Deep Reinforcement Learning Resource Allocation in Wireless Sensor Networks With Energy Harvesting and Relay

Green wireless communications have been extensively studied in wireless sensor networks (WSNs), including the use of new energy, renewable energy, and low-power consumption and energy-saving technologies for years. In these networks, due to channel fading, insufficient and random energy arrival, some possible bad deployment of sensors, etc., the communication among sensor nodes in a WSNs will inevitably be affected or even interrupted sometimes, which may result in unacceptable performance in the entire network. In order to solve this problem, we propose a WSN composing of several local subnetworks with amplified forwarding relay and specially designed working time cycle. In this network, we study our resource allocation policies to manage both power and time for throughput maximization. We use deep reinforcement learning (DRL) to develop our resource allocation policies under the model constructed as a Markov decision process for this optimization problem in the subnetwork. We apply an actor–critic strategy to find our optimal solution in continuous state and action space and adaptively achieve maximum throughput of this network based on energy harvesting, causal information of battery state and channel gains. The simulation results demonstrate that the proposed transmission policies can produce higher throughput in the local network and finally improve overall system performance in comparison with greedy policy, random policy, and conservative policy.