Design of a hybrid fuzzy classifier system for power system sensor status evaluation

Correct estimation of the system operating states in the presence of uncertain measurement data is a crucial challenge for real-time power system monitoring. Proposed in this paper is a strategy that augments state estimation methods using an approach that can incorporate additional information that is not traditionally included as a part of the state variables. Specifically, fuzzy logic is utilized to create a hybrid fuzzy classifier system (HFCS). The HFCS aims to combine information from multiple domains in order to detect, isolate, identify, and mitigate threats to the power networks. Results from applying this HFCS to the IEEE 14-bus test system are presented.

[1]  Daniel Y. Abramovitch,et al.  Some crisp thoughts on fuzzy logic , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[2]  Hugo Trienko Grimmelius,et al.  Three state-of-the-art methods for condition monitoring , 1999, IEEE Trans. Ind. Electron..

[3]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[4]  Keith E. Holbert,et al.  Fuzzy associative memories for instrument fault detection , 1996 .

[5]  Philip G. Hill,et al.  Power generation , 1927, Journal of the A.I.E.E..

[6]  E. Cox,et al.  Fuzzy fundamentals , 1992, IEEE Spectrum.

[7]  K.E. Holbert,et al.  Reducing state estimation uncertainty through fuzzy logic evaluation of power system measurements , 2004, 2004 International Conference on Probabilistic Methods Applied to Power Systems.

[8]  A. Monticelli,et al.  Electric power system state estimation , 2000, Proceedings of the IEEE.

[9]  Wu Chou,et al.  Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition , 2000, Proceedings of the IEEE.