Caching-Aware Intelligent Handover Strategy for LEO Satellite Networks

Recently, many Low Earth Orbit (LEO) satellite networks are being implemented to provide seamless communication services for global users. Since the high mobility of LEO satellites, handover strategy has become one most important topics systems. However, limited on-board caching resource satellites make it difficult guarantee performance. In this paper, we propose a multiple attributes decision jointly considering three factors, which capacity, remaining service time and idle channels satellites. Furthermore, caching-aware intelligent is given based on deep reinforcement learning (DRL) maximize long-term benefits system. Compared with traditional strategies, proposed reduces failure rate by up nearly 81% when system occupancy reaches 90%, lower call blocking in user arrival scenarios. Simulation results show that can effectively mitigate due occupation, as well flexibly allocate channel resources reduce blocking.