MPTCP Throughput Enhancement by Q-learning for Mobile Devices

Esmaeil F. G. M. Beig; Parisa Daneshjoo; Saeid Rezaei; Ali Akbar Movassagh; Ramin Karimi; Yongrui Qin

doi:10.1109/HPCC/SmartCity/DSS.2018.00197

MPTCP Throughput Enhancement by Q-learning for Mobile Devices

Esmaeil F. G. M. Beig, Parisa Daneshjoo, Saeid Rezaei, Ali Akbar Movassagh, Ramin Karimi, Yongrui Qin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

Mobile devices are able to leverage diverse heterogeneous network paths by Multi-Path Transmission Control Protocol (MPTCP); nevertheless, boosting MPTCP throughput in wireless networks is a real bear. Not only the best path(s) should be selected, but also the optimal congestion control mechanism should be chosen. We investigate the impact of different paths and congestion control for different signal quality states. Consequently, we present the novel MPTCP algorithm augmenting the end user throughput by understating the best policy in different situations by Q-learning. The Results reveal a tremendous effect of switching between the different interfaces and changing the congestion control mechanism on throughput and delay. By and large, the proposed framework achieves 10% more throughput compared to base MPTCP.

Original language	English
Title of host publication	2018 IEEE 20th International Conference on High Performance Computing and Communications
Subtitle of host publication	IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
Publisher	IEEE
Pages	1171-1176
Number of pages	6
ISBN (Electronic)	9781538666142
ISBN (Print)	9781538666159
DOIs	https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00197
Publication status	Published - 24 Jan 2019
Event	20th IEEE International Conference on High Performance Computing and Communications - Exeter, United Kingdom Duration: 28 Jun 2018 → 30 Jun 2018 Conference number: 20 http://cse.stfx.ca/~hpcc2018/ (Link to Conference Website)

Conference

Conference	20th IEEE International Conference on High Performance Computing and Communications
Abbreviated title	HPCC-2018
Country/Territory	United Kingdom
City	Exeter
Period	28/06/18 → 30/06/18
Internet address	http://cse.stfx.ca/~hpcc2018/ (Link to Conference Website)

Access to Document

10.1109/HPCC/SmartCity/DSS.2018.00197Licence: Unspecified

SmartNEM-2018-187-final ver (3)Accepted author manuscript, 788 KB

Cite this

Beig, E. F. G. M., Daneshjoo, P., Rezaei, S., Movassagh, A. A., Karimi, R., & Qin, Y. (2019). MPTCP Throughput Enhancement by Q-learning for Mobile Devices. In 2018 IEEE 20th International Conference on High Performance Computing and Communications: IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS) (pp. 1171-1176). IEEE. https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00197

Beig, Esmaeil F. G. M. ; Daneshjoo, Parisa ; Rezaei, Saeid et al. / MPTCP Throughput Enhancement by Q-learning for Mobile Devices. 2018 IEEE 20th International Conference on High Performance Computing and Communications: IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). IEEE, 2019. pp. 1171-1176

@inproceedings{b1d02aeabde64275ad7108968836df4b,

title = "MPTCP Throughput Enhancement by Q-learning for Mobile Devices",

abstract = "Mobile devices are able to leverage diverse heterogeneous network paths by Multi-Path Transmission Control Protocol (MPTCP); nevertheless, boosting MPTCP throughput in wireless networks is a real bear. Not only the best path(s) should be selected, but also the optimal congestion control mechanism should be chosen. We investigate the impact of different paths and congestion control for different signal quality states. Consequently, we present the novel MPTCP algorithm augmenting the end user throughput by understating the best policy in different situations by Q-learning. The Results reveal a tremendous effect of switching between the different interfaces and changing the congestion control mechanism on throughput and delay. By and large, the proposed framework achieves 10% more throughput compared to base MPTCP.",

keywords = "Congestion control, Multi-path TCP, Q-learning, Throughput",

author = "Beig, {Esmaeil F. G. M.} and Parisa Daneshjoo and Saeid Rezaei and Movassagh, {Ali Akbar} and Ramin Karimi and Yongrui Qin",

note = "{\textcopyright} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works; 20th IEEE International Conference on High Performance Computing and Communications, HPCC-2018 ; Conference date: 28-06-2018 Through 30-06-2018",

year = "2019",

month = jan,

day = "24",

doi = "10.1109/HPCC/SmartCity/DSS.2018.00197",

language = "English",

isbn = "9781538666159",

pages = "1171--1176",

booktitle = "2018 IEEE 20th International Conference on High Performance Computing and Communications",

publisher = "IEEE",

address = "United States",

url = "http://cse.stfx.ca/~hpcc2018/",

}

Beig, EFGM, Daneshjoo, P, Rezaei, S, Movassagh, AA, Karimi, R & Qin, Y 2019, MPTCP Throughput Enhancement by Q-learning for Mobile Devices. in 2018 IEEE 20th International Conference on High Performance Computing and Communications: IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). IEEE, pp. 1171-1176, 20th IEEE International Conference on High Performance Computing and Communications, Exeter, United Kingdom, 28/06/18. https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00197

MPTCP Throughput Enhancement by Q-learning for Mobile Devices. / Beig, Esmaeil F. G. M.; Daneshjoo, Parisa; Rezaei, Saeid et al.

2018 IEEE 20th International Conference on High Performance Computing and Communications: IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). IEEE, 2019. p. 1171-1176.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MPTCP Throughput Enhancement by Q-learning for Mobile Devices

AU - Beig, Esmaeil F. G. M.

AU - Daneshjoo, Parisa

AU - Rezaei, Saeid

AU - Movassagh, Ali Akbar

AU - Karimi, Ramin

AU - Qin, Yongrui

N1 - Conference code: 20

PY - 2019/1/24

Y1 - 2019/1/24

N2 - Mobile devices are able to leverage diverse heterogeneous network paths by Multi-Path Transmission Control Protocol (MPTCP); nevertheless, boosting MPTCP throughput in wireless networks is a real bear. Not only the best path(s) should be selected, but also the optimal congestion control mechanism should be chosen. We investigate the impact of different paths and congestion control for different signal quality states. Consequently, we present the novel MPTCP algorithm augmenting the end user throughput by understating the best policy in different situations by Q-learning. The Results reveal a tremendous effect of switching between the different interfaces and changing the congestion control mechanism on throughput and delay. By and large, the proposed framework achieves 10% more throughput compared to base MPTCP.

AB - Mobile devices are able to leverage diverse heterogeneous network paths by Multi-Path Transmission Control Protocol (MPTCP); nevertheless, boosting MPTCP throughput in wireless networks is a real bear. Not only the best path(s) should be selected, but also the optimal congestion control mechanism should be chosen. We investigate the impact of different paths and congestion control for different signal quality states. Consequently, we present the novel MPTCP algorithm augmenting the end user throughput by understating the best policy in different situations by Q-learning. The Results reveal a tremendous effect of switching between the different interfaces and changing the congestion control mechanism on throughput and delay. By and large, the proposed framework achieves 10% more throughput compared to base MPTCP.

KW - Congestion control

KW - Multi-path TCP

KW - Q-learning

KW - Throughput

UR - http://www.scopus.com/inward/record.url?scp=85062502079&partnerID=8YFLogxK

U2 - 10.1109/HPCC/SmartCity/DSS.2018.00197

DO - 10.1109/HPCC/SmartCity/DSS.2018.00197

M3 - Conference contribution

SN - 9781538666159

SP - 1171

EP - 1176

BT - 2018 IEEE 20th International Conference on High Performance Computing and Communications

PB - IEEE

T2 - 20th IEEE International Conference on High Performance Computing and Communications

Y2 - 28 June 2018 through 30 June 2018

ER -

Beig EFGM, Daneshjoo P, Rezaei S, Movassagh AA, Karimi R, Qin Y. MPTCP Throughput Enhancement by Q-learning for Mobile Devices. In 2018 IEEE 20th International Conference on High Performance Computing and Communications: IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). IEEE. 2019. p. 1171-1176 doi: 10.1109/HPCC/SmartCity/DSS.2018.00197

MPTCP Throughput Enhancement by Q-learning for Mobile Devices

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this