Open AccessA novel approach for voltage secure operation using Probabilistic Neural Network in transmission network
Author(s) -
Santi Kumari Behera,
M. Tripathy,
J.K. Satapathy
Publication year - 2016
Publication title -
journal of electrical systems and information technology
Language(s) - English
Resource type - Journals
ISSN - 2314-7172
DOI - 10.1016/j.jesit.2015.03.016
Subject(s) - artificial neural network , probabilistic logic , probabilistic neural network , computer science , voltage , transmission line , control theory (sociology) , classifier (uml) , electric power system , artificial intelligence , engineering , time delay neural network , control (management) , telecommunications , electrical engineering , power (physics) , physics , quantum mechanics
This work proposes a unique approach for improving voltage stability limit using a Probabilistic Neural Network (PNN) classifier that gives corrective controls available in the system in the scenario of contingencies. The sensitivity of system is analyzed to identify weak buses with ENVCI evaluation approaching zero. The input to the classifier, termed as voltage stability enhancing neural network (VSENN) classifier, for training are line flows and bus voltages near the notch point of the P–V curve and the output of the VSENN is a control variable. For various contingencies the control action that improves the voltage profile as well as stability index is identified and trained accordingly. The trained VSENN is finally tested for its robustness to improve load margin and ENVCI as well, apart from trained set of operating condition of the system along with contingencies. The proposed approach is verified in IEEE 39-bus test system