Detection of Power Quality Disturbances Based on Adaptive Neural Net and Shannon Entropy Method
Detection of power quality (PQ) events is a vital task for the power system monitoring and control. This paper presents a new scheme for the revealing of PQ disturbances using adaptive neural net (ANN) and information theory which employs neural net as a harmonics extracting unit and the difference entropy as a feature extracting unit. Simulations on six signals, such as ideal sine wave, interruption, voltage sag, voltage swell, impulse, and oscillation transient, are done with and without the presence of harmonics and the begin and end instants of disturbances are accurately tracked. The robust nature of the algorithm allows accurate estimation in the presence of noises about 10 db and the results of detection show that the proposed method has good compliance on determination of attributes of the signals.
KeywordsNeural network Difference entropy Power quality Detection Harmonics
- 1.Z. Jing, H. Zhengyou, Q. Qingquan, Detection of power quality disturbances based on generalized morphological filter and information theory. IEEE. (2009)Google Scholar
- 6.V. Suresh Kumar, D. Kavitha, K. Kalaiselvi, P.S. Kannan, Harmonic Mitigation and Power Factor Improvement using Fuzzy Logic and Neural Network Controlled Active Power Filter. Journal of Electrical Engineering & Technology. 3(3), 520–527 (2008)Google Scholar
- 7.D. Kavitha, A.F. Zobaa, P. Renuga, V. Suresh Kumar, NSGA-II optimized neural network controlled active power line conditioner under non-sinusoidal conditions. Int. Rev. Electr. Eng. (IREE). 6(2011)Google Scholar
- 8.V. Suresh Kumar, D. Kavitha, K. Kalaiselvi, P.S. Kannan, Optimal estimation of harmonics in power system using intelligent computing techniques. Proceedings of IEEE Neural Networks conference. (2007)Google Scholar