Intelligent Multi-Path TCP Congestion Control for video streaming in Internet of Deep Space Things communication

Abstract

The vision of space exploration includes missions to deep space that produce significant amounts of video data and require reliable video streaming back to the Earth. The Internet of Deep Space Things (IoDST) is envisioned to provide communication services for video data streaming for the mission spacecrafts. Ensuring reliable communications in IoDST requires Transmission Control Protocol (TCP) layer functionalities. However, current TCP Congestion Control (CC) protocols provide poor performance in IoDST communications primarily owing to the dependence on pre-defined rules to determine the transmission rate in a single path TCP flow. This paper proposes a Multi-Path TCP (MPTCP) CC design for data streaming transmission in IoDST. We utilized Scalable Video Coding (SVC)-based streaming to overcome the Head-of-Line (HoL) blocking and proposed an intelligent CC scheme based on Q-learning and Deep Q-Network (DQN) to solve the problems of challenging link conditions in IoDST. Our proposed CC scheme determines the optimal congestion window for data transmission in IoDST communications to maximize the TCP throughput performance and streaming data playback. Simulation results show that our proposed CC scheme achieves TCP throughput performance by up to approximately 257.14% and 73.08% compared to TCP CUBIC and TCP Westwood. In addition, video streaming playback by up to approximately 164.86%, 104.17%, 75%, 157.89% and 66% compared to TCP CUBIC, TCP BBR, TCP Westwood, DRL-TCP and QLE-DS, respectively. Finally the total streaming data transfer time by up to approximately 61%, 20%, 63%, 21% and 19% compared to TCP CUBIC, TCP BBR, TCP Westwood, DRL-TCP and QLE-DS, respectively. © 2023