Deep Neural Network-guided PSO for Tracking a Global Optimal Position in Complex Dynamic Environment

TL;DR

This paper introduces novel PSO variants guided by deep neural networks to efficiently track moving global optima in dynamic environments, outperforming recent algorithms with fewer particles.

Contribution

It presents two DNN-guided PSO variants that adapt to environmental changes, enabling effective tracking with smaller swarms, a novel approach in dynamic optimization.

Findings

Both variants outperform recent PSO algorithms in tracking accuracy.

The methods require fewer particles than the number of potential optima.

Experimental results demonstrate lower cumulative tracking error.

Abstract

We propose novel particle swarm optimization (PSO) variants incorporated with deep neural networks (DNNs) for particles to pursue globally optimal positions in dynamic environments. PSO is a heuristic approach for solving complex optimization problems. However, canonical PSO and its variants struggle to adapt efficiently to dynamic environments, in which the global optimum moves over time, and to track them accurately. Many PSO algorithms improve convergence by increasing the swarm size beyond potential optima, which are global/local optima but are not identified until they are discovered. Additionally, in dynamic environments, several methods use multiple sub-population and re-diversification mechanisms to address outdated memory and local optima entrapment. To track the global optimum in dynamic environments with smaller swarm sizes, the DNNs in our methods determine particle movement by learning environmental characteristics and adapting dynamics to pursue moving optimal positions. This enables particles to adapt to environmental changes and predict the moving optima. We propose two variants: a swarm with a centralized network and distributed networks for all particles. Our experimental results show that both variants can track moving potential optima with lower cumulative tracking error than those of several recent PSO-based algorithms, with fewer particles than potential optima.