About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
ew 23(1):

Research Article

Fault Diagnosis Algorithm Based on Power Outage Data in Power Grid

Download131 downloads
Cite
BibTeX Plain Text
  • @ARTICLE{10.4108/ew.4657,
        author={Haiyan Wang and Xinping Yuan and Shanfei Gao and Shoushan Gao},
        title={Fault Diagnosis Algorithm Based on Power Outage Data in Power Grid},
        journal={EAI Endorsed Transactions on Energy Web},
        volume={10},
        number={1},
        publisher={EAI},
        journal_a={EW},
        year={2023},
        month={12},
        keywords={Power grid, Fault diagnosis, Support vector machines, Decision tree},
        doi={10.4108/ew.4657}
    }
    
  • Haiyan Wang
    Xinping Yuan
    Shanfei Gao
    Shoushan Gao
    Year: 2023
    Fault Diagnosis Algorithm Based on Power Outage Data in Power Grid
    EW
    EAI
    DOI: 10.4108/ew.4657
Haiyan Wang1,*, Xinping Yuan1,*, Shanfei Gao1,*, Shoushan Gao1,*
  • 1: Yunnan Power Grid Co., Ltd. Kunming Enersun Technology Co., Ltd. Kunming 65000, Yunnan, China
*Contact email: 18208891009@163.com, 101170084@ousn.edu.cn, 101170084@ousn.edu.cn, 101170084@ousn.edu.cn

Abstract

INTRODUCTION: With the rapid development of the power industry, the power system has become more and more complex and prone to failures, which seriously impacts power supply and safety. OBJECTIVES: Development of efficient and accurate fault diagnosis algorithms for power systems. METHODS:Proposes a fault diagnosis algorithm based on outage data to construct an outage fault prediction model using accurate data. First, the outage data are collected, pre-processed, feature extracted and reduced to obtain a more efficient data set. Then, an optimized fault diagnosis algorithm is designed based on logit, support vector machine (SVM) and decision tree (DT) to improve the accuracy and efficiency of fault diagnosis. RESULTS: The method is applied to the natural power system, and the results show that the optimization algorithm outperforms the traditional methods.   Specifically, the accuracy of the optimization algorithm can reach 100%, while the accuracy of the traditional logit algorithm and SVM algorithm is only 84% and 93%, which is a significant improvement in the model prediction performance. CONCLUSION: The author can significantly optimize the performance of its model and construct an outage data mining algorithm with a good predictive ability to achieve grid fault research and judgment, which has a specific application value in the practical field.

Keywords
Power grid, Fault diagnosis, Support vector machines, Decision tree
Received
2023-04-27
Accepted
2023-12-15
Published
2023-12-20
Publisher
EAI
http://dx.doi.org/10.4108/ew.4657

Copyright © 2023 Wang et al., licensed to EAI. This open-access article is distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transforming, and building upon the material in any medium so long as the original work is properly cited.

EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL