A Deep Reinforcement Learning-Based Context-Aware Wireless Mobile Charging Scheme for the Internet of Things

Abstract

The Internet of Things (IoT) has gained in popularity over the years and is used in numerous applications. IoT networks employ many constrained devices, thus, finding energy is mandatory to maximize device and network lifetime. In this paper, we investigate a scheme based on wireless Mobile Chargers (MCs) to maximize device lifetime. Instead of transmitting energy to devices to only charge them back, we design a charging scheme considering the near future needs of the devices. We provide our ongoing research on a context-aware wireless energy transfer scheme to charge the devices according to the current and probable upcoming events. Our scheme is based on two modules: a context reasoning module predicting the possible future events in the IoT network and an intelligent Wireless Mobile Charger using Deep Reinforcement Learning (DRL). Our solution aims to establish a preventive charging scheme, considering the energy status and probable future events.