作者: Mohammad Javad Shamani , Saeid Rezaei , Guillaume Jourjon , Aruna Seneviratne
DOI: 10.1109/ATNAC.2017.8215408
关键词: Efficient energy use 、 Distributed computing 、 Mobile device 、 Q-learning 、 Wireless network 、 Energy consumption 、 Energy (signal processing) 、 Throughput 、 Context (language use) 、 Computer science
摘要: Leveraging multi-path transmission in an energy-efficient manner is of great importance for mobile devices heterogeneous wireless networks. Recently, Multi-Path TCP (MPTCP) has been introduced as a potential solution that could leverage this path diversity, but making it energy efficient not only depends on the end-user's observed interface capacity also other competitors' decision. We discuss about paradox saving MPTCP devices. Then we propose, hereafter, new algorithm to enhance efficiency resource-shared network context by exploiting newly Q-learning framework. Based large scale simulation, demonstrate our proposed save up 36%, compared vanilla MPTCP.