AbstractsBiology & Animal Science

Investigation of efficient Bio inspired intelligent paradigms for Solving unique constraint Based optimization problems;

by Surekha P




Institution: Anna University
Department: Investigation of efficient Bio inspired intelligent paradigms for Solving unique constraint Based optimization problems
Year: 2015
Keywords: Enhanced Particle Swarm Optimization; Fuzzy based Radial Basis Function Network; Job Shop Scheduling Problem
Record ID: 1185456
Full text PDF: http://shodhganga.inflibnet.ac.in/handle/10603/38951


Abstract

Optimization is an interdisciplinary area providing solutions to newlineNonlinear stochastic combinatorial and multi objective problems With the newlineincreasing challenges of satisfying optimization goals of current applications newlinethere is a strong drive to improve the development of efficient optimizers Thus it newlineis important to identify suitable computationally intelligent algorithms for newlinesolving the challenges posed by optimization problems In this research four newlineunique optimization problems namely the Unit Commitment and Economic newlineLoad Dispatch UC ELD Job Shop Scheduling Problem JSSP Multi Depot newlineVehicle Routing Problem MDVRP and Digital Image Watermarking DIWM newlineare chosen to test and validate the performance of bio inspired intelligent newlinealgorithms The primary aim is to apply bio inspired heuristics to the problems newlineunder consideration and identify the most suitable algorithm in terms of optimal newlinesolution robustness and computational time newlineThe non convex and combinatorial nature of the UC ELD problems newlinerequires the application of heuristic algorithms to generate optimal schedules In newlinestudies reported so far the Unit Commitment and the Economic Load Dispatch newlineproblems are solved as separate problems In the addressed work the newlinecommitment and de commitment of generating units is obtained using a Genetic newlineAlgorithm GA and the optimal load distribution of the scheduled units is newlineobtained using a Fuzzy based Radial Basis Function Network FRBFN Surekha newlineand Sumathi July 2011 Enhanced Particle Swarm Optimization EPSO newlineDifferential Evolution with Opposition Based Learning newline%%%appendix p345-368, reference p369-390.