A COMPARATIVE STUDY ON MULTI-SWARM OPTIMISATION AND BAT ALGORITHM FOR UNCONSTRAINED NON LINEAR OPTIMISATION PROBLEMS

Print

ABSTRACT

A study branch that mocks-up a population of network of swarms or agents with the ability to self-organise is Swarm intelligence. In spite of the huge amount of work that has been done in this area in both theoretically and empirically and the greater success that has been attained in several aspects, it is still ongoing and at its infant stage. An immune system, a cloud of bats, or a flock of birds are distinctive examples of a swarm system. . In this study, two types of meta-heuristics algorithms based on population and swarm intelligence - Multi Swarm Optimization (MSO) and Bat algorithms (BA) - are set up to find optimal solutions of continuous non-linear optimisation models. In order to analyze and compare perfect solutions at the expense of performance of both algorithms, a chain of computational experiments on six generally used test functions for assessing the accuracy and the performance of algorithms, in swarm intelligence fields are used. Computational experiments show that MSO algorithm seems much superior to BA.

FULL TEXT

HOW TO CITE THIS PAPER

Baidoo, E., & Opoku Oppong, S. (2016). A comparative study on Multi-Swarm Optimisation and Bat algorithm for unconstrained non linear optimisation problems. Applied Computer Science, 12(4), 59-77.
Baidoo, Evans, and Stephen Opoku Oppong. "A Comparative Study on Multi-Swarm Optimisation and Bat Algorithm for Unconstrained Non Linear Optimisation Problems." Applied Computer Science 12, no. 4 (2016): 59-77.
E. Baidoo and S. Opoku Oppong, "A comparative study on Multi-Swarm Optimisation and Bat algorithm for unconstrained non linear optimisation problems," Applied Computer Science, vol. 12, no. 4, pp. 59-77, 2016.
Baidoo E, Opoku Oppong S. A comparative study on Multi-Swarm Optimisation and Bat algorithm for unconstrained non linear optimisation problems. Applied Computer Science. 2016;12(4):59-77.
​​​​