Title :
On-Line Voltage Security Assessment Using Modified Neo Fuzzy Neuron Based Classifier
Author :
Pandit, Manjaree ; Srivastava, Laxmi ; Singh, Vijay
Author_Institution :
Madhav Inst. of Technol. & Sci., Gwalior
Abstract :
Neural networks and fuzzy systems can be trained to generate accurate relations among variables in complex nonlinear dynamical environment, as both are model free estimators. The existing synergy between these two fields has been exploited in this paper to obtain a classifier for the on-line management of power systems. A system state classifier based on neo-fuzzy neuron (NFN), modified by Kohonen network, capable of real time training is proposed for the classification and ranking of critical voltage contingencies. The proposed method has been tested on IEEE 30-bus test system and is found to classify selected contingencies accurately even for previously unseen operating conditions, instantaneously.
Keywords :
fuzzy neural nets; fuzzy systems; pattern classification; power system analysis computing; self-organising feature maps; Kohonen network; complementary membership functions; contingency ranking; fuzzy systems; neo fuzzy neuron classifier; neural networks; on-line voltage security assessment; Energy management; Fuzzy systems; Neural networks; Neurons; Power system dynamics; Power system management; Power system modeling; Security; System testing; Voltage; Complementary membership functions; Contingency ranking; Kohonen network; Neo-fuzzy classifier; On-line security assessment;
Conference_Titel :
Industrial Technology, 2006. ICIT 2006. IEEE International Conference on
Conference_Location :
Mumbai
Print_ISBN :
1-4244-0726-5
Electronic_ISBN :
1-4244-0726-5
DOI :
10.1109/ICIT.2006.372261