Hiercharge: Low-Complexity Hierarchical Optimization for Scalable IoT Energy Solution

This paper proposes HierCharge, a hierarchical optimization system for scalable Internet-of-Things(IoT) energy solutions using Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) equipped with wireless power transmitters. The system is designed to schedule, assign, and execute charging tasks for IoT devices with low computational complexity while minimizing failures and optimizing energy efficiency. Numerical results demonstrate that HierCharge outperforms state-of-the-art AI-based approaches, including Deep Deterministic Policy Gradient (DDPG) and Q-learning, which struggle to converge due to the large system state and complex action space. The proposed method minimizes failures with low computational cost, which makes it a practical and scalable solution for realtime IoT energy optimization.