Work-in-Progress: Cooperative Communication Between Two Transiently Powered Sensors by Reinforcement Learning

The transmission between two energy harvesting (EH) powered sensors is successful only when both sensors have enough energy at the same time. Given the scarce, unpredictable, and unevenly distributed energy between two sensors, it is challenging to ensure efficient data transmission. We propose a sensor node architecture with multiple wake-up radios, each with a different ratio of energy consumption on the transmitter and receiver. Two sensors cooperatively select wake-up radios to maximize data throughput. The communication procedure is modeled as a cooperative Markov game with partial observability and multi-agent reinforcement learning (MARL) is employed to maximize the throughput. The proposed methods achieve near-optimal data throughput.