🤖 AI Summary
In dense Wi-Fi scenarios, the conventional CSMA/CA mechanism suffers from high packet collision rates and excessive MAC-layer latency. To address these challenges, this paper proposes an intelligent channel access method jointly driven by Federated Learning (FL) and Deep Deterministic Policy Gradient (DDPG). We introduce a novel FL-DDPG co-design architecture, incorporating a lightweight training pruning strategy and an adaptive weighted aggregation algorithm to preserve user privacy and reduce communication overhead while enhancing adaptability to dynamic channel conditions. Extensive NS-3-AI simulations demonstrate that, under static conditions, the proposed method reduces average MAC latency by 25.24%; under dynamic conditions, it achieves 25.72% and 45.9% improvements over A-FRL and DRL baselines, respectively. These results substantiate significant gains in multi-AP concurrent access efficiency and system robustness.
📝 Abstract
The IEEE 802.11 MAC layer utilizes the Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) mechanism for channel contention, but dense Wi-Fi deployments often cause high collision rates. To address this, this paper proposes an intelligent channel contention access mechanism that combines Federated Learning (FL) and Deep Deterministic Policy Gradient (DDPG) algorithms. We introduce a training pruning strategy and a weight aggregation algorithm to enhance model efficiency and reduce MAC delay. Using the NS3-AI framework, simulations show our method reduces average MAC delay by 25.24% in static scenarios and outperforms A-FRL and DRL by 25.72% and 45.9% in dynamic environments, respectively.