PARAMETERS TUNING OF THE FIREWORKS INTELLIGENCE ALGORITHM FOR THE GLOBAL OPTIMIZATION

Abstract

The swarm intelligence algorithm, namely Fireworks, plays an imperative role in the solution of optimization problems in the field of engineering and sciences. The Fireworks Intelligence Algorithm (FWA) is a prominent swarm intelligence (SI) algorithm used for global optimization; however, its traditional form suffers from premature convergence and inefficient information sharing among individuals, limiting its performance on complex problems.

This research addresses the key limitations of conventional FWA, specifically its lack of population diversity, propensity to get trapped in local optima, and the absence of a dynamic mechanism to adapt to different problem landscapes.

In this paper, we highlighted the issues in its different versions that severely affect the efficiency of FWA, and we suggested different parameter modifications to enhance its efficiency by maintaining a proper balance between exploration and exploitation searches, and also keeping the diversity of the swarm of FWA for global optimization problems