Reinforcement Learning Based Load Balancing for Geographically Distributed Data centres

Max Mackie, Hongjian Sun, Jing Jiang

    Research output: Contribution to conferencePaperpeer-review

    22 Downloads (Pure)

    Abstract

    This paper proposes a method of migrating workload among geo-distributed data centres that are equipped with on-site renewable energy sources (RES), such as solar and wind energy, to decarbonise data centres. It aims to optimise the performance of such a system by introducing a tunable Reinforcement Learning (RL) based load-balancing algorithm that implements a Neural Network to intelligently migrate workload. By migrating workload within the network of geo-distributed data centres, spatial variations in electricity price and intermittent RES can be capitalised upon to enhance data centres' operations. The proposed algorithm is evaluated by running simulations using real-world data traces. It is found that the proposed algorithm is able to reduce costs by 6.1% whilst also increasing the utilisation of RES by 10.7%.
    Original languageEnglish
    Number of pages6
    Publication statusUnpublished - 18 Oct 2021
    EventISGT Europe 2021: IEEE PES Innovative Smart Grid Technologies: Smart Grids: Toward a Carbon-free Future - Virtual, Aalto University, Espoo, Finland
    Duration: 18 Oct 202121 Oct 2021
    https://ieee-isgt-europe.org/

    Conference

    ConferenceISGT Europe 2021: IEEE PES Innovative Smart Grid Technologies
    Abbreviated titleIEEE PES ISGT EUROPE 2021
    Country/TerritoryFinland
    CityEspoo
    Period18/10/2121/10/21
    Internet address

    Keywords

    • Data centre
    • Machine Learning
    • Load Balancing
    • Reinforcement Learning

    Fingerprint

    Dive into the research topics of 'Reinforcement Learning Based Load Balancing for Geographically Distributed Data centres'. Together they form a unique fingerprint.

    Cite this