Enhancing Efficiency with Adaptive Optimized Balancing Factor for MPTCP Congestion Control Using Deep Deterministic Policy Gradient: EE-AOBF-MPTCP-DDPG
DOI:
https://doi.org/10.22399/ijcesen.1409Keywords:
Congestion window, Threshold, Multipath, Machine Learning, Balancing factor, Sub-flowAbstract
MPTCP is rapidly emerging as one of the most advanced networking protocols. Standardized by the IETF as an extension of TCP, it enables seamless communication across multiple interfaces from source to destination. Despite its potential, existing multipath congestion control mechanisms face significant challenges due to the diverse QoS characteristics of heterogeneous interfaces. While recent algorithms primarily emphasize enhancing the growth dynamics of the congestion window (CWND), the reduction mechanisms remain largely overlooked. Furthermore, conventional congestion control approaches often rely on manual adjustments, which are insufficient in highly dynamic network environments. Given the demonstrated success of machine learning algorithms across industries such as IoT, video streaming, and autonomous vehicles, this study introduces the Deep Deterministic Policy Gradient Multi-Path (DDPG-MP) framework. This innovative approach dynamically optimizes congestion control using a balancing factor, enabling adaptive and efficient performance in multipath networking environments.
References
Barré, S., Paasch, C. and Bonaventure, O., (2011). Multipath TCP: from theory to practice. In NETWORKING 2011: 10th International IFIP TC 6 Networking Conference, Valencia, Spain, May 9-13, 2011, Proceedings, Part I 10 (pp. 444-457). Springer Berlin Heidelberg.
Raiciu C, Paasch C, Barre S, Ford A, Honda M, Duchene F, Bonaventure O, Handley M. How hard can it be? designing and implementing a deployable multipath {TCP}. In9th USENIX symposium on networked systems design and implementation (NSDI 12) 2012 (pp. 399-412).
Wischik, D., Raiciu, C., Greenhalgh, A. and Handley, M., (2011). Design, implementation and evaluation of congestion control for multipath {TCP}. In 8th USENIX Symposium on Networked Systems Design and Implementation (NSDI 11).
Khalili, Ramin, Nicolas Gast, Miroslav Popovic, and Jean-Yves Le Boudec. (2013). MPTCP is not Pareto-optimal: Performance issues and a possible solution." IEEE/ACM Transactions On Networking 21(5); 1651-1665.
Peng, Qiuyu, Anwar Walid, and Steven H. Low. (2013) Multipath TCP algorithms: Theory and design." ACM SIGMETRICS Performance Evaluation Review 41(1): 305-316.
Lubna, T., Mahmud, I. and Cho, Y.Z., 2020. D-LIA: Dynamic congestion control algorithm for MPTCP. ICT Express, 6(4),;263-268.
Becke, M., Dreibholz, T., Adhari, H. and Rathgeb, E.P., (2012), June. On the fairness of transport protocols in a multi-path environment. In 2012 IEEE International Conference on Communications (ICC) (pp. 2666-2672).
Raiciu, C., Handley, M. and Wischik, D., (2011). Coupled congestion control for multipath transport protocols (No. rfc6356).
Raiciu, Costin, Damon Wischik, and Mark Handley (2009). Practical congestion control for multipath transport protocols. University College London, London/United Kingdom, Tech. Rep
Jowkarishasaltaneh, Farinaz, and Jason But. (2022). An Analysis of MPTCP Congestion Control. In Telecom, vol. 3, no. 4, pp. 581-609. MDPI.
Wei, W., Xue, K., Han, J., Wei, D.S. and Hong, P., (2020). Shared bottleneck-based congestion control and packet scheduling for multipath TCP. IEEE/ACM Transactions on Networking, 28(2);653-666.
Li, Wenzhong, Han Zhang, Shaohua Gao, ChaojingXue, Xiaoliang Wang, and Sanglu Lu. (2019) SmartCC: A reinforcement learning approach for multipath TCP congestion control in heterogeneous networks. IEEE Journal on Selected Areas in Communications 37(11): 2621-2633.
Yu, Chengxiao, Wei Quan, Nan Cheng, Shihua Chen, and Hongke Zhang. (2019). Coupled or uncoupled? Multi-path TCP congestion control for high-speed railway networks. In 2019 IEEE/CIC International Conference on Communications in China (ICCC), pp. 612-617. IEEE.
Rao, K. Raghavendra, and B. N. Jagadesh. (2021). Design and Implementation of Dynamic Packet Scheduling with Waiting Time Aware: DPSW2A." International Journal of Advanced Computer Science and Applications 12(11).
Paasch, Christoph, Ramin Khalili, and Olivier Bonaventure. (2013). On the benefits of applying experimental design to improve multipath TCP. In Proceedings of the ninth ACM conference on Emerging networking experiments and technologies, pp. 393-398.
Abbasloo, Soheil, Chen-Yu Yen, and H. Jonathan Chao. (2020). Classic meets modern: A pragmatic learning-based congestion control for the internet. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication, pp. 632-647.
Xiao, K., Mao, S. and Tugnait, J.K., 2019. TCP-Drinc: Smart congestion control based on deep reinforcement learning. IEEE Access, 7;11892-11904.
Maliha, Maisha, Golnaz Habibi, and Mohammed Atiquzzaman. (2023). A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical Approaches. In 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 49-61. IEEE,
Ha, Taeyun, Arooj Masood, Woongsoo Na, and Sungrae Cho. (2023) Intelligent multi-path TCP congestion control for video streaming in internet of deep space things communication. ICT Express 9, no. 5: 860-868.
Maliha, Maisha, Golnaz Habibi, and Mohammed Atiquzzaman. (2023).A Survey on Congestion Control and Scheduling for Multipath TCP: Machine Learning vs Classical Approaches. In 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS), pp. 49-61.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
