Abstract
Supported by the latest evolution of the 5G technologies, Augmented Reality (AR) & Virtual Reality (VR) video streaming services are experiencing an unprecedented growth. However, the transmission issues caused by heterogeneous access and dynamic traffic are still challenging 5G communications. The Internet Engineering Task Force (IETF)’s Multipath Transmission Control Protocol (MPTCP) can aggregate bandwidth and balance traffic across multiple subflows in a heterogeneous network environment. However, in order to support delivery of high quality 5G media services, researchers should also address MPTCP’s inefficient data scheduling to heterogenous sub-paths, consideration of multiple criteria, including energy consumption and its inconsistent behavior when employed along with the Dynamic Adaptive Streaming over HTTP (DASH) adaptive application layer protocol. To address these issues, we propose a Q-Learning driven Energy-aware Data Scheduling (QLE-DS) mechanism for MPTCP-based media services. QLE-DS models the multipath scheduling as a Q-learning process and employs a novel quantum clustering approach to discretize the high dimensional continuous Q-table. An asynchronous framework is designed to improve the learning efficiency of QLE-DS. The simulation results show that QLE-DS performs better than other MPTCP scheduling algorithms in terms of flow completion time (FCT), retransmission rate, and energy consumption.
Highlights
T HE LATEST developments of communication technologies and intelligent devices, have fueled a rapid evolution of 5G services including high quality video streaming
We design the reward with throughput th, packet loss pl and energy consumption e, which prompt improving the throughput, reducing loss rate and declining the energy expend in Multipath Transmission Control Protocol (MPTCP)
This paper proposes a new MPTCP scheduling solution based on reinforcement learning method to optimize energy consumption
Summary
T HE LATEST developments of communication technologies and intelligent devices, have fueled a rapid evolution of 5G services including high quality video streaming. In such an environment, aggregating the video traffic transmitted over multiple network interfaces can improve the overall user experiences. The authors of [11] proposed an energy-aware load balancing method for MPTCP scheduling and those of [12] introduced a low latency-focused scheduler These researchers did not focus on the performance of 5G media services, ignoring the interaction between transport layer scheduling and application layer scheduling. Model MPTCP data scheduling as a Q-learning process based on accurate evaluation of multiple important transmission factors for 5G media services: packet loss rate, throughput and energy consumption.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have