A Prediction Approach to End-to-End Traffic in Space Information Networks

摘要

Software Defined Space Information Networks (SDSIN) is increasingly applied to life and production, the reason is that it can cope with various complex environments and tasks in the future communication environment. Owing to the performance advantages of the Software Defined Networking (SDN), some advanced technologies based on SDN are more and more applied to satellite network. In order to better provide users with high-quality services, network providers must predict and analyze End-to-End (E2E) traffic. Hence, this poses the natural question of how to accurately predict the future trend of E2E traffic to load balance, network optimization, and network security. Different from the previous 2-dimension terrestrial network, we study a 3-dimension SDSIN in this paper. Firstly, we analyze the difficulties and challenges of traffic engineering in SDSIN. Subsequently, an improved Hidden Markov Model (HMM) to E2E traffic prediction method is proposed. Finally, simulation results show that our improved HMM can be well applied for E2E traffic prediction in SDSIN.