Classic Meets Modern
Authors:
Open Access
- 30 July 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 632-647
Abstract
These days, taking the revolutionary approach of using clean-slate learning-based designs to completely replace the classic congestion control schemes for the Internet is gaining popularity. However, we argue that current clean-slate learning-based techniques bring practical issues and concerns such as overhead, convergence issues, and low performance over unseen network conditions to the table. To address these issues, we take a pragmatic and evolutionary approach combining classic congestion control strategies and advanced modern deep reinforcement learning (DRL) techniques and introduce a novel hybrid congestion control for the Internet named Orca1. Through extensive experiments done over global testbeds on the Internet and various locally emulated network conditions, we demonstrate that Orca is adaptive and achieves consistent high performance in different network conditions, while it can significantly alleviate the issues and problems of its clean-slate learning-based counterparts.Keywords
This publication has 28 references indexed in Scilit:
- GENI: A federated testbed for innovative network experimentsComputer Networks, 2014
- Controlling queue delayCommunications of the ACM, 2012
- CUBICACM SIGOPS Operating Systems Review, 2008
- TCP-Illinois: A loss- and delay-based congestion control algorithm for high-speed networksPerformance Evaluation, 2008
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999
- Long Short-Term MemoryNeural Computation, 1997
- TCP VegasACM SIGCOMM Computer Communication Review, 1994
- Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions.Psychological Review, 1990
- Analysis of the increase and decrease algorithms for congestion avoidance in computer networksComputer Networks and ISDN Systems, 1989
- Flow Control Power is NondecentralizableIEEE Transactions on Communications, 1981