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

被引：44

作者：

Xiao, Kefan ^{[1
]}

Mao, Shiwen ^{[1
]}

Tugnait, Jitendra K. ^{[1
]}

机构：

[1] Auburn Univ, Dept Elect & Comp Engn, Auburn, AL 36849 USA

来源：

IEEE ACCESS | 2019年 / 7卷

关键词：

Congestion control; deep convolutional neural network (DCNN); deep reinforcement learning (DRL); long short term memory (LSTM); machine learning;

D O I：

10.1109/ACCESS.2019.2892046

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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 modelfree, 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.

引用

页码：11892 / 11904

页数：13

共 50 条

[1] TCP Congestion Control with Multiagent Reinforcement and Transfer Learning
Kasi, Shahrukh Khan
Das, Saptarshi
Biswas, Subir
2021 IEEE 11TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2021, : 1507 - 1513
[2] A Deep Reinforcement Learning based Congestion Control Mechanism for NDN
Lan, Dehao
Tan, Xiaobin
Lv, Jinyang
Jin, Yang
Yang, Jian
ICC 2019 - 2019 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2019,
[3] RAN Information-Assisted TCP Congestion Control Using Deep Reinforcement Learning With Reward Redistribution
Chen, Minghao
Li, Rongpeng
Crowcroft, Jon
Wu, Jianjun
Zhao, Zhifeng
Zhang, Honggang
IEEE TRANSACTIONS ON COMMUNICATIONS, 2022, 70 (01) : 215 - 230
[4] Glider: rethinking congestion control with deep reinforcement learning
Xia, Zhenchang
Wu, Libing
Wang, Fei
Liao, Xudong
Hu, Haiyan
Wu, Jia
Wu, Dan
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2023, 26 (01): : 115 - 137
[5] Glider: rethinking congestion control with deep reinforcement learning
Zhenchang Xia
Libing Wu
Fei Wang
Xudong Liao
Haiyan Hu
Jia Wu
Dan Wu
World Wide Web, 2023, 26 : 115 - 137
[6] A Reinforcement Learning Congestion Control Algorithm for Smart Grid Networks
Andrade-Zambrano, Argenis Ronaldo
Leon, Juan Pablo Astudillo
Morocho-Cayamcela, Manuel Eugenio
Cardenas, Leticia Lemus
Llopis, Luis J. de la Cruz
IEEE ACCESS, 2024, 12 : 75072 - 75092
[7] Experience-Driven Congestion Control: When Multi-Path TCP Meets Deep Reinforcement Learning
Xu, Zhiyuan
Tang, Jian
Yin, Chengxiang
Wang, Yanzhi
Xue, Guoliang
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2019, 37 (06) : 1325 - 1336
[8] Implementability improvement of deep reinforcement learning based congestion control in cellular network
Naqvi, Haidlir Achmad
Hilman, Muhammad Hafizhuddin
Anggorojati, Bayu
COMPUTER NETWORKS, 2023, 233
[9] Dynamic TCP Initial Windows and Congestion Control Schemes Through Reinforcement Learning
Nie, Xiaohui
Zhao, Youjian
Li, Zhihan
Chen, Guo
Sui, Kaixin
Zhang, Jiyang
Ye, Zijie
Pei, Dan
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2019, 37 (06) : 1231 - 1247
[10] DeepCC: Multi-Agent Deep Reinforcement Learning Congestion Control for Multi-Path TCP Based on Self-Attention
He, Bo
Wang, Jingyu
Qi, Qi
Sun, Haifeng
Liao, Jianxin
Du, Chunning
Yang, Xiang
Han, Zhu
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2021, 18 (04): : 4770 - 4788

← 1 2 3 4 5 →