Years of research on transport protocols have not solved the tussle between in-network and end-to-end congestion control. This debate is due to the variance of conditions and assumptions in different network scenarios, e.g., cellular versus data center networks. Recently, the community has proposed a few transport protocols driven by machine learning, nonetheless limited to end-to-end approaches. In this paper, we present Owl, a transport protocol based on reinforcement learning, whose goal is to select the proper congestion window learning from end-to-end features and network signals, when available. We show that our solution converges to a fair resource allocation after the learning overhead. Our kernel implementation, deployed over emulated and large scale virtual network testbeds, outperforms all benchmark solutions based on end-to-end or in-network congestion control.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Owl: Congestion Control with Partially Invisible Networks via Reinforcement Learning


    Beteiligte:
    Sacco, Alessio (Autor:in) / Flocco, Matteo (Autor:in) / Esposito, Flavio (Autor:in) / Marchetto, Guido (Autor:in)

    Erscheinungsdatum :

    2021-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Partially Oblivious Congestion Control for the Internet via Reinforcement Learning

    Alessio Sacco / Matteo Flocco / Flavio Esposito et al. | BASE | 2023

    Freier Zugriff

    ReCoCo: Reinforcement learning-based Congestion control for Real-time applications

    Markudova, Dena / Meo, Michela | BASE | 2023

    Freier Zugriff

    Freeway Congestion Management With Reinforcement Learning Headway Control of Connected and Autonomous Vehicles

    Elmorshedy, Lina / Smirnov, Ilia / Abdulhai, Baher | Transportation Research Record | 2023

    Freier Zugriff