Novel wireless charging algorithms to charge mobile wireless sensor network by using reinforcement learning

Abstract

Generally, mobile wireless sensor network (MWSN) senses the sensitive and typical kind of events in various application areas along with the frequent mobility of sensor nodes as compared to traditional wireless sensor network. Due to mobility feature, MWSN extended the working of WSN. To design MWSN, certain key factors like energy efficiency, mobility, data routing, localization and charging strategy are involved. Mobile sensor nodes consume extra amount of energy due to mobility along with sensing and data routing task which exhaust network lifetime rapidly. In this research study, authors have proposed two wireless chargers (fixed and mobile) for sensor nodes. The main difference between fixed and mobile wireless charger is: fixed wireless charger invites mobile sensor nodes for wireless charging at base station whereas mobile wireless charger travels to the position of mobile sensor nodes for wireless charging. Both chargers fulfilled the charging request of sensor nodes efficiently. This is the first research study to propose such type of charging strategy for mobile wireless sensor network (MWSN) as per the available literature. The RL (reinforcement learning) technique is used here for optimization purpose of charging cost. These wireless chargers simulated in MATLAB enviorment and results showed that there is a significant improvement in network lifetime due to these charging strategies when compared to the existing algorithms.

Collaborative Wireless Power Transfer in Wireless Rechargeable Sensor Networks

“…The authors in [29] have proposed a reinforcement learning-based recharging algorithm. The proposed algorithm recharges sensor nodes by using a fixed charger for less critical regions; however, critical sensor nodes are recharged through a mobile charger.…”

Attention-Shared Multi-Agent Actor–Critic-Based Deep Reinforcement Learning Approach for Mobile Charging Dynamic Scheduling in Wireless Rechargeable Sensor Networks

“…There are several works that have tried to solve the charging scheduling problem with RL algorithms. For example, Wei et al [ 29 ] and Soni and Shrivastava [ 30 ] proposed a charging path planning algorithm (CSRL), combining RL and MC to extend the network lifetime and improve the autonomy of MC. However, the proposed CSRL method only suits offline mode, where the energy consumption of sensor nodes is time-invariant.…”