DDPG-MPCC: An Experience Driven Multipath Performance Oriented Congestion Control
-
Published:2024-01-23
Issue:2
Volume:16
Page:37
-
ISSN:1999-5903
-
Container-title:Future Internet
-
language:en
-
Short-container-title:Future Internet
Author:
Pokhrel Shiva Raj1ORCID, Kua Jonathan1ORCID, Satish Deol1, Ozer Sebnem2, Howe Jeff2, Walid Anwar3
Affiliation:
1. IoT Research Lab, Deakin University, Geelong 3220, Australia 2. Comcast Corporation, Philadelphia, PA 19103, USA 3. Amazon Science, New York, NY 10001, USA
Abstract
We introduce a novel multipath data transport approach at the transport layer referred to as ‘Deep Deterministic Policy Gradient for Multipath Performance-oriented Congestion Control’ (DDPG-MPCC), which leverages deep reinforcement learning to enhance congestion management in multipath networks. Our method combines DDPG with online convex optimization to optimize fairness and performance in simultaneously challenging multipath internet congestion control scenarios. Through experiments by developing kernel implementation, we show how DDPG-MPCC performs compared to the state-of-the-art solutions.
Funder
COMCAST Innovation Fund
Subject
Computer Networks and Communications
Reference40 articles.
1. BBR: Congestion-based congestion control;Cardwell;Commun. ACM,2017 2. Dong, M., Li, Q., Zarchy, D., Godfrey, P.B., and Schapira, M. (2015, January 4–6). PCC: Re-architecting congestion control for consistent high performance. Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15), Oakland, CA, USA. 3. Dong, M., Meng, T., Zarchy, D., Arslan, E., Gilad, Y., Godfrey, B., and Schapira, M. (2018, January 9–11). PCC Vivace: Online-Learning Congestion Control. Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18), Renton, WA, USA. 4. Arun, V., and Balakrishnan, H. (2018, January 9–11). Copa: Practical Delay-Based Congestion Control for the Internet. Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18), Renton, WA, USA. 5. Gilad, T., Rozen-Schiff, N., Godfrey, P.B., Raiciu, C., and Schapira, M. (2020, January 1–4). MPCC: Online learning multipath transport. Proceedings of the 16th International Conference on emerging Networking EXperiments and Technologies, Barcelona, Spain.
|
|