Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks
For LEO satellite network operators, this method improves handover performance under dynamic conditions, though it is an incremental application of existing RL techniques.
The paper proposes a dueling DDQN-based adaptive multi-objective handover framework for LEO satellite networks, achieving up to 10.3% throughput improvement and near-zero blocking probability.
In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for LEO satellite networks. The proposed method enables dynamic trade-off learning among throughput, blocking probability, and switching cost under time-varying network conditions. Simulation results demonstrate that the proposed approach consistently outperforms conventional baselines, achieving up to 10.3% throughput improvement and near-zero blocking under typical operating conditions.