A novel variant of self-organizing migrating algorithm for global optimization

Abstract

This paper presents a novel variant SOMAQI of population based optimization technique self organizing migrating algorithm (SOMA). This variant uses the quadratic approximation or interpolation for creating a new solution vector in search space. To validate the efficiency of this algorithm it is tested on 10 benchmark test problems and the obtained results are compared with already published results using the same quadratic approximation. On the basis of comparison it is concluded that the presented algorithm shows better performance in terms of number of population size and function mean best.