Abnormal electricity consumption monitoring method and system

Abstract

The invention discloses an abnormal power consumption monitoring method and system, and the method comprises the steps: obtaining historical power consumption data of a target power distribution network, and constructing an abnormal monitoring sample library; training the power consumption diagnosis model based on the abnormal monitoring sample library, and optimizing the target power consumption diagnosis model based on a self-learning technology to obtain a trained and optimized target power consumption diagnosis model; in the actual abnormal power consumption monitoring process, performing feature extraction processing on the obtained real-time data of the target power distribution network to obtain a power operation feature data set; and inputting the data into the optimized target power consumption diagnosis model, and outputting a monitoring result. According to the abnormal power consumption monitoring method provided by the embodiment of the invention, the accuracy and efficiency of abnormal power consumption diagnosis are improved, and missing detection and misjudgment are reduced; through a self-learning mechanism, new abnormal conditions and power consumption modes can be continuously adapted, and the flexibility and adaptability of the system are improved; and a complicated electricity utilization environment can be better dealt with, and more reliable service can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic metrology, and in particular, to a method and system for monitoring abnormal electricity consumption. Background Art

[0002] Electronic metrology technology features high precision, high stability, and high reliability, and can accurately measure the consumption and distribution of electrical energy in a power system. By adopting advanced electronic metering equipment and systems, real-time monitoring and collection of power data can be achieved, improving metering accuracy, reducing metering errors, and thus ensuring the economy and fairness of the power system.

[0003] In the prior art, manual inspections are mainly relied on to monitor abnormal electricity consumption, which has problems of low efficiency and low accuracy, and it is difficult to ensure the stable operation of the power grid system.

[0004] Thus, how to improve the accuracy of monitoring abnormal electricity consumption has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a method and system for monitoring abnormal electricity consumption to solve the technical problems of the accuracy, efficiency, flexibility, and adaptability of abnormal electricity consumption diagnosis, so as to achieve the effects of improving the accuracy and efficiency of abnormal electricity consumption diagnosis and enhancing the flexibility and adaptability of the system.

[0006] To solve the above technical problems, an embodiment of the present invention provides a method for monitoring abnormal electricity consumption, including:

[0007] Obtain historical electricity consumption data of a target distribution network, and based on the historical electricity consumption data, construct an abnormal monitoring sample library; train a constructed electricity consumption diagnosis model based on the abnormal monitoring sample library to obtain a trained target electricity consumption diagnosis model, and optimize the target electricity consumption diagnosis model based on neural network self-learning technology to obtain an optimized target electricity consumption diagnosis model; in the actual process of monitoring abnormal electricity consumption, perform feature extraction processing on the obtained real-time data of the target distribution network to obtain a power operation feature data set; input the power operation feature data set into the optimized target electricity consumption diagnosis model, and output the monitoring result of the target distribution network.

[0008] As one of the preferred solutions, it includes:

[0009] After outputting the monitoring result of the target distribution network, execute an abnormal repair strategy that matches the monitoring result on the target distribution network, and the abnormal repair strategy includes at least a grid maintenance strategy and a log generation strategy.

[0010] As one of the preferred solutions, it includes:

[0011] After detecting that the repair task corresponding to the grid maintenance strategy executed by the target distribution network is completed, upload the real-time updated status data of the target distribution network to the abnormal monitoring sample database

[0012] As one of the preferred solutions, it includes:

[0013] When detecting that the target distribution network executes the log generation strategy, send the generated log to the cloud server for storage.

[0014] As one of the preferred solutions, it includes:

[0015] After obtaining the optimized target power consumption diagnosis model, perform model evaluation processing on the optimized target power consumption diagnosis model.

[0016] Another embodiment of the present invention provides an abnormal power consumption monitoring system, including:

[0017] A construction module for analyzing the historical power consumption data of the target distribution network obtained and constructing an abnormal monitoring sample database;

[0018] A training module for training the target power consumption diagnosis model and obtaining the trained target power consumption diagnosis model based on the abnormal monitoring sample database;

[0019] An optimization module for optimizing the target power consumption diagnosis model and obtaining the optimized target power consumption diagnosis model based on the neural network self-learning technology;

[0020] A monitoring module for performing feature extraction processing on the real-time data of the target distribution network obtained to obtain a power operation feature data set;

[0021] An input module for inputting the power operation feature data set into the optimized target power consumption diagnosis model and outputting a monitoring result.

[0022] Another embodiment of the present invention provides an abnormal power consumption monitoring system, including:

[0023] A repair module for executing an abnormal repair strategy matching the monitoring result on the target distribution network, and the abnormal repair strategy includes at least a grid maintenance strategy and a log generation strategy.

[0024] Another embodiment of the present invention provides an abnormal power consumption monitoring system, including:

[0025] An update module for uploading the real-time updated status data of the target distribution network to the abnormal monitoring sample database after detecting that the repair task corresponding to the grid maintenance strategy executed by the target distribution network is completed.

[0026] Another embodiment of the present invention provides an abnormal power consumption monitoring system, including:

[0027] The logging module is used to generate logs from the output monitoring results and send the logs to the cloud server for storage.

[0028] Another embodiment of the present invention provides an abnormal power consumption monitoring system, including:

[0029] The evaluation module is used to perform model evaluation processing on the optimized target power consumption diagnosis model.

[0030] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0031] (1) By establishing a power consumption diagnosis model, it is possible to deeply analyze the subtle features of power consumption data, accurately capture abnormal signals, and thus effectively distinguish normal power consumption from abnormal power consumption. This not only improves the reliability of the diagnosis results, but also provides a more accurate judgment basis for the operation and maintenance personnel, helping them take targeted measures in a timely manner;

[0032] (2) Through the neural network self-learning mechanism, the system can continuously learn from new abnormal situations and power consumption patterns and self-optimize, reducing manual intervention and improving the timeliness and accuracy of the system. This improvement in flexibility and adaptability not only enhances the stability and reliability of the system, but also brings great convenience to the operation and maintenance management of the power system;

[0033] (3) The system's good ability to cope with complex power consumption environments is reflected in its ability to accurately identify and quickly respond to various power consumption anomalies. Whether it is a sharp change in power consumption load or a latent fault in power equipment, the system can accurately capture and timely diagnose through advanced monitoring technologies. This not only helps the operation and maintenance personnel take measures in a timely manner to avoid potential safety hazards, but also ensures the stable operation of the power system and the power consumption safety of users. At the same time, providing more reliable power consumption anomaly monitoring and diagnosis services also means that the system can bring a better power service experience to users. Users do not need to worry about power outages or equipment damage caused by power consumption anomalies and can use power resources with more confidence. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a schematic flowchart of an abnormal power consumption monitoring method in one embodiment of the present invention;

[0035] Figure 2 is a schematic diagram of the modules of an abnormal power consumption monitoring system in one embodiment of the present invention;

[0036] Reference Signs in the Drawings:

[0037] 11. Construction module; 12. Training module; 13. Optimization module; 14. Monitoring module; 15. Input module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the scope of protection of the present invention.

[0039] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0040] In the description of the present application, it should be noted that, unless otherwise clearly defined and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0041] In the description of the present application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which this technology belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0042] The embodiments of the present invention provide an abnormal power consumption monitoring method. Specifically, please refer to Figure 1 , Figure 1 which shows a schematic flowchart of the abnormal power consumption monitoring method in one of the embodiments of the present invention, including steps S1 to S4:

[0043] S1. Obtain the historical power consumption data of the target distribution network, and based on the historical power consumption data, construct an abnormal monitoring sample library;

[0044] S2. Train the constructed power consumption diagnosis model based on the abnormal monitoring sample library to obtain a trained target power consumption diagnosis model, and optimize the target power consumption diagnosis model based on the neural network self-learning technology to obtain an optimized target power consumption diagnosis model;

[0045] S3. In the actual abnormal power consumption monitoring process, perform feature extraction processing on the obtained real-time data of the target distribution network to obtain a power operation feature data set;

[0046] S4. Input the power operation feature data set into the optimized target power consumption diagnosis model, and output the monitoring result of the target distribution network.

[0047] In the above embodiment, the historical power consumption data is preferably information such as voltage, current, and power of the terminal and the electric energy meter. For the acquisition method of the historical power consumption data, it can also be realized by high-frequency acquisition, which is not specifically limited in the embodiments of the present invention.

[0048] Further, in the above embodiment, in order to improve the accuracy of the data, the data can be preprocessed to improve its data accuracy. Specifically, the preprocessing method can be data cleaning, data missing, data filling, and data normalization processing to remove abnormal data and noise and improve the data quality.

[0049] Further, in the above embodiment, it is preferably to use machine learning algorithms such as neural networks and decision trees to construct a power consumption diagnosis model. In order to accurately identify abnormal power consumption, the abnormal monitoring sample library can be divided into a training set and a test set, and the training set is used to train the power consumption diagnosis model and adjust the parameters of the model.

[0050] Further, in the above embodiment, the neural network self-learning technology is preferably in the ways of supervised learning, unsupervised learning, and reinforcement learning. The neural network self-learning technology is used to analyze the historical power consumption data regularly, discover new abnormal patterns, and update the target power consumption diagnosis model.

[0051] Further, in the above embodiment, the power operation feature data set is preferably the data collected by the electric energy meter such as voltage, current, active power, power factor, and harmonic content, as well as the analysis and calculation data such as voltage / current unbalance rate, voltage over-limit, indication imbalance, and electric energy meter flying away.

[0052] Furthermore, in the above embodiment, for the monitored results obtained, this embodiment sets relevant anomaly repair strategies. Preferably, the anomaly repair strategies include two types. One is the power grid maintenance strategy, whose function is to alarm and notify, execute the repair tasks corresponding to the power grid maintenance strategy, and upload the real-time updated status data of the target distribution network to the anomaly monitoring sample library. The other is the log generation strategy, which sends the generated logs to the cloud server for storage.

[0053] Furthermore, in the above embodiment, after obtaining the optimized target power consumption diagnosis model, model evaluation processing is performed on the optimized target power consumption diagnosis model. The evaluation metrics are preferably accuracy, recall rate, F1 value, etc.

[0054] An embodiment of the present invention provides an abnormal power consumption monitoring system. Specifically, please refer to Figure 2 , Figure 2 which shows a module schematic diagram of the abnormal power consumption monitoring system in one of the embodiments of the present invention, including:

[0055] A construction module 11, configured to analyze the historical power consumption data of the obtained target distribution network and construct an anomaly monitoring sample library;

[0056] A training module 12, configured to train the target power consumption diagnosis model and obtain a trained target power consumption diagnosis model based on the anomaly monitoring sample library;

[0057] An optimization module 13, configured to optimize the target power consumption diagnosis model and obtain an optimized target power consumption diagnosis model based on the neural network self-learning technology;

[0058] A monitoring module 14, configured to perform feature extraction processing on the real-time data of the obtained target distribution network to obtain a power operation feature data set;

[0059] An input module 15, configured to input the power operation feature data set into the optimized target power consumption diagnosis model and output the monitoring results.

[0060] In the above embodiment, the historical power consumption data is preferably information such as voltage, current, and power of the terminal and the electric energy meter. For the acquisition method of the historical power consumption data, it can also be achieved by high-frequency acquisition, which is not specifically limited in the embodiment of the present invention.

[0061] Furthermore, in the above embodiment, in order to improve the accuracy of the data, the data can be preprocessed to improve its data accuracy. Specifically, the preprocessing methods can be data cleaning, data missing, data filling, and data normalization processing to remove abnormal data and noise and improve the data quality.

[0062] Further, in the above embodiments, it is preferably to use machine learning algorithms such as neural networks and decision trees to construct an electricity consumption diagnosis model. In order to accurately identify abnormal electricity consumption, the abnormal monitoring sample library can be divided into a training set and a test set, and the training set is used to train the electricity consumption diagnosis model and adjust the parameters of the model.

[0063] Further, in the above embodiments, the neural network self-learning technology is preferably in the ways of supervised learning, unsupervised learning, and reinforcement learning. The neural network self-learning technology is used to analyze historical electricity consumption data regularly, discover new abnormal patterns, and update the target electricity consumption diagnosis model.

[0064] Further, in the above embodiments, the power operation feature data set is preferably the data collected by the electric energy meter such as voltage, current, active power, power factor, harmonic content, etc., and the analysis and calculation data such as voltage / current unbalance rate, voltage over-limit, indication unevenness, and electric energy meter flying away.

[0065] In the above embodiments, after obtaining the monitoring result, a repair module is further included to execute an abnormal repair strategy matching the monitoring result on the target distribution network. The abnormal repair strategy is preferably a grid maintenance strategy and a log generation strategy.

[0066] Further, in the above embodiments, an update module is further included. After monitoring that the repair task corresponding to the grid maintenance strategy is executed on the target distribution network, the real-time update status data of the target distribution network is uploaded to the abnormal monitoring sample library.

[0067] Further, in the above embodiments, a log module is further included to generate a log of the output monitoring result and send the log to the cloud server for storage.

[0068] Further, in the above embodiments, an evaluation module is further included to perform model evaluation processing on the optimized target electricity consumption diagnosis model. The evaluation indexes are preferably accuracy rate, recall rate, F1 value, etc.

[0069] The abnormal electricity consumption monitoring method and system provided by the embodiments of the present invention have at least one of the following beneficial effects:

[0070] (1) By establishing an electricity consumption diagnosis model, it is possible to deeply analyze the subtle features of electricity consumption data, accurately capture abnormal signals, and thus effectively distinguish normal electricity consumption from abnormal electricity consumption. This not only improves the reliability of the diagnosis result, but also provides a more accurate judgment basis for operation and maintenance personnel, helping them take targeted measures in a timely manner;

[0071] (2) Through the neural network self-learning mechanism, the system can continuously learn and self-optimize from new abnormal situations and power consumption patterns, reducing manual intervention and improving the timeliness and accuracy of the system. This enhancement of flexibility and adaptability not only strengthens the stability and reliability of the system but also brings great convenience to the operation and maintenance management of the power system;

[0072] (3) The system's good ability to cope with complex power consumption environments is reflected in its ability to accurately identify and quickly respond to various power consumption anomalies. Whether it is a sharp change in power load or a latent fault in power equipment, the system can achieve precise capture and timely diagnosis through advanced monitoring technologies. This not only helps operation and maintenance personnel take timely measures to avoid potential safety hazards but also ensures the stable operation of the power system and the power consumption safety of users. At the same time, providing more reliable power consumption anomaly monitoring and diagnosis services also means that the system can bring a better power service experience to users. Users do not need to worry about power outages or equipment damage caused by power consumption anomalies and can use power resources with more confidence.

[0073] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. An abnormal power consumption monitoring method, characterized in that Including: Obtain the historical power consumption data of the target distribution network, and construct an abnormal monitoring sample library based on the historical power consumption data; Train the constructed power consumption diagnosis model based on the abnormal monitoring sample library to obtain a trained target power consumption diagnosis model, and optimize the target power consumption diagnosis model based on the neural network self-learning technology to obtain the optimized target power consumption diagnosis model; In the actual abnormal power consumption monitoring process, perform feature extraction processing on the obtained real-time data of the target distribution network to obtain a power operation feature data set; Input the power operation feature data set into the optimized target power consumption diagnosis model, and output the monitoring result of the target distribution network.

2. The abnormal power consumption monitoring method according to claim 1, characterized in that, After the monitoring result of the target distribution network is output, the abnormal power consumption monitoring method further includes: Execute an abnormal repair strategy matching the monitoring result on the target distribution network, and the abnormal repair strategy at least includes a power grid maintenance strategy and a log generation strategy.

3. The abnormal power consumption monitoring method according to claim 2, characterized in that, After executing the abnormal repair strategy matching the monitoring result on the target distribution network, the abnormal power consumption monitoring method further includes: After monitoring that the repair task corresponding to the power grid maintenance strategy executed by the target distribution network is completed, upload the real-time updated status data of the target distribution network to the abnormal monitoring sample library.

4. The abnormal power consumption monitoring method according to claim 2, characterized in that When monitoring that the target distribution network executes the log generation strategy, send the generated log to the cloud server for storage.

5. The abnormal power consumption monitoring method according to claim 1, wherein After obtaining the optimized target power consumption diagnosis model, the abnormal power consumption monitoring method further includes: Perform model evaluation processing on the optimized target power consumption diagnosis model.

6. An abnormal power consumption monitoring system, characterized in that, Including: A construction module for analyzing the historical power consumption data of the obtained target distribution network and constructing an abnormal monitoring sample library; A training module for training the target power consumption diagnosis model and obtaining a trained target power consumption diagnosis model based on the abnormal monitoring sample library; An optimization module for optimizing the target power consumption diagnosis model and obtaining the optimized target power consumption diagnosis model based on the neural network self-learning technology; A monitoring module for performing feature extraction processing on the obtained real-time data of the target distribution network to obtain a power operation feature data set; An input module for inputting the power operation feature data set into the optimized target power consumption diagnosis model and outputting a monitoring result.

7. The abnormal power consumption monitoring system according to claim 6, characterized in that, After the monitoring result is output, the abnormal power consumption monitoring system further includes: A repair module for executing an abnormal repair strategy matching the monitoring result on the target distribution network, and the abnormal repair strategy at least includes a power grid maintenance strategy and a log generation strategy.

8. The abnormal power consumption monitoring system according to claim 7, characterized in that, The abnormal power consumption monitoring system further includes: An update module for uploading the real-time updated status data of the target distribution network to the abnormal monitoring sample library after monitoring that the repair task corresponding to the power grid maintenance strategy executed by the target distribution network is completed.

9. The abnormal power consumption monitoring system according to claim 7, wherein, Including: A log module for generating a log of the output monitoring result and sending the log to the cloud server for storage.

10. The abnormal power consumption monitoring system according to claim 6, characterized in that, Including: An evaluation module for performing model evaluation processing on the optimized target power consumption diagnosis model.

Images