Reinforcement learning based reliability-aware routing in IoT networks

The unprecedented scale and ubiquity of the Internet Things (IoT) introduce a maintainability challenge. IoT networks operate in diverse harsh environments that impose thermal stress on devices. lifetime these can be limited by hardware failures resulting from exacerbated reliability degradation mechanisms at high temperatures. In this paper, we propose novel adaptive distributed reliability-aware routing protocol based reinforcement learning to mitigate devices improve network Mean Time Failure (MTTF). Through routing, curb utilization quickly degrading devices, which helps lower device power dissipation temperature, thus reducing effect temperature-driven failure mechanisms. To quantify optimize networking performance besides reliability, incorporate Expected Transmission Count (ETX) our formulations as measure communication link quality. Our proposed algorithm adapts decisions current status amount they are likely experience due activity, goals. We extend ns-3 simulator support models evaluate comparing with state-of-the-art approaches. results show up 73.2% improvement for various data rates number nodes while delivering comparable performance.