ADAPTIVE ROUTING IN WIRELESS LOCAL AREA NETWORK MESSAGING SYSTEM USING PARTICLE SWARM OPTIMIZATION

Abstract

This study explores optimizing Wireless Local Area Network (WLAN) messaging systems using swarm intelligence techniques to enhance communication efficiency and reliability in congested wireless environments. Increasing device connectivity has led to challenges such as high latency, reduced throughput, message collisions, and inefficient routing, negatively impacting network performance and user experience. To address these issues, the study applies Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) as adaptive, decentralized methods. WLAN systems are modeled mathematically, incorporating particle position, velocity, fitness evaluation, throughput, and delay metrics. Swarm intelligence algorithms dynamically optimize routing, minimize transmission delay, and improve throughput. Simulation results indicate that PSO achieves stable convergence, with particle positions stabilizing around optimal values and fitness functions confirming global optimum targeting. ACO demonstrates progressive pheromone reinforcement, enhancing routing probabilities along shorter paths. Quantitative outcomes show throughput around 0.03 under moderate dispersion and total routing delay approximately 122.45 seconds across multiple paths, reflecting improved throughput-delay balance compared to conventional methods. The results highlight that swarm intelligence reduces latency, improves data routing, and increases adaptability in dynamic network conditions. From a policy perspective, the study advocates adopting intelligent, self-organizing optimization frameworks in WLANs to support scalable infrastructures, improve quality of service, and meet the growing demands of modern digital communication.