Title: Charge scheduling for wireless rechargeable sensor networks with multiple mobile charges that uses hybrid reinforcement learning is energy-efficient and lifespan-aware

Authors: B.C. Vengamuni; V. Rajendran

Addresses: Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Science, Technology and Advanced Studies (VISTAS), Chennai, Tamil Nadu, India ' Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Science, Technology and Advanced Studies (VISTAS), Chennai, Tamil Nadu, India

Abstract: To ensure continuous sensor coverage, Wireless Rechargeable Sensor Networks (WRSNs) utilise Mobile Chargers (MCs) and wireless drones for energy transfer. However, drones alone are unsuitable for large WRSNs due to limited battery capacity. Existing charge scheduling methods face latency, efficiency, and scalability issues. We propose the Energy Efficient Network Lifespan aware Charge Scheduler (EENL-CS), which uses an Improved Grasshopper Optimisation (IGO) for clustering and an Improved Butterfly Optimisation (IBO) to select Cluster Heads. A Self-Healing Deep Reinforcement Learning (SHDRL) model schedules charging. Simulations show EENL-CS improves charging timeliness, efficiency, cost, and overall network lifetime.

Keywords: charge scheduling model; mobile chargers; wireless rechargeable sensor networks; clustering; CH selection; reinforcement learning.

DOI: 10.1504/IJWMC.2025.148115

International Journal of Wireless and Mobile Computing, 2025 Vol.29 No.2, pp.116 - 130

Accepted: 20 Nov 2024
Published online: 25 Aug 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article