The knowledge of future throughput variation in wireless networks usingsmartphone becomes more and more possible by exploiting the rich contextualinformation from smartphone sensors through mobile applications and services.Contextual information may include the traffic, mobility and radio conditions.Inspired by the attractive features and potential advantages of this agileresource management, several approaches have been proposed during the lastperiod. However, agile resource management also comes with its own challenges,and there are significant technical issues that still need to be addressed forsuccessful rollout and operation of this technique. In this paper, we proposean approach for anticipating throughput variation for mobile video streamingservices. The solution of the optimization problem realizes a fundamentaltrade-offs among critical metrics that impact the user's perceptual quality ofthe experience (QoE) and system utilization. Both simulated and real-worldtraces are carried out to evaluate the performance of the proposed approach. Itis shown that our approach provides the accuracy, efficiency and robustnessthat the new 5G architectures require.
展开▼
