Collaborative Charging Optimization for Wireless Rechargeable Sensor Networks via Heterogeneous Mobile Chargers

TL;DR

The paper tackles energy sustainability in wireless rechargeable sensor networks by introducing a heterogeneous air-ground charging framework that leverages AAVs and SVs. It formulates a multi-objective optimization to maximize charging efficacy while minimizing charger travel and sensor mortality, solved via IHATRPO, which combines self-attention for environment-aware coordination and Beta sampling to respect bounded action spaces. Empirical results show IHATRPO outperforms baselines (including HATRPO) and reduces sensor mortality from >90% to <10%, with a 39% performance gain over the original HATRPO. The findings demonstrate adaptive, territorial coordination between aerial and ground chargers, suggesting scalable, energy-efficient provisioning for dynamic WRSN deployments.

Abstract

Despite the rapid proliferation of Internet of Things applications driving widespread wireless sensor network (WSN) deployment, traditional WSNs remain fundamentally constrained by persistent energy limitations that severely restrict network lifetime and operational sustainability. Wireless rechargeable sensor networks (WRSNs) integrated with wireless power transfer (WPT) technology emerge as a transformative paradigm, theoretically enabling unlimited operational lifetime. In this paper, we investigate a heterogeneous mobile charging architecture that strategically combines automated aerial vehicles (AAVs) and ground smart vehicles (SVs) in complex terrain scenarios to collaboratively exploit the superior mobility of AAVs and extended endurance of SVs for optimal energy distribution. We formulate a multi-objective optimization problem that simultaneously addresses the dynamic balance of heterogeneous charger advantages, charging efficiency versus mobility energy consumption trade-offs, and real-time adaptive coordination under time-varying network conditions. This problem presents significant computational challenges due to its high-dimensional continuous action space, non-convex optimization landscape, and dynamic environmental constraints. To address these challenges, we propose the improved heterogeneous agent trust region policy optimization (IHATRPO) algorithm that integrates a self-attention mechanism for enhanced complex environmental state processing and employs a Beta sampling strategy to achieve unbiased gradient computation in continuous action spaces. Comprehensive simulation results demonstrate that IHATRPO achieves a 39% performance improvement over the original HATRPO, significantly outperforming state-of-the-art baseline algorithms while substantially increasing sensor node survival rate and charging system efficiency.

Figures (8)

• Figure 1: Architecture diagram of the HAGCCS for the WRSN. The AAV and SV travel within the WRSN to collaboratively provide energy for sensors through WPT waves.
• Figure 2: The time slot division model in HAGCCS.
• Figure 3: Boundary effects on Gaussian distribution bias. The shaded areas represent probability mass falling outside the valid action range, which must be truncated during sampling.
• Figure 4: Framework of IHATRPO for heterogeneous air-ground collaborative charging in the WRSN. The algorithm integrates Beta distribution-based action sampling, self-attention mechanism enhanced state processing, and heterogeneous actor-critic structures for the AAV and SV to optimize multi-objective charging strategies.
• Figure 5: Visualization results obtained by IHATRPO. (a) The total reward of the AAV and SV. (b) The charging efficiency of the AAV and SV. (c) The travel distance of the AAV and SV. (d) The mortality of sensor nodes.