Transformer area user-transformer relation abnormity diagnosis method and device

Abstract

The invention discloses a transformer area user-transformer relation abnormity diagnosis method and device, and the method comprises the steps: S01, obtaining a total meter and user ammeter voltage data of a specified transformer area, and carrying out the dimension reduction processing, and obtaining dimension-reduced voltage data; S02, clustering the dimension-reduced voltage data by adopting a Kmeans clustering method, selecting an initial clustering center according to the maximum value and the minimum value of the data dimension in the clustering process, and finding out abnormal users with abnormal user-transformer relationships in a specified transformer area; S03, respectively calculating Pearson correlation coefficients between the abnormal user and each transformer area general table, sorting the calculated Pearson correlation coefficients, and diagnosing a correct transformer area to which the abnormal user belongs according to a sorting result. The method can realize diagnosis of one or more abnormal users in the same transformer area and multiple abnormal users in different transformer areas, and has the advantages of simple realization method, high diagnosis efficiency and precision and the like.

Description

technical field [0001] The invention relates to the technical field of electricity consumption information collection systems, and in particular to a method and device for diagnosing abnormalities in household-to-substation relations in a station area. Background technique [0002] With the rapid development of power grid construction, the power consumption information collection system containing massive data can not only directly reflect the operation status of the distribution network, but also indirectly reflect the topological relationship of the distribution network. The existing distribution network topology verification mainly includes: line-to-substation relationship verification, feeder topology verification, household-to-substation relationship and phase verification, and line-to-household relationship verification. The correct low-voltage distribution network topology, especially the correct relationship between households and transformers is the basis for the cu...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, there are mainly two methods of on-site identification by manual special equipment and online automatic identification in the verification station area. The manual method needs to arrange staff to identify on-site, which has low identification efficiency and high cost. Online automatic identification can solve the problem of manual identification. The above-mentioned problems existing in the method, the current online automatic identification method is mainly based on data mining technology, by extracting the abnormal user characteristics of the station area to identify the station area with the same characteristics, such as by extracting the similarity characteristics of the user voltage curve to realize the abnormal diagnosis of the household change relationship in the station area , in the low-voltage distribution network, due to the uncertainty of the loads everywhere, the voltage usually fluctuates accordingly. The loads with a closer electrical distance have similar voltage fluctuation curves, while the loads with a farther electrical distance have a lower similarity in voltage fluctuation curves. , so the user voltage curve similarity can be selected as the basis for abnormal diagnosis of the household-to-substation relationship

However, the above-mentioned online automatic identification method needs to rely on the feature extraction of abnormal users, which can only be used for the case of a small number of abnormal users in the station area. In the case of abnormal users, it is difficult to extract a large number of abnormal user features, and the information that can be represented by the extracted features is limited, so it is difficult to quickly and accurately realize the diagnosis and analysis of multi-user station areas and multiple abnormal users

Images