Abstract
Leveraging multi-path transmission in an energy-efficient manner is of great importance for mobile devices in 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 but also on the other competitors' decision. We discuss about the paradox of energy saving in MPTCP for mobile devices. Then we propose, hereafter, a new algorithm to enhance the MPTCP energy efficiency in a resource-shared wireless network context by exploiting a newly introduced Q-learning framework. Based on large scale simulation, we demonstrate that our proposed algorithm could save up to 36%, energy compared to vanilla MPTCP.