TCP-Drinc: Smart Congestion Control Based on Deep Reinforcement Learning

As wired/wireless networks become more and more complex, the fundamental assumptions made by many existing TCP variants may not hold true anymore. In this paper, we develop a model-free, smart congestion control algorithm based on deep reinforcement learning, which has a high potential in dealing wi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.11892-11904
Main Authors: Xiao, Kefan, Mao, Shiwen, Tugnait, Jitendra K.
Format: Article
Language:English
Subjects:
Algorithms
Congestion
Congestion control
Control algorithms
Control theory
deep convolutional neural network (DCNN)
Deep learning
deep reinforcement learning (DRL)
Delays
long short term memory (LSTM)
Machine learning
Microsoft Windows
Protocols
Reinforcement learning
Wireless communication
Wireless networks
Wireless sensor networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As wired/wireless networks become more and more complex, the fundamental assumptions made by many existing TCP variants may not hold true anymore. In this paper, we develop a model-free, smart congestion control algorithm based on deep reinforcement learning, which has a high potential in dealing with the complex and dynamic network environment. We present TCP-Deep ReInforcement learNing-based Congestion control (Drinc) which learns from past experience in the form of a set of measured features to decide how to adjust the congestion window size. We present the TCP-Drinc design and validate its performance with extensive ns-3 simulations and comparison with five benchmark schemes.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2892046