method, apparatus, and processor for determining the branch of a high-voltage transmission line with line loss. Background Technology

[0002] The line loss level of 10kV transmission lines in my country is relatively high compared to other voltage levels, making it a top priority in loss reduction efforts. Considering that the technical line losses of 10kV transmission lines are mainly affected by factors such as the line structure, line and equipment parameters, and are difficult to reduce, loss reduction work on 10kV transmission lines primarily focuses on addressing non-technical line loss issues. However, currently, when power supply companies assess whether there are unreasonable non-technical line loss problems in 10kV transmission lines, the evaluation standard is solely based on the actual statistical line loss level. They often use fixed assessment indicators and implement a "one-size-fits-all" management approach. Undoubtedly, this simplistic and crude management method ignores the high loss problems caused by the inherent characteristics of 10kV transmission lines themselves. Therefore, the urgent task is to research a reasonable method for assessing the line loss level of 10kV transmission lines and implement a "one line, one loss" assessment approach.

[0003] Furthermore, to further analyze non-technical line losses on 10kV transmission lines and identify abnormal electricity users, power supply companies often resort to cumbersome methods such as manual inspections. Clearly, this approach is time-consuming and labor-intensive, and ineffective against increasingly sophisticated and sophisticated electricity theft methods. Therefore, based on existing measurement capabilities, researching accurate and effective methods for detecting abnormal electricity users can significantly reduce non-technical line losses on 10kV transmission lines, which is of great significance for energy conservation and loss reduction in the power grid and for contributing to the achievement of "dual carbon" goals.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, and processor for determining loss branches in high-voltage transmission lines, thereby at least addressing the technical problem of low efficiency in methods for locating loss branches during high-voltage power transmission in related technologies.

[0006] According to one aspect of the present invention, a method for determining the line loss branches of a high-voltage transmission line is provided, comprising: verifying the line-transformer relationship of the line to be evaluated based on basic electricity consumption information, and obtaining verification results, wherein the basic electricity consumption information includes at least: historical electricity consumption data of users, historical line loss data, voltage curve data of the substations of the line to be evaluated, voltage curve data of public and private transformers within the jurisdiction, and electricity consumption data characteristics, wherein the electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance, and the verification results characterize the line to be evaluated. Estimate the line loss level of the line; assess the line loss of the line to be evaluated based on the verification results, and obtain the line loss time interval, wherein the line loss time interval is the time interval during which the line loss of the line to be evaluated occurs; detect abnormal power consumption of the line to be evaluated based on the line loss time interval, and obtain a set of abnormal power consumption nodes; train a machine learning model using a power consumption sample set to obtain an abnormal power consumption detection model, wherein the power consumption sample set includes at least: the set of abnormal power consumption nodes, the line loss time interval, and the basic power consumption information; input the current basic power consumption information into the abnormal power consumption detection model to obtain the target line loss branch.

[0007] Optionally, before verifying the line-transformer relationship of the line to be evaluated based on the basic electricity consumption information, the process includes: acquiring the basic electricity consumption information through an electricity consumption information acquisition platform, wherein the electricity consumption information acquisition platform includes at least: an electricity consumption information acquisition system, a data acquisition and monitoring control system, and an integrated power consumption and line loss management system.

[0008] Optionally, the line-transformer relationship verification is performed on the line to be evaluated based on the basic electricity consumption information, including: filtering out null values ​​in the voltage curve data of the substations of the line to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; obtaining the filtered voltage curve data of the substations of the line to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; obtaining the DTW distance between each pair of the filtered voltage curve data of the substations of the line to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; using the DTW distance as a feature value, and performing a clustering algorithm on the voltage curves of the substations of the line to be transmitted and the voltage curves of public and private transformers within the jurisdiction to complete the line-transformer relationship verification, wherein the clustering algorithm includes at least the k-means clustering algorithm.

[0009] Optionally, before training the machine learning model using the electricity consumption sample set, the method includes: preprocessing the abnormal electricity consumption nodes, the line loss time interval, the electricity consumption data features, and the basic electricity consumption information using a predetermined algorithm to construct the electricity consumption sample set, wherein the predetermined algorithm includes at least: normalization processing.

[0010] Optionally, abnormal power consumption detection is performed on the line to be evaluated based on the line loss time interval to obtain a set of abnormal power consumption nodes, including: obtaining the loss change rate and the actual current amplitude change rate of multiple branches of the line to be evaluated based on the line loss time interval; comparing a preset threshold with the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, respectively, filtering out branches whose preset threshold is greater than the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, and integrating multiple filtered branches to obtain a set of abnormal power consumption nodes.

[0011] According to another aspect of the present invention, a device for determining the line loss branches of a high-voltage transmission line is also provided, comprising: a line-transformer relationship verification module, used to verify the line-transformer relationship of the line to be evaluated based on basic electricity consumption information and obtain verification results, wherein the basic electricity consumption information includes at least: historical electricity consumption data of users, historical line loss data, voltage curve data of the substation of the line to be evaluated, voltage curve data of public and private transformers within the jurisdiction, and electricity consumption data characteristics, wherein the electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance, and the verification results characterize the degree of line loss of the line to be evaluated; and a line loss assessment module. The system includes: a line loss assessment module for evaluating the line to be evaluated based on the verification results, and a line loss time interval for obtaining the line loss time interval, wherein the line loss time interval is the time interval during which the line to be evaluated experiences line loss; an abnormal power consumption detection module for detecting abnormal power consumption on the line to be evaluated based on the line loss time interval, and obtaining an abnormal power consumption node set; a training module for training a machine learning model using a power consumption sample set, and obtaining an abnormal power consumption detection model, wherein the power consumption sample set includes at least: the abnormal power consumption node set, the line loss time interval, and the basic power consumption information; and a first acquisition module for inputting the current basic power consumption information into the abnormal power consumption detection model to acquire the target line loss branch.

[0012] Optionally, the method further includes: a second acquisition module, used to acquire the basic electricity consumption information through an electricity consumption information acquisition platform before performing line-transformer relationship verification on the line to be evaluated based on the basic electricity consumption information, wherein the electricity consumption information acquisition platform includes at least: an electricity consumption information acquisition system, a data acquisition and monitoring control system, and an integrated power consumption and line loss management system.

[0013] Optionally, the line-transformer relationship verification module includes: a filtering unit, used to filter out null values ​​in the voltage curve data of the substation to be transmitted and the voltage curve data of public and private transformers within the jurisdiction, and obtain the filtered voltage curve data of the substation to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; a first acquisition unit, used to acquire the DTW distance between each pair of the filtered voltage curve data of the substation to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; and a processing unit, used to use the DTW distance as a feature value and process the voltage curves of the substation to be transmitted and the voltage curves of public and private transformers within the jurisdiction using a clustering algorithm to complete the line-transformer relationship verification, wherein the clustering algorithm includes at least the k-means clustering algorithm.

[0014] Optionally, the method further includes: a preprocessing unit, used to preprocess the abnormal electricity consumption nodes, the line loss time interval, the electricity consumption data features, and the basic electricity consumption information using a predetermined algorithm before training the machine learning model with the electricity consumption sample set, thereby constructing the electricity consumption sample set, wherein the predetermined algorithm includes at least: normalization processing.

[0015] Optionally, the abnormal power consumption monitoring module includes: a second acquisition unit, configured to acquire the loss change rate and the actual current amplitude change rate of multiple branches of the line to be evaluated based on the line loss time interval; and a comparison unit, configured to compare a preset threshold with the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, respectively, filter out branches whose preset threshold is greater than the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, integrate multiple filtered branches, and obtain an abnormal power consumption node set.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed by a processor, it controls the device where the computer-readable storage medium is located to perform any of the above-described methods for determining the high-voltage transmission line loss branches.

[0017] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a computer program, wherein the computer program, when running, executes any of the above-described methods for determining high-voltage transmission line loss branches.

[0018] In this embodiment of the invention, the line-transformer relationship of the line to be evaluated is verified based on the basic electricity consumption information to obtain the verification result. The basic electricity consumption information includes at least: historical electricity consumption data of users, historical line loss data, voltage curve data of substations of the line to be transmitted, voltage curve data of public and private transformers within the jurisdiction, and electricity consumption data characteristics. The electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance. The verification result characterizes the degree of line loss of the line to be evaluated. Based on the verification result, the line loss of the line to be evaluated is assessed to obtain the line loss time interval, which is the time interval during which line loss occurs in the line to be evaluated. Based on the line loss time interval, abnormal electricity consumption detection is performed on the line to be evaluated to obtain the abnormal electricity consumption node set. The machine learning model is trained using the electricity consumption sample set to obtain the abnormal electricity consumption detection model. The electricity consumption sample set includes at least: abnormal electricity consumption node set, line loss time interval, and basic electricity consumption information. The current basic electricity consumption information is input into the abnormal electricity consumption detection model to obtain the target line loss branch. The method for determining high-voltage transmission line loss branches provided by the embodiments of the present invention achieves the goal of obtaining a set of abnormal power consumption nodes after assessing the line loss of basic power consumption information, then training an abnormal power consumption detection model, and using the model to obtain the target line loss branch, thereby improving the technical effect of fault detection efficiency and solving the technical problem of low efficiency in the method of finding line loss branches in high-voltage transmission processes in related technologies. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 This is a flowchart of a method for determining high-voltage transmission line loss branches according to an embodiment of the present invention;

[0021] Figure 2 This is a schematic diagram of an electricity consumption sample model based on a 2D CNN-based abnormal electricity consumption detection model according to an embodiment of the present invention;

[0022] Figure 3 This is a structural diagram of an abnormal power consumption detection model based on 2D CNN according to an embodiment of the present invention;

[0023] Figure 4 This is a flowchart of an abnormal power consumption detection model based on 2D CNN according to an embodiment of the present invention;

[0024] Figure 5 This is a flowchart of a preferred method for determining high-voltage transmission line loss branches according to an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of a device for determining the branch of high-voltage transmission line loss according to an embodiment of the present invention; Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] According to an embodiment of the present invention, a method embodiment for determining the branch of high-voltage transmission line loss is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] Figure 1 This is a flowchart of a method for determining high-voltage transmission line loss branches according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0031] Step S102: Based on the basic electricity consumption information, the line-transformer relationship of the line to be evaluated is verified, and the verification result is obtained. The basic electricity consumption information includes at least: historical electricity consumption data of users, historical line loss data, voltage curve data of substations of the line to be transmitted, voltage curve data of public transformers and private transformers in the jurisdiction, and electricity consumption data characteristics. The electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance. The verification result characterizes the degree of line loss of the line to be evaluated.

[0032] Step S104: Based on the verification results, perform line loss assessment on the line to be evaluated and obtain the line loss time interval, wherein the line loss time interval is the time interval during which line loss occurs on the line to be evaluated.

[0033] Step S106: Based on the line loss time interval, perform abnormal power consumption detection on the line to be evaluated and obtain the abnormal power consumption node set;

[0034] Step S108: Train the machine learning model using the electricity consumption sample set to obtain an abnormal electricity consumption detection model. The electricity consumption sample set includes at least: an abnormal electricity consumption node set, line loss time interval, and basic electricity consumption information.

[0035] It should be noted that abnormal power consumption detection models include, but are not limited to, 2D CNN neural network models.

[0036] Figure 2 This is a schematic diagram of an electricity consumption sample model based on a 2D CNN-based abnormal electricity consumption detection model according to an embodiment of the present invention, as shown below. Figure 2 As shown, the time span of the AMI data sample matrix is ​​taken as month (30 days), and it slides on the time axis with a step size of days. The independent characteristic quantities of user electricity consumption data considered include electrical parameters such as the average three-phase active power and the average three-phase voltage.

[0037] Step S110: Input the current basic electricity consumption information into the abnormal electricity consumption detection model to obtain the target line loss branch.

[0038] As can be seen from the above, in this embodiment of the invention, the line-transformer relationship of the line to be evaluated can first be verified based on the basic electricity consumption information to obtain the verification results. The basic electricity consumption information includes at least: user historical electricity consumption data, historical line loss data, voltage curve data of the substation of the line to be transmitted, voltage curve data of public transformers and private transformers in the jurisdiction, and electricity consumption data characteristics. The electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance. The verification results characterize the degree of line loss of the line to be evaluated. Based on the verification results, line loss is assessed on the line to be evaluated to obtain the line loss time interval, which is the time interval during which line loss occurs on the line to be evaluated. Next, abnormal power consumption detection can be performed on the line to be evaluated based on the line loss time interval to obtain a set of abnormal power consumption nodes. Then, a machine learning model can be trained using the power consumption sample set to obtain an abnormal power consumption detection model, where the power consumption sample set includes at least: a set of abnormal power consumption nodes, the line loss time interval, and basic power consumption information. Finally, the current basic power consumption information can be input into the abnormal power consumption detection model to obtain the target line loss branch. The method for determining high-voltage transmission line loss branches provided by this invention achieves the goal of obtaining a set of abnormal power consumption nodes after assessing line loss based on basic power consumption information, then training an abnormal power consumption detection model, and finally obtaining the target line loss branch through this model. This improves the technical effect of fault detection efficiency and solves the technical problem of low efficiency in methods for finding line loss branches during high-voltage transmission in related technologies.

[0039] As an optional embodiment, before verifying the line-transformer relationship of the line to be evaluated based on the basic electricity consumption information, the process includes: acquiring basic electricity consumption information through an electricity consumption information acquisition platform, wherein the electricity consumption information acquisition platform includes at least: an electricity consumption information acquisition system, a data acquisition and monitoring control system, and an integrated power consumption and line loss management system.

[0040] In the above optional embodiments, before performing line-transformer verification, basic electricity consumption information is obtained through an electricity consumption information collection platform to verify the line-transformer relationship, making the model more accurate.

[0041] As an optional embodiment, line-transformer relationship verification is performed on the line to be evaluated based on basic electricity consumption information, including: filtering out null values ​​in the voltage curve data of the substations of the line to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; obtaining the filtered voltage curve data of the substations of the line to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; obtaining the DTW distance between each pair of the filtered voltage curve data of the substations of the line to be transmitted and the voltage curve data of public and private transformers within the jurisdiction; using the DTW distance as a feature value, processing the voltage curves of the substations of the line to be transmitted and the voltage curves of public and private transformers within the jurisdiction using a clustering algorithm to complete the line-transformer relationship verification, wherein the clustering algorithm includes at least the k-means clustering algorithm.

[0042] In the above optional embodiments, firstly, null values ​​(i.e., unknown values) in the voltage curve data of the substations to be transmitted and the voltage curve data of public and private transformers within the jurisdiction are filtered out to obtain the filtered data, so as to make the data more accurate; then, the DTW distance (i.e., dynamic time bending distance) between the data is obtained, and the distance is used as a feature value. The voltage curves of the substations to be transmitted and the voltage curves of public and private transformers within the jurisdiction are processed by a clustering algorithm to complete the line-transformer relationship verification, so as to enhance the robustness of the data.

[0043] It should be noted that the power absorption line is a type of high-voltage transmission line that can transmit large amounts of power over long distances.

[0044] Figure 3 This is a structural diagram of an abnormal power consumption detection model based on 2D CNN according to an embodiment of the present invention, as shown below. Figure 3 As shown, when the original sample data is reshaped into a 30*96 dimensional sample matrix, the convolution kernel will slide along both the horizontal and vertical dimensions to extract features.

[0045] As an optional embodiment, before training the machine learning model using the electricity consumption sample set, the method includes: preprocessing abnormal electricity consumption nodes, line loss time intervals, electricity consumption data characteristics, and basic electricity consumption information using a predetermined algorithm to construct an electricity consumption sample set, wherein the predetermined algorithm includes at least: normalization processing.

[0046] In the above optional embodiments, a predetermined algorithm is used to preprocess abnormal electricity consumption nodes, line loss time intervals, electricity consumption data characteristics, and basic electricity consumption information to construct an electricity consumption sample set, so as to make the model more comprehensive and accurate.

[0047] It should be noted that abnormal power consumption nodes are nodes suspected of abnormal power consumption; the line loss time interval is the normal distribution time interval of abnormally bad line loss level.

[0048] Figure 4This is a flowchart of an abnormal power consumption detection model based on 2D CNN according to an embodiment of the present invention, as shown below. Figure 4 As shown, after obtaining the sample data, the data is first normalized and preprocessed. Then, the sample dataset is divided into a training set and a test set in a 7:3 ratio. Next, the training set is upsampled by SMOTE to generate a balanced training set. Then, the abnormal user identification model based on 2DCNN is trained until the training is completed. Finally, the performance of the model is evaluated using the test set.

[0049] As an optional embodiment, abnormal power consumption detection is performed on the line to be evaluated based on the line loss time interval to obtain a set of abnormal power consumption nodes. This includes: obtaining the loss change rate and the actual current amplitude change rate of multiple branches of the line to be evaluated based on the line loss time interval; comparing a preset threshold with the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, respectively, filtering out branches whose preset threshold is greater than the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, and integrating multiple filtered branches to obtain a set of abnormal power consumption nodes.

[0050] Figure 5 This is a flowchart of a preferred method for determining high-voltage transmission line loss branches according to an embodiment of the present invention, such as... Figure 5 As shown, the method includes the following steps:

[0051] S1: Obtain AMI power consumption data, SCADA measurement data, and statistical line loss related data from multiple system platforms such as the power consumption information collection system, data acquisition and monitoring control system, and integrated power consumption and line loss management system;

[0052] S2: Based on the principle of voltage similarity, the voltage curves of the substations of the 10kV transmission line under test and the voltage curves of public and private transformers in the area under its jurisdiction are used. The line-transformer relationship of the 10kV transmission line under test is verified by the k-means clustering method based on the DTW algorithm. The user profile information of the 10kV transmission line under test is adjusted according to the line-transformer relationship verification results.

[0053] S3: Using the theoretical line loss calculation method based on capacity correction, complete the point-by-point theoretical line loss calculation of the 10kV transmission line under test. Combined with the actual statistical line loss level in the integrated power and line loss management system, complete the rationality assessment of the line loss level of the 10kV transmission line under test, and give the time period of abnormal line loss level.

[0054] S4: Based on the abnormal time period of the line loss level, use the abnormal power consumption detection method based on the branch electrical parameter characteristics to detect abnormal power consumption of the 10kV transmission line under test, obtain the list of suspected branches with abnormal power consumption, and obtain the list of all suspected nodes based on the list of suspected branches.

[0055] S5: For the 10kV transmission line under test, based on historical AMI electricity consumption data, data preprocessing methods such as interpolation are used to further extract electricity consumption data features and construct an electricity consumption sample set;

[0056] S6: Divide the sample set, train an abnormal power consumption detection model based on 2D CNN, and evaluate the trained model;

[0057] S7: Based on the abnormal time period of the line loss level and the list of suspected nodes, construct input samples, input the abnormal power consumption detection model based on 2D CNN, perform abnormal power consumption detection on the 10kV transmission line under test, obtain the list of suspected users of abnormal power consumption, adjust the list of suspected branches according to the list of suspected users, and further update the list of suspected branches.

[0058] Preferably, the k-means clustering method based on the DTW algorithm in step S2 includes the following steps:

[0059] S21: Obtain the voltage curve data of the substation and the voltage curve data of the public transformer and the special transformer of the 10kV transmission line to be tested, and remove the null values ​​in the original voltage curve data.

[0060] S22: Calculate the DTW distance between each pair of the voltage curve data of the substation and the voltage curve data of all public and private transformers;

[0061] S23: Using the DTW distance between each voltage curve of the public or special transformer under test and all other voltage curves as its feature, and using the k-means clustering algorithm to cluster all voltage curves of the public or special transformer under test, the line-transformer relationship verification of the 10kV transmission line under test can be completed.

[0062] Preferably, the theoretical line loss calculation method based on capacity correction described in step S3 includes the following steps:

[0063] S31: Based on the network topology and node connectivity of the transmission line, calculate the connectivity matrix of the nodes and combine it with the user electricity consumption data to obtain the cumulative electricity sales of each node.

[0064] S32: Based on the cumulative electricity sales of each node, calculate the theoretical loss value of the transmission line in each calculation section. The theoretical loss value of the transmission line in each calculation section is as follows:

[0065]

[0066] ...

[0067] Among them, segment j:j has no downstream users;

[0068] The j:x segment has downstream users.

[0069] S33: Based on the transmission line network topology, the node connectivity, and the transformer parameters, calculate the theoretical copper loss and theoretical iron loss of the transmission step-up transformer;

[0070] S34: Based on the theoretical loss values ​​of the transmission lines in each section, the theoretical copper loss and theoretical iron loss of the transmission step-up transformer, the theoretical line loss value of the 10kV transmission line to be tested is obtained by summing.

[0071] Preferably, the abnormal power consumption detection method based on branch electrical parameter characteristics in step S4 includes the following steps:

[0072] S41: Based on the AMI power consumption data, obtain the active and reactive power, current and voltage amplitude data of the end user side of the transmission line. Combine the data such as the transmission line network topology and line parameters, calculate the loss and current amplitude of each branch of the transmission line through power flow calculation, and use them as the standard values ​​of loss and current amplitude of each branch.

[0073] S42: Obtain the actual values ​​of loss and current amplitude of each branch through measuring devices such as FTU;

[0074] S43: Calculate the rate of change of loss and current amplitude of each branch based on the standard values ​​of loss and current amplitude of each branch and the actual values ​​of loss and current amplitude of each branch.

[0075] S44: When there is an extreme point 1 where the absolute value of the branch loss change rate is greater than the threshold, and an extreme point 2 where the absolute value of the current amplitude change rate is greater than the threshold, and the extreme point 1 and extreme point 2 are electrically close, it is determined that the branches with large losses and current amplitudes near extreme point 1 and extreme point 2 are suspected of abnormal power consumption, thereby obtaining a list of suspected branches.

[0076] Preferably, step S5 requires interpolation processing of the original historical AMI electricity consumption data to unify the data with different time resolutions into a 15-minute time resolution. The electricity consumption data characteristics in step S5 include: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance. A sliding window method is used, with a sliding time window of 30 days, to construct an electricity consumption sample set. To eliminate the influence caused by inconsistent dimensions, the electricity consumption sample set is normalized.

[0077] Preferably, in step S6, the sample division is carried out in a 7:3 ratio, with 70% used as the training set and 30% as the test set. To address the impact of sample imbalance on the model, the Synthetic Minority Over-Sampling Technique (SMOTE) algorithm is used to process the training set data, generating a certain proportion of minority class samples to achieve sample balance. The evaluation metrics for the model are accuracy, precision, recall, and score.

[0078] As can be seen from the above, the method provided by the embodiments of the present invention has the following beneficial effects compared with the prior art:

[0079] (1) Based on theoretical line loss calculation, a reasonable assessment of the line loss level of 10kV transmission lines was completed. It can comprehensively consider the differences in basic characteristics such as power supply radius and line equipment status of different 10kV transmission lines, avoid "one-size-fits-all" approach, and realize the assessment method of "one line, one loss".

[0080] (2) The abnormal electricity consumption detection method based on branch electrical parameter characteristics can effectively detect users who steal electricity without meters in 10kV transmission lines, making up for the deficiency of the abnormal electricity consumption detection method based on big data, which can only detect users who steal electricity with meters. Combined with the abnormal electricity consumption detection model based on 2D CNN, it ensures the feasibility of detecting various abnormal electricity consumption users in 10kV transmission lines, and provides an effective and relatively comprehensive detection method for abnormal electricity consumption detection in 10kV transmission lines.

[0081] (3) The power consumption sample model based on 2D CNN constructs the power consumption sample set by using a sliding window method, which increases the number of samples and alleviates the problem of insufficient abnormal power consumption samples to a certain extent. At the same time, the SMOTE sampling algorithm is used to sample the training set data, which solves the problem of sample imbalance under actual working conditions.

[0082] Example 2

[0083] According to another aspect of the present invention, a device for determining the branch of a high-voltage transmission line with line loss is also provided. Figure 6 This is a schematic diagram of a device for determining the branch loss of a high-voltage transmission line according to an embodiment of the present invention, as shown below. Figure 6 As shown, it includes: a line-to-line relationship verification module 61, a line loss assessment module 63, an abnormal power consumption detection module 65, a training module 67, and a first acquisition module 69.

[0084] The line-transformer relationship verification module 61 is used to verify the line-transformer relationship of the line to be evaluated based on the basic electricity consumption information and obtain the verification results. The basic electricity consumption information includes at least: user historical electricity consumption data, historical line loss data, voltage curve data of the substation of the line to be transmitted, voltage curve data of public transformers and private transformers in the jurisdiction, and electricity consumption data characteristics. The electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance. The verification results characterize the degree of line loss of the line to be evaluated.

[0085] The line loss assessment module 63 is used to assess the line loss of the line to be assessed based on the verification results and obtain the line loss time interval, wherein the line loss time interval is the time interval during which the line to be assessed experiences line loss.

[0086] The abnormal power consumption detection module 65 is used to detect abnormal power consumption of the line to be evaluated based on the line loss time interval and obtain the abnormal power consumption node set.

[0087] Training module 67 is used to train a machine learning model using an electricity consumption sample set to obtain an abnormal electricity consumption detection model. The electricity consumption sample set includes at least: an abnormal electricity consumption node set, a line loss time interval, and basic electricity consumption information.

[0088] The first acquisition module 69 is used to input the current basic electricity consumption information into the abnormal electricity consumption detection model to obtain the target line loss branch.

[0089] It should be noted that the aforementioned line-to-line relationship verification module 61, line loss assessment module 66, abnormal power consumption detection module 65, training module 67, and first acquisition module 69 correspond to steps S102 to S110 in Embodiment 1. The instances and application scenarios implemented by these modules and their corresponding steps are the same, but they are not limited to the content disclosed in Embodiment 1. It should be noted that the aforementioned modules, as part of a device, can be executed in a computer system such as a set of computer-executable instructions.

[0090] As can be seen from the above, in this embodiment of the invention, the line-transformer relationship verification module 61 can first verify the line-transformer relationship of the line to be evaluated based on the basic electricity consumption information to obtain the verification result. The basic electricity consumption information includes at least: historical electricity consumption data of users, historical line loss data, voltage curve data of the substation of the line to be transmitted, voltage curve data of public and private transformers within the jurisdiction, and electricity consumption data characteristics. The electricity consumption data characteristics include at least: average three-phase active power, average three-phase voltage, average three-phase current, average three-phase power factor, voltage imbalance, and current imbalance. The verification result characterizes the degree of line loss of the line to be evaluated. Then, the line loss assessment module 63 uses the verification result to... The line loss assessment of the line to be evaluated is performed to obtain the line loss time interval, which is the time interval during which line loss occurs on the line to be evaluated. Then, the abnormal power consumption detection module 65 is used to detect abnormal power consumption on the line to be evaluated based on the line loss time interval, obtaining a set of abnormal power consumption nodes. Next, the training module 67 can be used to train a machine learning model using a power consumption sample set to obtain an abnormal power consumption detection model. The power consumption sample set includes at least: a set of abnormal power consumption nodes, the line loss time interval, and basic power consumption information. Finally, the first acquisition module 69 can be used to input the current basic power consumption information into the abnormal power consumption detection model to obtain the target line loss branch. The high-voltage transmission line loss branch determination device provided in this embodiment of the invention achieves the goal of obtaining an abnormal power consumption node set after assessing line loss based on basic power consumption information, then training an abnormal power consumption detection model, and using this model to obtain the target line loss branch. This achieves the technical effect of improving fault detection efficiency and solves the technical problem of low efficiency in methods for finding line loss branches during high-voltage transmission in related technologies.

[0091] As an optional embodiment, the method further includes: a second acquisition module, used to acquire basic electricity consumption information through an electricity consumption information acquisition platform before performing line-transformer relationship verification on the line to be evaluated based on the basic electricity consumption information, wherein the electricity consumption information acquisition platform includes at least: an electricity consumption information acquisition system, a data acquisition and monitoring control system, and an integrated power consumption and line loss management system.

[0092] As an optional embodiment, the line-transformer relationship verification module includes: a filtering unit, used to filter out null values ​​in the voltage curve data of the substation of the transmission line to be transmitted and the voltage curve data of public transformers and dedicated transformers within the jurisdiction, and obtain the filtered voltage curve data of the substation of the transmission line to be transmitted and the voltage curve data of public transformers and dedicated transformers within the jurisdiction; a first acquisition unit, used to acquire the DTW distance between each pair of the filtered voltage curve data of the substation of the transmission line to be transmitted and the voltage curve data of public transformers and dedicated transformers within the jurisdiction; and a processing unit, used to use the DTW distance as a feature value and process the voltage curves of the substation of the transmission line to be transmitted and the voltage curves of public transformers and dedicated transformers within the jurisdiction using a clustering algorithm to complete the line-transformer relationship verification, wherein the clustering algorithm includes at least the k-means clustering algorithm.

[0093] As an optional embodiment, the method further includes: a preprocessing unit, used to preprocess abnormal electricity consumption nodes, line loss time intervals, electricity consumption data characteristics, and basic electricity consumption information using a predetermined algorithm before training the machine learning model with the electricity consumption sample set, thereby constructing an electricity consumption sample set, wherein the predetermined algorithm includes at least: normalization processing.

[0094] As an optional embodiment, the abnormal power consumption monitoring module includes: a second acquisition unit, used to acquire the loss change rate and the actual current amplitude change rate of multiple branches of the line to be evaluated based on the line loss time interval; and a comparison unit, used to compare a preset threshold with the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, respectively, to filter out branches whose preset threshold is greater than the absolute value of the loss change rate and the absolute value of the actual current amplitude change rate, and to integrate multiple filtered branches to obtain an abnormal power consumption node set.

[0095] Example 3

[0096] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is run by a processor, it controls the device where the computer-readable storage medium is located to execute any of the above-described methods for determining the loss branch of a high-voltage transmission line.

[0097] Example 4

[0098] According to another aspect of the present invention, a processor is also provided, which is configured to run a computer program, wherein the computer program executes any of the above-described methods for determining the loss branches of high-voltage transmission lines.

[0099] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0100] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0102] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0103] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0104] If the integrated unit is implemented as 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0105] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining a loss branch of a high-voltage transmission line, characterized in that, The method comprises the following steps: Based on the power consumption basic information, the line-voltage relationship of the to-be-evaluated line is verified, and a verification result is obtained, wherein the power consumption basic information at least includes: user historical power consumption data, historical line loss data, to-be-transmitted line substation voltage curve data, voltage curve data of public and special transformer substations in the jurisdictional area, and power consumption data characteristics, the power consumption data characteristics at least include: three-phase active power mean value, three-phase voltage mean value, three-phase current mean value, three-phase power factor mean value, voltage unbalance degree, and current unbalance degree, and the verification result represents the line loss degree of the to-be-evaluated line; Based on the verification result, the line loss of the to-be-evaluated line is evaluated, and a line loss time interval is obtained, wherein the line loss time interval is the time interval in which the line loss of the to-be-evaluated line occurs; Based on the line loss time interval, abnormal power consumption detection is performed on the to-be-evaluated line, and an abnormal power consumption node set is obtained; An abnormal power consumption detection model is trained by using a power consumption sample set, wherein the power consumption sample set at least includes: the abnormal power consumption node set, the line loss time interval, and the power consumption basic information; Current power consumption basic information is input into the abnormal power consumption detection model, and a target line loss branch is obtained; The line-voltage relationship verification of the to-be-evaluated line based on the power consumption basic information comprises: The null values in the to-be-transmitted line substation voltage curve data and the voltage curve data of public and special transformer substations in the jurisdictional area are screened out, and the screened to-be-transmitted line substation voltage curve data and the voltage curve data of public and special transformer substations in the jurisdictional area are obtained; The DTW distances between the screened to-be-transmitted line substation voltage curve data and the voltage curve data of public and special transformer substations in the jurisdictional area are obtained; The DTW distances are taken as characteristic values, and the to-be-transmitted line substation voltage curve and the voltage curve of public and special transformer substations in the jurisdictional area are processed by using a clustering algorithm to complete the line-voltage relationship verification, wherein the clustering algorithm at least includes: a k-means clustering algorithm.

2. The method of claim 1, wherein, Before the line-voltage relationship verification of the to-be-evaluated line based on the power consumption basic information, the following steps are included: The power consumption basic information is obtained through a power consumption information collection platform, wherein the power consumption information collection platform at least includes: a power consumption information collection system, a data collection and monitoring control system, and an integrated power and line loss management system.

3. The method of claim 1, wherein, Before the machine learning model is trained by using the power consumption sample set, the following steps are included: The abnormal power consumption node, the line loss time interval, the power consumption data characteristics, and the power consumption basic information are preprocessed by using a predetermined algorithm, and the power consumption sample set is constructed, wherein the predetermined algorithm at least includes: normalization processing.

4. The method of claim 1, wherein, Based on the line loss time interval, abnormal power consumption detection is performed on the to-be-evaluated line, and an abnormal power consumption node set is obtained, which comprises: Based on the line loss time interval, the loss change rate and the current amplitude actual value change rate of multiple branches of the to-be-evaluated line are obtained; The preset threshold is compared with the absolute values of the loss change rate and the current amplitude actual value change rate respectively, branches with the preset threshold greater than the absolute values of the loss change rate and the current amplitude actual value change rate are screened out, and the screened out branches are integrated to obtain an abnormal power consumption node set.

5. A device for determining a loss branch of a high-voltage transmission line, characterized in that Comprise: The line variable relationship verification module is used for verifying the line variable relationship of the to-be-evaluated line based on the power consumption basic information, and obtaining a verification result, wherein the power consumption basic information at least includes: user historical power consumption data, historical line loss data, to-be-supplied line variable station voltage curve data, voltage curve data of public variable and special variable in the jurisdiction area, and power consumption data features, the power consumption data features at least include: three-phase active power mean value, three-phase voltage mean value, three-phase current mean value, three-phase power factor mean value, voltage unbalance degree, and current unbalance degree, and the verification result represents the line loss degree of the to-be-evaluated line; The line loss evaluation module is used for evaluating the line loss of the to-be-evaluated line based on the verification result, and obtaining a line loss time interval, wherein the line loss time interval is a time interval in which the to-be-evaluated line occurs line loss; The abnormal power consumption detection module is used for detecting abnormal power consumption of the to-be-evaluated line based on the line loss time interval, and obtaining an abnormal power consumption node set; The training module is used for training a machine learning model by using a power consumption sample set, and obtaining an abnormal power consumption detection model, wherein the power consumption sample set at least includes: the abnormal power consumption node set, the line loss time interval, and the power consumption basic information; The first obtaining module is used for inputting current power consumption basic information into the abnormal power consumption detection model, and obtaining a target line loss branch; The line variable relationship verification module comprises: The screening unit is used for excluding null values in the to-be-supplied line variable station voltage curve data and the voltage curve data of public variable and special variable in the jurisdiction area, and obtaining the to-be-supplied line variable station voltage curve data and the voltage curve data of public variable and special variable in the jurisdiction area after screening; The first obtaining unit is used for obtaining DTW distances between the to-be-supplied line variable station voltage curve data and the voltage curve data of public variable and special variable in the jurisdiction area after screening; The processing unit is used for taking the DTW distances as characteristic values, processing the to-be-supplied line variable station voltage curve and the voltage curve of public variable and special variable in the jurisdiction area by a clustering algorithm, so as to complete line variable relationship verification, wherein the clustering algorithm at least includes: k-means clustering algorithm.

6. The apparatus of claim 5, wherein, Comprise: The second obtaining module is used for obtaining the power consumption basic information through a power consumption information collection platform before verifying the line variable relationship of the to-be-evaluated line based on the power consumption basic information, wherein the power consumption information collection platform at least includes: a power consumption information collection system, a data collection and monitoring control system, and an integrated power and line loss management system.

7. A computer readable storage medium characterized by The computer readable storage medium comprises a stored computer program, wherein the computer program controls the device where the computer readable storage medium is located to perform the method for determining the loss branch of the high-voltage transmission line according to any one of claims 1 to 4 when the computer program is run by the processor.

8. A processor, comprising: The processor is configured to run a computer program, wherein the computer program performs the method for determining the loss branch of the high-voltage transmission line according to any one of claims 1 to 4 when the computer program is run.

Images