Decentralized satellite federated learning (DSFL) enables LEO satellites to collaboratively train models without relying on terrestrial infrastructures. In DSFL, concurrent model updates for multiple services increase the amount of computation on the satellite, which can lead to longer total training time. This paper proposes a computation-efficient DSFL framework to construct the overlay network for services to minimize the total training time. Simulation results demonstrate that the proposed scheme outperforms the baseline algorithms in terms of total training time.

This paper proposes a proactive aerial base station (ABS) deployment framework for hotspots that optimizes the placement of ABSs based on mobility and data traffic demand prediction using a LSTM model. We design a greedy-based ABS deployment algorithm to solve the data rate maximization problem, which is known to be NP-hard. Simulation results demonstrate that the proposed algorithm achieves a higher data rate with fewer ABSs compared to benchmark methods.

This paper proposes a strategy for offloading unmanned aerial vehicles (UAVs) tasks to electric vehicles and edge servers using a Stackelberg game model. We introduce a suitability score that considers distance, resource availability, and battery level to select the most suitable nodes for offloading UAV tasks. Simulation results demonstrate that the proposed scheme outperforms existing methods in terms of energy consumption and utility for UAVs.

Edge caching has been emerged to avoid redundant data transmission to the cloud by caching the popular contents on edge networks. While existing solutions for edge caching have focused on optimizing the hit ratio at the edge, they did not address the burden on edge servers under a massive content requests circumstance. The massive amount of content requests can cause the waiting delay at the edge server, leading to an unexpected long content delivery delay. Therefore, in this paper, we propose the distributed edge caching scheme that can reduce the content delivery delay by considering the waiting delay at the edge server.