Learning to Schedule Resources in Software-Defined Radio Access Networks

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    Abstract

    A software-defined control plane simplifies network operations in dense radio access networks (RANs) by abstracting the base stations as a logical centralized network controller (CNC). In a software-defined RAN, the CNC and the wireless service providers (WSPs) can thus be decoupled. The CNC allocates subbands to the mobile terminals (MTs) based on their submitted bids. Such an auction is repeated across time and regulated by the Vickrey-Clarke-Groves pricing mechanism. The objective of an MT subscribed to a particular WSP is to optimize the expected long-term transmit power in transmitting packets subject to a specific Quality-of-Service constraint. We formulate the problem as a multi-agent Markov decision process, where the subband allocation (SA) and packet scheduling decisions are a function of the global network state. To address the challenges of signalling overhead and computational complexity, we approximate the queue state-SA factor by the sum of per-MT queue state value functions, and derive an online localized algorithm to learn them. The presented experiments show significant performance gains from our proposed studies.

    Original languageEnglish
    Title of host publication2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Number of pages6
    ISBN (Electronic)978-1-5386-4920-6, 978-1-5386-6977-8
    DOIs
    Publication statusPublished - 21 Feb 2019
    MoE publication typeA4 Article in a conference publication
    Event2018 IEEE Globecom Workshops, GC Wkhps 2018 - Abu Dhabi, United Arab Emirates
    Duration: 9 Dec 201813 Dec 2018

    Conference

    Conference2018 IEEE Globecom Workshops, GC Wkhps 2018
    CountryUnited Arab Emirates
    CityAbu Dhabi
    Period9/12/1813/12/18

    Fingerprint

    Controllers
    Base stations
    Computational complexity
    Quality of service
    Scheduling
    Costs
    Experiments

    Cite this

    Chen, X. (2019). Learning to Schedule Resources in Software-Defined Radio Access Networks. In 2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GLOCOMW.2018.8644407
    Chen, Xianfu. / Learning to Schedule Resources in Software-Defined Radio Access Networks. 2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019.
    @inproceedings{e8b3597a91f04ee79d7d7c63713e35ac,
    title = "Learning to Schedule Resources in Software-Defined Radio Access Networks",
    abstract = "A software-defined control plane simplifies network operations in dense radio access networks (RANs) by abstracting the base stations as a logical centralized network controller (CNC). In a software-defined RAN, the CNC and the wireless service providers (WSPs) can thus be decoupled. The CNC allocates subbands to the mobile terminals (MTs) based on their submitted bids. Such an auction is repeated across time and regulated by the Vickrey-Clarke-Groves pricing mechanism. The objective of an MT subscribed to a particular WSP is to optimize the expected long-term transmit power in transmitting packets subject to a specific Quality-of-Service constraint. We formulate the problem as a multi-agent Markov decision process, where the subband allocation (SA) and packet scheduling decisions are a function of the global network state. To address the challenges of signalling overhead and computational complexity, we approximate the queue state-SA factor by the sum of per-MT queue state value functions, and derive an online localized algorithm to learn them. The presented experiments show significant performance gains from our proposed studies.",
    author = "Xianfu Chen",
    year = "2019",
    month = "2",
    day = "21",
    doi = "10.1109/GLOCOMW.2018.8644407",
    language = "English",
    booktitle = "2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    Chen, X 2019, Learning to Schedule Resources in Software-Defined Radio Access Networks. in 2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018 IEEE Globecom Workshops, GC Wkhps 2018, Abu Dhabi, United Arab Emirates, 9/12/18. https://doi.org/10.1109/GLOCOMW.2018.8644407

    Learning to Schedule Resources in Software-Defined Radio Access Networks. / Chen, Xianfu.

    2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019.

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    TY - GEN

    T1 - Learning to Schedule Resources in Software-Defined Radio Access Networks

    AU - Chen, Xianfu

    PY - 2019/2/21

    Y1 - 2019/2/21

    N2 - A software-defined control plane simplifies network operations in dense radio access networks (RANs) by abstracting the base stations as a logical centralized network controller (CNC). In a software-defined RAN, the CNC and the wireless service providers (WSPs) can thus be decoupled. The CNC allocates subbands to the mobile terminals (MTs) based on their submitted bids. Such an auction is repeated across time and regulated by the Vickrey-Clarke-Groves pricing mechanism. The objective of an MT subscribed to a particular WSP is to optimize the expected long-term transmit power in transmitting packets subject to a specific Quality-of-Service constraint. We formulate the problem as a multi-agent Markov decision process, where the subband allocation (SA) and packet scheduling decisions are a function of the global network state. To address the challenges of signalling overhead and computational complexity, we approximate the queue state-SA factor by the sum of per-MT queue state value functions, and derive an online localized algorithm to learn them. The presented experiments show significant performance gains from our proposed studies.

    AB - A software-defined control plane simplifies network operations in dense radio access networks (RANs) by abstracting the base stations as a logical centralized network controller (CNC). In a software-defined RAN, the CNC and the wireless service providers (WSPs) can thus be decoupled. The CNC allocates subbands to the mobile terminals (MTs) based on their submitted bids. Such an auction is repeated across time and regulated by the Vickrey-Clarke-Groves pricing mechanism. The objective of an MT subscribed to a particular WSP is to optimize the expected long-term transmit power in transmitting packets subject to a specific Quality-of-Service constraint. We formulate the problem as a multi-agent Markov decision process, where the subband allocation (SA) and packet scheduling decisions are a function of the global network state. To address the challenges of signalling overhead and computational complexity, we approximate the queue state-SA factor by the sum of per-MT queue state value functions, and derive an online localized algorithm to learn them. The presented experiments show significant performance gains from our proposed studies.

    UR - http://www.scopus.com/inward/record.url?scp=85063435702&partnerID=8YFLogxK

    U2 - 10.1109/GLOCOMW.2018.8644407

    DO - 10.1109/GLOCOMW.2018.8644407

    M3 - Conference article in proceedings

    AN - SCOPUS:85063435702

    BT - 2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -

    Chen X. Learning to Schedule Resources in Software-Defined Radio Access Networks. In 2018 IEEE Globecom Workshops, GC Wkshps 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019 https://doi.org/10.1109/GLOCOMW.2018.8644407