Massive MIMO power allocation in millimeter wave networks

Hang Liu, Chinh Tran, Jan Lasota, Son Dinh, Xianfu Chen, Feng Ouyang

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

    Abstract

    Massive multiple-input multiple-output (MMIMO) is a key technology for 5G mobile communication systems, which enables to simultaneously form and transmit multiple directional signal beams to multiple mobile terminals (MTs) on the same frequency channel with high array beamforming gains and throughput. One of the challenges in MMMIO beamforming is how to allocate the transmit power to multiple beams sent from a MMIMO base station to multiple MTs and schedule data transmissions, given heterogeneous traffic and channel conditions of multiple MTs. Furthermore, the statistics of users’ packet arrivals and channel states may not be known a priori and vary over time. In this paper, we propose a framework to optimize MMIMO beam power allocation and transmission scheduling in millimeter wave networks with time-varying traffic and channel conditions. The optimization problem is formulated as a Markov decision process (MDP) with the objective to minimize the overall queueing delay of multiple MTs by taking their heterogeneous and dynamic traffic and channel states into account. An online reinforcement learning scheme is designed which allows achieving the long-term optimal system performance with no requirement for a priori knowledge of user traffic statistics and wireless network states. Evaluation results show that our proposed scheme outperforms the state-of-the-art baselines.

    Original languageEnglish
    Title of host publicationWireless Algorithms, Systems, and Applications, WASA 2018
    PublisherSpringer
    Pages296-307
    Number of pages12
    ISBN (Electronic)978-3-319-94268-1
    ISBN (Print)978-3-319-94267-4
    DOIs
    Publication statusPublished - 1 Jan 2018
    MoE publication typeA4 Article in a conference publication
    Event13th International Conference on Wireless Algorithms, Systems, and Applications, WASA 2018 - Tianjin, China
    Duration: 20 Jun 201822 Jun 2018

    Publication series

    SeriesLecture Notes in Computer Science
    Volume10874
    ISSN0302-9743

    Conference

    Conference13th International Conference on Wireless Algorithms, Systems, and Applications, WASA 2018
    CountryChina
    CityTianjin
    Period20/06/1822/06/18

    Fingerprint

    Millimeter Wave
    Power Allocation
    Beamforming
    MIMO systems
    Millimeter waves
    Multiple-input multiple-output (MIMO)
    Telecommunication traffic
    Statistics
    Optimal systems
    Reinforcement learning
    Traffic
    Base stations
    Data communication systems
    Wireless networks
    Scheduling
    Throughput
    Traffic Dynamics
    Optimal System
    Online Learning
    Queueing

    Keywords

    • Dynamic networks
    • Machine learning
    • Markov decision process
    • Massive MIMO
    • Millimeter wave communications
    • Power allocation

    Cite this

    Liu, H., Tran, C., Lasota, J., Dinh, S., Chen, X., & Ouyang, F. (2018). Massive MIMO power allocation in millimeter wave networks. In Wireless Algorithms, Systems, and Applications, WASA 2018 (pp. 296-307). Springer. Lecture Notes in Computer Science, Vol.. 10874 https://doi.org/10.1007/978-3-319-94268-1_25
    Liu, Hang ; Tran, Chinh ; Lasota, Jan ; Dinh, Son ; Chen, Xianfu ; Ouyang, Feng. / Massive MIMO power allocation in millimeter wave networks. Wireless Algorithms, Systems, and Applications, WASA 2018. Springer, 2018. pp. 296-307 (Lecture Notes in Computer Science, Vol. 10874).
    @inproceedings{86e0a4777d614af58a96599a21c867e9,
    title = "Massive MIMO power allocation in millimeter wave networks",
    abstract = "Massive multiple-input multiple-output (MMIMO) is a key technology for 5G mobile communication systems, which enables to simultaneously form and transmit multiple directional signal beams to multiple mobile terminals (MTs) on the same frequency channel with high array beamforming gains and throughput. One of the challenges in MMMIO beamforming is how to allocate the transmit power to multiple beams sent from a MMIMO base station to multiple MTs and schedule data transmissions, given heterogeneous traffic and channel conditions of multiple MTs. Furthermore, the statistics of users’ packet arrivals and channel states may not be known a priori and vary over time. In this paper, we propose a framework to optimize MMIMO beam power allocation and transmission scheduling in millimeter wave networks with time-varying traffic and channel conditions. The optimization problem is formulated as a Markov decision process (MDP) with the objective to minimize the overall queueing delay of multiple MTs by taking their heterogeneous and dynamic traffic and channel states into account. An online reinforcement learning scheme is designed which allows achieving the long-term optimal system performance with no requirement for a priori knowledge of user traffic statistics and wireless network states. Evaluation results show that our proposed scheme outperforms the state-of-the-art baselines.",
    keywords = "Dynamic networks, Machine learning, Markov decision process, Massive MIMO, Millimeter wave communications, Power allocation",
    author = "Hang Liu and Chinh Tran and Jan Lasota and Son Dinh and Xianfu Chen and Feng Ouyang",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.1007/978-3-319-94268-1_25",
    language = "English",
    isbn = "978-3-319-94267-4",
    series = "Lecture Notes in Computer Science",
    publisher = "Springer",
    pages = "296--307",
    booktitle = "Wireless Algorithms, Systems, and Applications, WASA 2018",
    address = "Germany",

    }

    Liu, H, Tran, C, Lasota, J, Dinh, S, Chen, X & Ouyang, F 2018, Massive MIMO power allocation in millimeter wave networks. in Wireless Algorithms, Systems, and Applications, WASA 2018. Springer, Lecture Notes in Computer Science, vol. 10874, pp. 296-307, 13th International Conference on Wireless Algorithms, Systems, and Applications, WASA 2018, Tianjin, China, 20/06/18. https://doi.org/10.1007/978-3-319-94268-1_25

    Massive MIMO power allocation in millimeter wave networks. / Liu, Hang; Tran, Chinh; Lasota, Jan; Dinh, Son; Chen, Xianfu; Ouyang, Feng.

    Wireless Algorithms, Systems, and Applications, WASA 2018. Springer, 2018. p. 296-307 (Lecture Notes in Computer Science, Vol. 10874).

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

    TY - GEN

    T1 - Massive MIMO power allocation in millimeter wave networks

    AU - Liu, Hang

    AU - Tran, Chinh

    AU - Lasota, Jan

    AU - Dinh, Son

    AU - Chen, Xianfu

    AU - Ouyang, Feng

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - Massive multiple-input multiple-output (MMIMO) is a key technology for 5G mobile communication systems, which enables to simultaneously form and transmit multiple directional signal beams to multiple mobile terminals (MTs) on the same frequency channel with high array beamforming gains and throughput. One of the challenges in MMMIO beamforming is how to allocate the transmit power to multiple beams sent from a MMIMO base station to multiple MTs and schedule data transmissions, given heterogeneous traffic and channel conditions of multiple MTs. Furthermore, the statistics of users’ packet arrivals and channel states may not be known a priori and vary over time. In this paper, we propose a framework to optimize MMIMO beam power allocation and transmission scheduling in millimeter wave networks with time-varying traffic and channel conditions. The optimization problem is formulated as a Markov decision process (MDP) with the objective to minimize the overall queueing delay of multiple MTs by taking their heterogeneous and dynamic traffic and channel states into account. An online reinforcement learning scheme is designed which allows achieving the long-term optimal system performance with no requirement for a priori knowledge of user traffic statistics and wireless network states. Evaluation results show that our proposed scheme outperforms the state-of-the-art baselines.

    AB - Massive multiple-input multiple-output (MMIMO) is a key technology for 5G mobile communication systems, which enables to simultaneously form and transmit multiple directional signal beams to multiple mobile terminals (MTs) on the same frequency channel with high array beamforming gains and throughput. One of the challenges in MMMIO beamforming is how to allocate the transmit power to multiple beams sent from a MMIMO base station to multiple MTs and schedule data transmissions, given heterogeneous traffic and channel conditions of multiple MTs. Furthermore, the statistics of users’ packet arrivals and channel states may not be known a priori and vary over time. In this paper, we propose a framework to optimize MMIMO beam power allocation and transmission scheduling in millimeter wave networks with time-varying traffic and channel conditions. The optimization problem is formulated as a Markov decision process (MDP) with the objective to minimize the overall queueing delay of multiple MTs by taking their heterogeneous and dynamic traffic and channel states into account. An online reinforcement learning scheme is designed which allows achieving the long-term optimal system performance with no requirement for a priori knowledge of user traffic statistics and wireless network states. Evaluation results show that our proposed scheme outperforms the state-of-the-art baselines.

    KW - Dynamic networks

    KW - Machine learning

    KW - Markov decision process

    KW - Massive MIMO

    KW - Millimeter wave communications

    KW - Power allocation

    UR - http://www.scopus.com/inward/record.url?scp=85049054875&partnerID=8YFLogxK

    U2 - 10.1007/978-3-319-94268-1_25

    DO - 10.1007/978-3-319-94268-1_25

    M3 - Conference article in proceedings

    AN - SCOPUS:85049054875

    SN - 978-3-319-94267-4

    T3 - Lecture Notes in Computer Science

    SP - 296

    EP - 307

    BT - Wireless Algorithms, Systems, and Applications, WASA 2018

    PB - Springer

    ER -

    Liu H, Tran C, Lasota J, Dinh S, Chen X, Ouyang F. Massive MIMO power allocation in millimeter wave networks. In Wireless Algorithms, Systems, and Applications, WASA 2018. Springer. 2018. p. 296-307. (Lecture Notes in Computer Science, Vol. 10874). https://doi.org/10.1007/978-3-319-94268-1_25