TRUST: A TCP Throughput Prediction Method in Mobile Networks

Bo Wei, Wataru Kawakami, Kenji Kanai, Jiro Katto, Shangguang Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Throughput prediction is essential for ensuring high quality of service for video streaming transmissions. However, current methods are incapable of accurately predicting throughput in mobile networks, especially for moving user scenarios. Therefore, we propose a TCP throughput prediction method TRUST using machine learning for mobile networks. TRUST has two stages: user movement pattern identification and throughput prediction. In the prediction stage, the long short-term memory (LSTM) model is employed for TCP throughput prediction. TRUST takes all the communication quality factors, sensor data and scenario information into consideration. Field experiments are conducted to evaluate TRUST in various scenarios. The results indicate that TRUST can predict future throughput with higher accuracy than the conventional methods, which decreases the throughput prediction error by maximum 44% under the moving bus scenario.

Original languageEnglish
Title of host publication2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538647271
DOIs
Publication statusPublished - 2019 Feb 20
Event2018 IEEE Global Communications Conference, GLOBECOM 2018 - Abu Dhabi, United Arab Emirates
Duration: 2018 Dec 92018 Dec 13

Publication series

Name2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings

Conference

Conference2018 IEEE Global Communications Conference, GLOBECOM 2018
CountryUnited Arab Emirates
CityAbu Dhabi
Period18/12/918/12/13

Fingerprint

Mobile Networks
Wireless networks
Throughput
Prediction
predictions
Scenarios
machine learning
Field Experiment
Video Streaming
Quality Factor
Memory Model
Video streaming
Prediction Error
Mobile networks
Q factors
Quality of Service
communication
Learning systems
Quality of service
Machine Learning

Keywords

  • LSTM
  • machine learning
  • mobile networks
  • throughput prediction

ASJC Scopus subject areas

  • Information Systems and Management
  • Renewable Energy, Sustainability and the Environment
  • Safety, Risk, Reliability and Quality
  • Signal Processing
  • Modelling and Simulation
  • Instrumentation
  • Computer Networks and Communications

Cite this

Wei, B., Kawakami, W., Kanai, K., Katto, J., & Wang, S. (2019). TRUST: A TCP Throughput Prediction Method in Mobile Networks. In 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings [8647390] (2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GLOCOM.2018.8647390

TRUST : A TCP Throughput Prediction Method in Mobile Networks. / Wei, Bo; Kawakami, Wataru; Kanai, Kenji; Katto, Jiro; Wang, Shangguang.

2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8647390 (2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wei, B, Kawakami, W, Kanai, K, Katto, J & Wang, S 2019, TRUST: A TCP Throughput Prediction Method in Mobile Networks. in 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings., 8647390, 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE Global Communications Conference, GLOBECOM 2018, Abu Dhabi, United Arab Emirates, 18/12/9. https://doi.org/10.1109/GLOCOM.2018.8647390
Wei B, Kawakami W, Kanai K, Katto J, Wang S. TRUST: A TCP Throughput Prediction Method in Mobile Networks. In 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8647390. (2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings). https://doi.org/10.1109/GLOCOM.2018.8647390
Wei, Bo ; Kawakami, Wataru ; Kanai, Kenji ; Katto, Jiro ; Wang, Shangguang. / TRUST : A TCP Throughput Prediction Method in Mobile Networks. 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings).
@inproceedings{274e8715e2574528b3a348296cfa822c,
title = "TRUST: A TCP Throughput Prediction Method in Mobile Networks",
abstract = "Throughput prediction is essential for ensuring high quality of service for video streaming transmissions. However, current methods are incapable of accurately predicting throughput in mobile networks, especially for moving user scenarios. Therefore, we propose a TCP throughput prediction method TRUST using machine learning for mobile networks. TRUST has two stages: user movement pattern identification and throughput prediction. In the prediction stage, the long short-term memory (LSTM) model is employed for TCP throughput prediction. TRUST takes all the communication quality factors, sensor data and scenario information into consideration. Field experiments are conducted to evaluate TRUST in various scenarios. The results indicate that TRUST can predict future throughput with higher accuracy than the conventional methods, which decreases the throughput prediction error by maximum 44{\%} under the moving bus scenario.",
keywords = "LSTM, machine learning, mobile networks, throughput prediction",
author = "Bo Wei and Wataru Kawakami and Kenji Kanai and Jiro Katto and Shangguang Wang",
year = "2019",
month = "2",
day = "20",
doi = "10.1109/GLOCOM.2018.8647390",
language = "English",
series = "2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings",

}

TY - GEN

T1 - TRUST

T2 - A TCP Throughput Prediction Method in Mobile Networks

AU - Wei, Bo

AU - Kawakami, Wataru

AU - Kanai, Kenji

AU - Katto, Jiro

AU - Wang, Shangguang

PY - 2019/2/20

Y1 - 2019/2/20

N2 - Throughput prediction is essential for ensuring high quality of service for video streaming transmissions. However, current methods are incapable of accurately predicting throughput in mobile networks, especially for moving user scenarios. Therefore, we propose a TCP throughput prediction method TRUST using machine learning for mobile networks. TRUST has two stages: user movement pattern identification and throughput prediction. In the prediction stage, the long short-term memory (LSTM) model is employed for TCP throughput prediction. TRUST takes all the communication quality factors, sensor data and scenario information into consideration. Field experiments are conducted to evaluate TRUST in various scenarios. The results indicate that TRUST can predict future throughput with higher accuracy than the conventional methods, which decreases the throughput prediction error by maximum 44% under the moving bus scenario.

AB - Throughput prediction is essential for ensuring high quality of service for video streaming transmissions. However, current methods are incapable of accurately predicting throughput in mobile networks, especially for moving user scenarios. Therefore, we propose a TCP throughput prediction method TRUST using machine learning for mobile networks. TRUST has two stages: user movement pattern identification and throughput prediction. In the prediction stage, the long short-term memory (LSTM) model is employed for TCP throughput prediction. TRUST takes all the communication quality factors, sensor data and scenario information into consideration. Field experiments are conducted to evaluate TRUST in various scenarios. The results indicate that TRUST can predict future throughput with higher accuracy than the conventional methods, which decreases the throughput prediction error by maximum 44% under the moving bus scenario.

KW - LSTM

KW - machine learning

KW - mobile networks

KW - throughput prediction

UR - http://www.scopus.com/inward/record.url?scp=85063429845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063429845&partnerID=8YFLogxK

U2 - 10.1109/GLOCOM.2018.8647390

DO - 10.1109/GLOCOM.2018.8647390

M3 - Conference contribution

T3 - 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings

BT - 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -