Energy-Aware Routing and Sleep Scheduling Using Reinforcement Learning in WSNs

Improving the energy efficiency and extending the network lifetime of wireless sensor networks (WSNs) remain significant challenges due to the limited battery capacity of sensor nodes. This paper presents an energy-efficient control and routing protocol for wireless sensor networks. This algorithm uses reinforcement learning (RL) to manage the network energy. The proposed method combines three key strategies: (1) energyaware routing using RL to reduce the transmission distance, (2) dynamic sleep scheduling to minimize idle power consumption, and (3) data variability-based transmission control to avoid communication redundancy. Simulation results show that the proposed method significantly outperforms previous methods reported in the literature in terms of network lifetime.