ARTIFICIAL INTELLIGENCE-DRIVEN CONGESTION MITIGATION AND PERFORMANCE OPTIMIZATION FOR IEEE 802.11 WIRELESS COMMUNICATION SYSTEMS

Abstract

The exponential growth of wireless devices and bandwidth-intensive applications has led to significant congestion and performance degradation in IEEE 802.11 wireless networks. Traditional congestion control mechanisms often fail to adapt dynamically to highly variable network conditions, resulting in packet loss, increased latency, and reduced throughput. This study presents an Artificial Intelligence (AI)-driven framework for congestion mitigation and performance optimization in IEEE 802.11 wireless communication systems. Leveraging reinforcement learning (RL) and deep learning (DL) algorithms, the proposed system dynamically predicts network congestion, allocates resources efficiently, and optimizes channel access to maximize throughput while minimizing latency and packet collisions. Extensive simulations demonstrate that the AI-based approach outperforms conventional methods by providing adaptive, real-time decision-making that enhances network reliability and Quality of Service (QoS). The results highlight the potential of integrating AI techniques into wireless communication protocols to address contemporary challenges in high-density and heterogeneous network environments.