CoMARS: Coordinated Multi-Agent Rollout Strategy for Distributed Channel Access in Clustered IoT Networks

The proliferation of Machine-to-Machine (M2M) communications in Internet of Things (IoT) networks intensifies interference management and resource allocation challenges for clustered devices. Existing solutions face limitations in scalability and fairness, particularly under dynamic conditions. We propose CoMARS, a bio-inspired framework integrating artificial immune systems with multi-agent reinforcement learning, designed to address these challenges through coordinated two-tier optimization. The architecture employs immune-inspired mechanisms at the device layer for autonomous cluster maintenance and interference-aware power control. At the network layer, a predictive rollout algorithm enables cluster heads to develop coordinated transmission strategies through model-based reinforcement learning. OMNeT++ simulations demonstrate CoMARS’s superior performance, achieving 5.71 Mbps/J energy efficiency with significantly improved throughput and lower latency compared to benchmark protocols. The framework maintains stable performance during topology changes and exhibits accelerated convergence under saturated traffic, proving effective for dynamic IoT environments.