Parameter Optimization for Elite Opposition Bacterial Foraging Optimization Algorithm.

Abstract

The investigation and analysis of algorithm parameters is an important task in most of the global optimization techniques. However, finding the best set of parameter value for the optimum performance of an algorithm still remain a challenging task in a modified Bacteria Foraging Optimization Algorithm (BFOA) since most of the existing research focuses on the application of the algorithm and likewise it benchmarking with the global test function. The Elite Opposition Bacterial Foraging Optimization Algorithm (EOBFOA) is a modified nature inspired optimization algorithm from BFOA which focuses on the generation of an elite solution from the opposition solution for an optimization process. This research is focused on the investigation of such parameters population size, probability of elimination dispersal, step size and number of chemotaxis so as to determine the extent to which they affect the optimal solution from the EOBFOA with respect to global minimum or least minimum standard deviation. From the results obtained, it was observed that the global minimum in EOBFOA depend on the exploitation ability of the bacteria in the search space.