ALANINE: A Novel Decentralized Personalized Federated Learning For Heterogeneous LEO Satellite Constellation

TL;DR

ALANINE introduces a decentralized personalized federated learning framework for heterogeneous LEO satellite constellations, improving on-orbit image super-resolution, data efficiency, and model adaptability.

Contribution

It presents a novel decentralized PFL framework combining model pruning and personalization for satellite image processing in heterogeneous LEO constellations.

Findings

Superior on-orbit training performance compared to centralized methods.

Enhanced data acquisition efficiency and model accuracy.

Effective handling of data heterogeneity and satellite-specific characteristics.

Abstract

Low Earth Orbit (LEO) satellite constellations have seen significant growth and functional enhancement in recent years, which integrates various capabilities like communication, navigation, and remote sensing. However, the heterogeneity of data collected by different satellites and the problems of efficient inter-satellite collaborative computation pose significant obstacles to realizing the potential of these constellations. Existing approaches struggle with data heterogeneity, varing image resolutions, and the need for efficient on-orbit model training. To address these challenges, we propose a novel decentralized PFL framework, namely, A Novel Decentra L ized Person A lized Federated Learning for Heteroge N eous LEO Satell I te Co N st E llation (ALANINE). ALANINE incorporates decentralized FL (DFL) for satellite image Super Resolution (SR), which enhances input data quality. Then it utilizes PFL to implement a personalized approach that accounts for unique characteristics of satellite data. In addition, the framework employs advanced model pruning to optimize model complexity and transmission efficiency. The framework enables efficient data acquisition and processing while improving the accuracy of PFL image processing models. Simulation results demonstrate that ALANINE exhibits superior performance in on-orbit training of SR and PFL image processing models compared to traditional centralized approaches. This novel method shows significant improvements in data acquisition efficiency, process accuracy, and model adaptability to local satellite conditions.