A bird's eye view on reinforcement learning approaches for power management in WSNs

Abstract

This paper presents a survey on the adoption of Reinforcement Learning (RL) approaches for power management in Wireless Sensor Networks (WSNs). The survey has been carried out after a review expressly focused on the most relevant and the most recent contributions for the topic. Moreover, the analysis encompassed proposals at every methodological level, from dynamic power management to adaptive autonomous middleware, from self learning scheduling to energy efficient routing protocols.