Impact of Metaheuristic Optimization Algorithms on Wireless Network Coverage Enhancement With Reconfigurable Intelligent Surfaces

Abstract

Reconfigurable intelligent surfaces are a transformative technological advancement in wireless networks toward enhancing coverage and signal strength by exploiting intelligent, programmable surfaces. This paper discusses the application of metaheuristic optimization to configure reconfigurable intelligent surfaces for performance enhancement in wireless communications. Reconfigurable intelligent surface (RIS) technology based on programmable surfaces dynamically adjusts a radio environment, thereby having an impact on signal quality enhancement and coverage. We test several optimization algorithms, including genetic algorithm (GA), cuckoo search (CS), harmony search (HS), ant colony optimization (ACO), differential evolution (DE), dual annealing, gradient descent, tabu search, and the bee algorithm. The results show that GA explores the solution space. CS and HS balance well between exploration and exploitation. ACO and DE find paths and parameters efficiently, and dual annealing excels in escaping local optima. Tabu search and the bee algorithm also provide strong performance in the avoidance of local minima. RIS elements can integrate highly into the network to enhance its performance, leading to better-received signal strength and improved coverage. The results have the potential to optimize wireless networks by combining the use of RIS technology with advanced algorithms such as those described here and call for further research in hybrid optimization approaches and complex network scenarios.