Fault Diagnosis Algorithm Based on Power Outage Data in Power Grid

Haiyan Wang; Xinping Yuan; Shanfei Gao; Shoushan Gao

doi:10.4108/ew.4657

Authors

Haiyan Wang Yunnan Power Grid Co., Ltd. Kunming Enersun Technology Co., Ltd. Kunming 65000, Yunnan, China
Xinping Yuan Yunnan Power Grid Co., Ltd. Kunming Enersun Technology Co., Ltd. Kunming 65000, Yunnan, China
Shanfei Gao Yunnan Power Grid Co., Ltd. Kunming Enersun Technology Co., Ltd. Kunming 65000, Yunnan, China
Shoushan Gao Yunnan Power Grid Co., Ltd. Kunming Enersun Technology Co., Ltd. Kunming 65000, Yunnan, China

DOI:

https://doi.org/10.4108/ew.4657

Keywords:

Power grid, Fault diagnosis, Support vector machines, Decision tree

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.

Downloads

Download data is not yet available.

References

Liu Hengyong, Guo Lu, Liu Yongli & Huang Ziqi. (2020).Research on Efficient Collection Method of Blackout Data in Distribution Network. Journal of Physics: Conference Series(5). doi:10.1088/1742-6596/1549/5/052030.

Supriya Chinthavali. (2019). Seattle City Light Standardizes Outage Data. Transmission & Distribution World.

Chunyan Shuai,Hengcheng Yang,Xin Ouyang,Mingwei He,Zeweiyi Gong & Wanneng Shu.(2019).Analysis and Identification of Power Blackout-Sensitive Users by Using Big Data in the Energy System.. IEEE Access. DOI: https://doi.org/10.1109/ACCESS.2018.2886551

Yue Meng, Toto Tami, Jensen Michael P., Giangrande Scott E. & Lofaro Robert. (2018).A Bayesian Approach-Based Outage Prediction in Electric Utility Systems Using Radar Measurement Data. IEEE Transactions on Smart Grid(6). doi:10.1109/tsg.2017.2704288. DOI: https://doi.org/10.1109/TSG.2017.2704288

Liu Feng,Guo Jinpeng,Zhang Xuemin,Hou Yunhe & Mei Shengwei.(2018).Mitigating the Risk of Cascading Blackouts: A Data Inference Based Maintenance Method. IEEE Access. doi:10.1109/access.2018.2855153. DOI: https://doi.org/10.1109/ACCESS.2018.2855153

Jun Fu, Xin Xu, Zhijie Sun, Li Wang, Dongmei Gong & Lingyu Zhang. (2018). Model Construction of Early Warning for Frequently Outage Complaint Based on Data Mining. MATEC Web of Conferences. doi:10.1051/matecconf/201817301002. DOI: https://doi.org/10.1051/matecconf/201817301002

Gurara Daniel & Tessema Dawit.(2018).Losing to Blackouts: Evidence from Firm-Level Data. IMF Working Papers(159). doi:10.5089/9781484363973.001. DOI: https://doi.org/10.2139/ssrn.3236776

Erwin Normanyo, and Godwin Diamenu."Predicting Reliability of Electric Power Distribution Grid Using Historical Outage Data." American Journal of Electrical Power and Energy Systems 11.4(2022). doi:10.11648/J.EPES.20221104.11.

Han Yi et al." Improved Fault Location Algorithm for Radial Distribution Network Based on Power Failure Information." Journal of Physics: Conference Series 1848.1(2021). doi:10.1088/1742-6596/1848/1/012049. DOI: https://doi.org/10.1088/1742-6596/1848/1/012049

Liu Hengyong et al." Research on Efficient Collection Method of Blackout Data in Distribution Network." Journal of Physics: Conference Series 1549.5(2020). doi:10.1088/1742-6596/1549/5/052030. DOI: https://doi.org/10.1088/1742-6596/1549/5/052030

Qingqing HAO, and Qun YU."Research on blackout simulation model considering hidden failures and reclosing." IOP Conference Series: Earth and Environmental Science 431. (2020). doi:10.1088/1755-1315/431/1/012005. DOI: https://doi.org/10.1088/1755-1315/431/1/012005

A. Sathish Kumar, et al."Contingency Analysis of Fault and Minimization of Power System Outage using Fuzzy Controller." International Journal of Innovative Technology and Exploring Engineering (IJITEE) 9.1(2019). DOI: https://doi.org/10.35940/ijitee.A4461.119119

Supriya Chinthavali."Seattle City Light Standardizes Outage Data." Transmission & Distribution World .(2019).

Sroka Krzysztof,and Złotecka Daria."The risk of significant blackout failures in power systems." Archives of Electrical Engineering 68.2(2019). doi:10.24425/aee.2019.128277. DOI: https://doi.org/10.24425/aee.2019.128277

C.C. Montanari, and P. Dimitriou."The IAEA stopping power database, following the trends in stopping power of ions in matter." Nuclear Inst. and Methods in Physics Research, B 408. (2017). doi:10.1016/j.nimb.2017.03.138. DOI: https://doi.org/10.1016/j.nimb.2017.03.138

Michael M. Li, and Brijesh Verma."Nonlinear curve fitting to stopping power data using RBF neural networks." Expert Systems With Applications 45. (2016). doi:10.1016/j.eswa.2015.09.033. DOI: https://doi.org/10.1016/j.eswa.2015.09.033

Stanko Novakovic et al." An Analysis of Load Imbalance in Scale-out Data Serving." ACM SIGMETRICS Performance Evaluation Review 44.1(2016). doi:10.1145/2964791.2901501. DOI: https://doi.org/10.1145/2964791.2901501

Bahiru Egziabiher, Scott Thomsen, and John Simmons."Seattle City Light Shares Outage Data Initiative: Collaboration, standards and APIs will improve restoration and drive the next generation of utilities." Transmission & Distribution World: The Information Leader Serving the Worldwide Power-Delivery Industry 68.2(2016).