Comparative Analysis of Particle Swarm Optimization and Harmony Search Algorithm Techniques

Abstract

Particle Swarm Optimization (PSO), is one of the most commonly used heuristic algorithms.
Simplicity and low computational cost make this algorithm is very influential and efficient to resolve a
varied range of problems. Growing particle's PSO algorithm improves its velocity and position based
on best practice and experience in the population through the learning process.The Harmony Search
Algorithm (HSA) approach remains a popular metaheuristic optimization algorithm that has been
used for several challenging tasks over the last decade. This paper presents the basic theory and
comparison between the PSO and the HS algorithm. Some common PSO and HSA versions, such as
Binary PSO and Binary HSA, Discrete Binary PSO and Discrete Binary HSA, are briefly explained
below. PSO and HSA were displayed to be a simple, well-organized and powerful optimization
algorithm. One of the key points is the exploitation capability of the PSO algorithm as well as the
exploration capability of the HSA.A new approach is projected in this paper to calculate the PSO's
exploitation capability and the HSA's exploration capability.The empirical study of the proposed
method is evaluated in accordance through the explanation of theoretical observations and
experimental results such as optimum expectation optimum variance the Wilcoxon rank sum test and
the history of particles