Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks

Po-Heng Chou; Chiapin Wang; Chung-Chi Huang; Kuan-Hao Chen

cs.ITMay 4, 2026

Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks

Authors: Po-Heng Chou, Chiapin Wang, Chung-Chi Huang, Kuan-Hao Chen

Organizations: Research Center for Information Technology Innovation (CITI), Academia Sinica (AS), Taipei 11529, Taiwan · Department of Electrical Engineering, National Taiwan Normal University (NTNU), Taipei 106308 Taiwan

Abstract

In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for low Earth orbit (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.

Explore similar work

Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
May 4, 2026Po-Heng Chou, Chiapin Wang, Shou-Yu Chen +1Low Earth Orbit Deep Q-Networks
xApp Empowered Resource Management for Non-Terrestrial Users in 5G O-RAN Networks
May 11, 2026Mohammed M. H. Qazzaz, Syed Ali Zaidi, Aubida A. Al-Hameed +2Multi-Drone Coordination Open Radio Access Networks
FedRings: A Scalable and Topology-Aware Federated Learning Framework for LEO Satellite Constellations
Aug 4, 2026Ziwu Liu, Inês Pinto Gouveia, Rehana Yasmin +2Low Earth Orbit Wireless Resource Allocation

May 4, 2026 · cs.NIJ/K move · Enter open · S save

Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks

Po-Heng Chou, Chiapin Wang, Shou-Yu Chen, Hsiang-Ming Wang

Research Center for Information Technology Innovation (CITI), Academia Sinica (AS), Taipei 11529, Taiwan · Department of Electrical Engineering, National Taiwan Normal University (NTNU), Taipei 106308 Taiwan

In this paper, we propose a spatial-temporal learning-based distributed routing framework for dynamic Low Earth Orbit (LEO) satellite networks, where graph attention networks (GAT) and long short-term memory (LSTM) are integrated within a deep Q-network (DQN)-based architecture to enable distributed and adaptive routing decisions based on local observations. The routing problem is formulated as a partially observable Markov decision process (POMDP) to address partial observability under dynamic topology and time-varying traffic. Simulation results show that the proposed method significantly outperforms conventional and learning-based routing schemes in terms of throughput, packet loss, queue length, and end-to-end delay, while achieving proactive congestion avoidance with up to 23.26% queue reduction. In addition, the proposed approach maintains low computational overhead with negligible carbon emissions, demonstrating its efficiency from a Green AI perspective.

Low Earth Orbit Deep Q-Networks Wireless Resource Allocation Low-Latency Systems Partial Observability

Open paper Ask about it PDF

Abstract

Explore similar work

Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks

xApp Empowered Resource Management for Non-Terrestrial Users in 5G O-RAN Networks

FedRings: A Scalable and Topology-Aware Federated Learning Framework for LEO Satellite Constellations