IEICE TRANSACTIONS on Information
MPTCP-meLearning: A Multi-Expert Learning-Based MPTCP Extension to Enhance Multipathing Robustness against Network Attacks
Summary :
With multiple network interfaces are being widely equipped in modern mobile devices, the Multipath TCP (MPTCP) is increasingly becoming the preferred transport technique since it can uses multiple network interfaces simultaneously to spread the data across multiple network paths for throughput improvement. However, the MPTCP performance can be seriously affected by the use of a poor-performing path in multipath transmission, especially in the presence of network attacks, in which an MPTCP path would abrupt and frequent become underperforming caused by attacks. In this paper, we propose a multi-expert Learning-based MPTCP variant, called MPTCP-meLearning, to enhance MPTCP performance robustness against network attacks. MPTCP-meLearning introduces a new kind of predictor to possibly achieve better quality prediction accuracy for each of multiple paths, by leveraging a group of representative formula-based predictors. MPTCP-meLearning includes a novel mechanism to intelligently manage multiple paths in order to possibly mitigate the out-of-order reception and receive buffer blocking problems. Experimental results demonstrate that MPTCP-meLearning can achieve better transmission performance and quality of service than the baseline MPTCP scheme.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.11 pp.1795-1804
- Publication Date
- 2021/11/01
- Publicized
- 2021/07/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021NGP0009
- Type of Manuscript
- Special Section PAPER (Special Section on Next-generation Security Applications and Practice)
- Category
Authors
Yuanlong CAO
Jiangxi Normal University
Ruiwen JI
Jiangxi Normal University
Lejun JI
Jiangxi Normal University
Xun SHAO
Kitami Institute of Technology
Gang LEI
Jiangxi Normal University
Hao WANG
Jiangxi Normal University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yuanlong CAO, Ruiwen JI, Lejun JI, Xun SHAO, Gang LEI, Hao WANG, "MPTCP-meLearning: A Multi-Expert Learning-Based MPTCP Extension to Enhance Multipathing Robustness against Network Attacks" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 11, pp. 1795-1804, November 2021, doi: 10.1587/transinf.2021NGP0009.
Abstract: With multiple network interfaces are being widely equipped in modern mobile devices, the Multipath TCP (MPTCP) is increasingly becoming the preferred transport technique since it can uses multiple network interfaces simultaneously to spread the data across multiple network paths for throughput improvement. However, the MPTCP performance can be seriously affected by the use of a poor-performing path in multipath transmission, especially in the presence of network attacks, in which an MPTCP path would abrupt and frequent become underperforming caused by attacks. In this paper, we propose a multi-expert Learning-based MPTCP variant, called MPTCP-meLearning, to enhance MPTCP performance robustness against network attacks. MPTCP-meLearning introduces a new kind of predictor to possibly achieve better quality prediction accuracy for each of multiple paths, by leveraging a group of representative formula-based predictors. MPTCP-meLearning includes a novel mechanism to intelligently manage multiple paths in order to possibly mitigate the out-of-order reception and receive buffer blocking problems. Experimental results demonstrate that MPTCP-meLearning can achieve better transmission performance and quality of service than the baseline MPTCP scheme.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021NGP0009/_p
Copy
@ARTICLE{e104-d_11_1795,
author={Yuanlong CAO, Ruiwen JI, Lejun JI, Xun SHAO, Gang LEI, Hao WANG, },
journal={IEICE TRANSACTIONS on Information},
title={MPTCP-meLearning: A Multi-Expert Learning-Based MPTCP Extension to Enhance Multipathing Robustness against Network Attacks},
year={2021},
volume={E104-D},
number={11},
pages={1795-1804},
abstract={With multiple network interfaces are being widely equipped in modern mobile devices, the Multipath TCP (MPTCP) is increasingly becoming the preferred transport technique since it can uses multiple network interfaces simultaneously to spread the data across multiple network paths for throughput improvement. However, the MPTCP performance can be seriously affected by the use of a poor-performing path in multipath transmission, especially in the presence of network attacks, in which an MPTCP path would abrupt and frequent become underperforming caused by attacks. In this paper, we propose a multi-expert Learning-based MPTCP variant, called MPTCP-meLearning, to enhance MPTCP performance robustness against network attacks. MPTCP-meLearning introduces a new kind of predictor to possibly achieve better quality prediction accuracy for each of multiple paths, by leveraging a group of representative formula-based predictors. MPTCP-meLearning includes a novel mechanism to intelligently manage multiple paths in order to possibly mitigate the out-of-order reception and receive buffer blocking problems. Experimental results demonstrate that MPTCP-meLearning can achieve better transmission performance and quality of service than the baseline MPTCP scheme.},
keywords={},
doi={10.1587/transinf.2021NGP0009},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - MPTCP-meLearning: A Multi-Expert Learning-Based MPTCP Extension to Enhance Multipathing Robustness against Network Attacks
T2 - IEICE TRANSACTIONS on Information
SP - 1795
EP - 1804
AU - Yuanlong CAO
AU - Ruiwen JI
AU - Lejun JI
AU - Xun SHAO
AU - Gang LEI
AU - Hao WANG
PY - 2021
DO - 10.1587/transinf.2021NGP0009
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2021
AB - With multiple network interfaces are being widely equipped in modern mobile devices, the Multipath TCP (MPTCP) is increasingly becoming the preferred transport technique since it can uses multiple network interfaces simultaneously to spread the data across multiple network paths for throughput improvement. However, the MPTCP performance can be seriously affected by the use of a poor-performing path in multipath transmission, especially in the presence of network attacks, in which an MPTCP path would abrupt and frequent become underperforming caused by attacks. In this paper, we propose a multi-expert Learning-based MPTCP variant, called MPTCP-meLearning, to enhance MPTCP performance robustness against network attacks. MPTCP-meLearning introduces a new kind of predictor to possibly achieve better quality prediction accuracy for each of multiple paths, by leveraging a group of representative formula-based predictors. MPTCP-meLearning includes a novel mechanism to intelligently manage multiple paths in order to possibly mitigate the out-of-order reception and receive buffer blocking problems. Experimental results demonstrate that MPTCP-meLearning can achieve better transmission performance and quality of service than the baseline MPTCP scheme.
ER -
English
