Logo image
Scheduling Model Transmission and Training for Contact-Based Decentralized Satellite Federated Learning
Journal article

Scheduling Model Transmission and Training for Contact-Based Decentralized Satellite Federated Learning

Lei Cheng, Gang Feng, Shuang Qin, Yao Sun, Jian Wang, Feng Wang and Tony Q. S. Quek
IEEE transactions on cognitive communications and networking, Vol.12, pp.1211-1226
2026

Abstract

Accuracy Computational modeling Data models Decentralized satellite federated learning Federated learning Low earth orbit satellites multi-agent reinforcement learning Orbits Processor scheduling Satellites Scheduling scheduling strategy Training
The significant enhancement of satellite onboard processing capability and drastic proliferation of Artificial Intelligence (AI) applications have fostered decentralized satellite federated learning (DSFL), a transformative paradigm that exchanges and aggregates machine learning (ML) models in satellite clusters for collaborative learning. However, the limited model exchange opportunities caused by intermittent inter-satellite contacts, along with heterogeneous onboard datasets, can lead to ineffective and/or biased model aggregation. To address these issues, it is crucial yet challenging to design an effective DSFL scheduling strategy that determines whether and when to pull models from contact satellites and perform local training for optimizing DSFL performance. In this paper, we propose a contact-based DSFL framework and formulate the DSFL scheduling problem to maximize the accuracy of trained models. As the problem cannot be solved directly, we transform it into a hierarchical Markov game by introducing options for decision agents deployed on individual satellites. Under a learning-to-learn paradigm, we develop a Multi-agent Dueling Double Deep Q Network (MA3DQN)-based intelligent DSFL scheduling strategy. The agents, trained in a distributed and alternating manner, adaptively make scheduling decisions based on instantaneous partial observations of the environment. Simulation results demonstrate the efficiency and adaptability of the MA3DQN-based strategy over three baselines.

Metrics

1 Record Views

Details

Logo image