Fault diagnosis for smart grid with uncertainty information based on data

  • Authors:

  • Qiuye Sun;Zhongxu Li;Jianguo Zhou;Xue Liang

  • Affiliations:

  • School of Information Science and Engineering, Northeastern University, Shenyang, P.R. China and Rongxin Power Electronic Co., Ltd, Anshan, P.R. China;School of Information Science and Engineering, Northeastern University, Shenyang, P.R. China;School of Information Science and Engineering, Northeastern University, Shenyang, P.R. China;School of Information Science and Engineering, Northeastern University, Shenyang, P.R. China

  • Venue:
  • ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The concept of Smart Grid has gained significant acceptance during the last several years due to the high cost of energy, environment concerns, and major advances in distributed generation (DG) technologies. Distribution systems have traditionally been designed as radial systems, and time coordination of protection devices at the distribution level, the main characteristic for fault diagnosis, is a standard practice used by the utilities. However, when Smart Grid occurs fault, the certainty and integrity of information will be damaged by many causations. In order to improve the accuracy and rapidity of fault diagnosis, it is necessary to discover a new method that has high fault tolerant and can compress data space and filtrate error data. To deal with the uncertainty and deferent structures of the causation, rough sets and intuitionistic fuzzy sets are introduced. Based on them, intuitionistic uncertainty-rough sets are proposed and the reduction algorithm is improved. The rule reliability is deduced using intuitionistic fuzzy sets and probability. The worked example for Xigaze power system in China's Tibet shows the effectiveness and usefulness of the approach.