Abnormal data detection method of smart substation based on K-means-SVM

Wei Zhai; Yanping Wu; Bochao Qi; Tiantian Xue; Qing Wu

doi:10.1117/12.3008728

27 October 2023 Abnormal data detection method of smart substation based on K-means-SVM

Wei Zhai, Yanping Wu, Bochao Qi, Tiantian Xue, Qing Wu

Proceedings Volume 12922, Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023); 129220Q (2023) https://doi.org/10.1117/12.3008728
Event: The Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023), 2023, Xiamen, China

Abstract

The safe operation of smart substation is an important guarantee to ensure the stability of power supply. Aiming at the problems of substation data anomaly identification caused by large amount of substation data, complex data and high dimension, a smart substation anomaly data detection method based on K-means-SVM is proposed in this paper. Firstly, the unlabeled substation data is transformed into labeled data by K-means method, and then the unsupervised classification results provided by K-means are used as the training data of SVM. After SVM training, use the trained plane to test the two types of data obtained by K-means clustering, use the accurate data predicted by SVM to retrain the SVM segmentation plane, and iteratively update the SVM segmentation plane according to this method until the error number of SVM prediction data is not changed. This method can effectively improve the accuracy and efficiency of substation abnormal data identification, so as to improve the operation and maintenance safety and equipment maintenance ability.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Wei Zhai, Yanping Wu, Bochao Qi, Tiantian Xue, and Qing Wu "Abnormal data detection method of smart substation based on K-means-SVM", Proc. SPIE 12922, Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023), 129220Q (27 October 2023); https://doi.org/10.1117/12.3008728

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available