Use of artifcial intelligence (AI) methods for improving visible light communications in modern wireless networks

Abstract

Visible Light Communication (VLC) has emerged as a promising wireless technology that utilizes Light Emitting Diodes (LEDs) for simultaneous illumination and high-speed data transmission. Compared to traditional Radio Frequency (RF) systems, VLC o?ers advantages such as higher data rates, enhanced security, and reduced electromagnetic interference. However, optimal LED placement remains a signi?cant challenge, as it directly impacts coverage, data throughput, and energy e?ciency. Given the NP-hard nature of this problem, conventional optimization methods are computationally infeasible for large-scale deployments. This research focuses on developing and enhancing meta-heuristic optimization algorithms to e?ciently address the LED placement challenge in VLC networks. We propose and evaluate three advanced techniques: Enhanced Whale Optimization Algorithm (EWOA), Hybrid Coronavirus Herd Immunity Optimize with Fire?y Algorithm (ICHIOFA), and a Multi-Objective Puma Optimizer (MOPO). These approaches integrate chaotic maps, Opposition-Based Learning (OBL), non-dominated sorting, and crowding distance mechanisms to improve search e?ciency, convergence speed, and solution quality. Extensive benchmarking against state-of-the-art meta-heuristics demonstrates that our proposed methods signi?cantly outperform existing algorithms in solution quality, robustness, and computational e?ciency. The ?ndings of this research contribute to advancing optimization techniques in VLC systems, providing scalable and e?cient solutions, to deployment in next-generation communication networks