Header menu link for other important links
Real time scenario based support vector regression for monitoring voltage stability through error minimization using particle swarm intelligence
A. Nageswara Rao,
Published in Institute of Advanced Scientific Research, Inc.
Volume: 11
Issue: 7
Pages: 858 - 871
Continuous assessment of voltage stability is a lively aspect to safeguard the electrical power system (EPS) operation. The conservative methods for online assessment in terms of stability check for voltage are extremely time engrossing and also absurd for supervising any application in online mode.In line to this a model which is an amalgamation of Particle Swarm Optimization Algorithm (PSOA) and support vector Machine (SVM) is aimed atsupervisingthe voltage stability (VS) in the manuscript. SVM is asignificant and promising tool in estimating the parameters.SVM is an algorithm based on supervised machine learning (ML) used for classification or regression problems. SVM uses a kernel trick method to transform the available data and find an optimumlimitamong the conceivable outputs. To advance the efficacy besidesprecision and minimize the SVM time for trainingselection of the optimum hyper parameters is a prime criterion.Pertaining to this, theattainment of optimum values regarding SVM has obtainedby using PSOA.The method anticipated for the aforesaid problem utilises the magnitude of voltage and its corresponding phase angle which are attained from the PMU as the inputs to the ML model and the respective output is considered to be voltage stability margin index (VSMI).The proficiency of anticipated model (PSOA - SVM) is verifiedby means of various test cases and compared with the same data set to attestitspre-eminence. © 2019, Institute of Advanced Scientific Research, Inc. All rights reserved.
About the journal
JournalJournal of Advanced Research in Dynamical and Control Systems
PublisherInstitute of Advanced Scientific Research, Inc.