Towards Intelligent IoT Networks: Reinforcement Learning for Reliable Backscatter Communications

Backscatter communication is becoming the focal point of research for low-powered Internet of things (loT). However, the intelligence aspect of the backscattering devices is not well-defined. Since future loT networks are going to be a formidable platform of intelligent sensing devices operating in a self-organizing manner, it is necessary to incorporate learning capabilities in backscatter devices. Motivated by this objective, this paper aims to employ reinforcement learning for improving the performance of backscatter networks. In particular, a multi-cluster backscatter communication model is developed for short-range information sharing. This is followed by a power allocation algorithm using Q-learning technique for minimizing the interference in the network. The results of the algorithm are compared with the conventional equal power allocation technique. It is shown that while the equal power allocation approaches capacity ceiling, the proposed algorithm continues to perform better as the number of backscatter devices increase.