FedHC: A Hierarchical Clustered Federated Learning Framework for Satellite Networks

With the proliferation of data-driven services, the volume of data that needs to be processed by satellite networks has significantly increased. Federated learning (FL) is well-suited for big data processing in distributed and resource-constrained satellite environments. However, achieving robust convergence while minimizing processing time and energy consumption remains challenging. To this end, we propose a hierarchical clustered federated learning framework, FedHC. This framework employs a combined feature based dynamic clustering algorithm at the cluster aggregation stage, grouping satellites into different clusters and designating a cluster center as the parameter server (PS) to accelerate model aggregation. Several communicable cluster PS satellites are then selected through ground stations to aggregate global parameters, facilitating the FL process. Moreover, a meta-learning-driven satellite re-clustering algorithm is introduced to enhance adaptability to dynamic satellite cluster changes. Extensive experiments conducted on a satellite network testbed demonstrate that FedHC can significantly reduce processing time (up to 3x) and energy consumption (up to 2x) compared to other comparative methods while maintaining model accuracy.