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

Ha, Taeyun; Masood, Arooj; Na, Woongsoo; Cho, Sungrae

doi:10.1016/j.icte.2023.02.006

Cited by 4 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Internet of Deep Space Things, or IoDST, offered communication services for mission spacecraft that send video data. To improve TCP throughput and stream playback, Ha et al [15] designed a congestion control framework for MPTCP, which can be used for data streaming transmission. Their proposed Q-learning and Deep Q-Network (DQN)-based congestion control scheme calculated the ideal congestion window for data transfer in IoDST conversations.…”

Section: B Machine Learning Approaches For Congestion Control In Mptcpmentioning

confidence: 99%

“…They were tested using simulation, which, of course, does not emulate the real-world scenario. Machine Learning and Reinforcement Learning models have improved the above drawbacks as they can learn from past experience and they are more robust to the dynamic nature of real-world networks; However, machine learning techniques are usually slower than classical approaches and need a huge dataset to train the models [15]- [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical Approaches

Maliha,

Habibi,

Atiquzzaman

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Multipath TCP (MPTCP) has been widely used as an efficient way for communication in many applications. Data centers, smartphones, and network operators use MPTCP to balance the traffic in a network efficiently. MPTCP is an extension of TCP (Transmission Control Protocol), which provides multiple paths, leading to higher throughput and low latency. Although MPTCP has shown better performance than TCP in many applications, it has its own challenges. The network can become congested due to heavy traffic in the multiple paths (subflows) if the subflow rates are not determined correctly. Moreover, communication latency can occur if the packets are not scheduled correctly between the subflows. This paper reviews techniques to solve the above-mentioned problems based on two main approaches; non data-driven (classical) and data-driven (Machine Learning) approaches. This paper compares these two approaches and highlights their strengths and weaknesses with a view to motivating future researchers in this exciting area of machine learning for communications. This paper also provides details on the simulation of MPTCP and its implementations in real environments.

show abstract

Section: B Machine Learning Approaches For Congestion Control In Mptcpmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical Approaches

Maliha,

Habibi,

Atiquzzaman

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…The reference [ 98 ], delves into the development and evaluation of a multipath cubic TCP congestion control mechanism, augmented with multipath fast recovery strategies, tailored specifically for networks characterized by high bandwidth-delay product conditions. The advantages of this research are rooted in its potential to significantly enhance network performance and reliability in challenging environments.…”

Section: Introductionmentioning

confidence: 99%

What are the key stability challenges in high-bandwidth, non-minimum phase systems with time-varying, and non-smooth delays?

Weiwei,

Shaohui,

Sabzevari

2024

Heliyon

View full text Add to dashboard Cite

“…QTCP is based on Q-learning for congestion control [10,11], which improves throughput to a certain extent. MPTCP [12] uses Q-learning and Deep Q-Networks (DQN) for multipath congestion control, which is able to learn to take the best action based on the runtime state. However, the Q-learning algorithm is slow to learn and difficult to converge.…”

Section: Introductionmentioning

confidence: 99%

Intelligent TCP Congestion Control Policy Optimization

Shi,

Wang

2023

Applied Sciences

View full text Add to dashboard Cite

Network congestion control is an important means to improve network throughput and reduce data transmission delay. To further optimize the network data transmission capability, this research suggests a proximal policy optimization-based intelligent TCP congestion management method, creates a proxy that can communicate with the real-time network environment, and abstracts the TCP congestion control mechanism into a partially observable Markov decision process. Changes in the real-time state of the network are fed back to the agent, and the agent makes action commands to control the size of the congestion window, which will produce a new network state, and the agent will immediately receive a feedback reward value. To guarantee that the actions taken are optimum, the agent’s goal is to obtain the highest feedback reward value. The state space of network characteristics should be designed so that agents can observe enough information to make appropriate decisions. The reward function is designed through a weighted algorithm that enables the agent to balance and optimize throughput and latency. The model parameters of the agent are updated by the proximal policy optimization algorithm, and the truncation function keeps the parameters within a certain range, reducing the possibility of oscillation during gradient descent and ensuring that the training process can converge quickly. Compared to the traditional CUBIC control method, the results show that the TCP-PPO2 policy reduces latency by 11.7–87.5%.

show abstract

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

Cited by 4 publications

References 46 publications

A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical Approaches

A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical Approaches

What are the key stability challenges in high-bandwidth, non-minimum phase systems with time-varying, and non-smooth delays?

Intelligent TCP Congestion Control Policy Optimization

Contact Info

Product

Resources

About