An Adaptive Mutation Strategy for Real Coded Genetic Algorithm

I. A. KOREJO, K. BROHI, A. A. CHANDIO, F. A. MEMON, A. R. NANGRAJ

Abstract


Generally, single mutation operator is used by the conventional genetic algorithms (GAs), so it determine that all individuals in the population apply the same mechanism. Due to this mechanism, simple gas suffer from the premature convergence problem, it is easy to be trapped in to local optima.This paper proposes adaptive mutation (AMGAs) scheme for GAs to automatically select the most suitable operator while solving the problem.It also proposes different mutation strategies to deal with different situations in the search space by using amgas. To analysis the performance of propose approach, twnenty well known and applied benchmark problems are used. The experimental results show that amgas greatly balance the performance of GAs on different set problems.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Copyright (c) 2017 Sindh University Research Journal - SURJ (Science Series)

 Copyright © University of Sindh, Jamshoro. 2017 All Rights Reserved.
Printing and Publication by: Sindh University Press.