Feature reduction techiniques in dynamic stability prediction power system using feedforward neural networks and radial basis function neural networks
Corressponding author's email:
aunn@hcmute.edu.vnKeywords:
Dynamic stability assessment, neural networks, feature/variable selectionAbstract
This paper presents an application of Multilayer Feedforward Neural Networks (MLFN) and Radial Bais Function Neural Network (RBFN) for Power System Dynamic Stability Assess- ment (DSA) with feature reduction techniques. Dyamic stability of the power system is first de- termined based on the generator relative rotor angles obtained from time domain simulations. Simulations were carried out on the GSO 37-bus test system considering three phase faults on at rated power. The data collected from the time domain simulations are then used as inputs to the MLFN and RBFN. Reduced feature inputs based on Fisher Discrimination and Divergence. MLFN and RBFN results show that the stability condition of the power system can be predicted with high accuracy. In addition, the performance of the variable selection methods as well as the performance of the MLFN and RBFN was compared
Downloads: 0
References
Prabha Kundur, ‘Power System Stability And Control’, 1994.
Rui Zhang, Yan Xu, Zhao Yang Dong, ‘Feature Selection For Intelligent Stability As- sessment of Power Systems’, IEEE 2012.
Kwang Y. Lee, Mohamed A. El-Sharkawi, ‘Modern Heuristic Optimization Tech- niques Theory And Applications To Power Systems’, Published by John Wiley & Sons, Inc., Hoboken, New Jersey, 2008.
M. R. Aghamohammadi, F.Mahdavizadeh ,R.Bagheri, ‘Power System Dynamic Secu- rity Classification Using Kohenen Neural Networks’, IEEE 2009.
Nima Amjady and Seyed Farough Majedi, ‘Transient Stability Prediction by a Hybrid Intelligent System’, IEEE Transactions On Power Systems, Vol. 22, No. 3, August 2007.
Mark Hudson Beale, Martin T. Hagan, Howard B. Demuth,’ Neural Network Toolbox User’s Guide’, R2014a.
Yan Xu, Zhao Yang Dong, JunHua Zhao, Pei Zhang, Kit Po Wong,’A Reliable Intel- ligent System for Real-Time Dynamic Security Assessment of Power Systems’, IEEE TRANSACTIONS ON POWER SYSTEMS, VOL. 27, NO. 3, AUGUST 2012.
K. Shanti Swarup, ‘Artificial neural network using pattern recognition for security as- sessment and analysis’, Neurocomputing 71 (2008) 983–998, Elsevier.
Quyen Huy Anh, ‘The applycation of pattern recognition for fast analysis of the dy- namic stability of electrical power system’, Electrical technology, No.2 pp 1-13, 1994, Perganon.
Downloads
Published
How to Cite
Issue
Section
Categories
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
