A learning approach for traffic offloading in stochastic heterogeneous cellular networks

Xianfu Chen, Celimuge Wu, Yifan Zhou, Honggang Zhang

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

    6 Citations (Scopus)

    Abstract

    This paper addresses energy-aware traffic offloading in stochastic heterogeneous cellular networks (HCNs). The objective is to minimize energy consumption of the HCN while maintaining Quality-of-Service experienced by the mobile users. For each cell, the energy consumption depends on its associated system load, which is coupled with system loads in other cells due to the sharing over a common spectrum band. Such a traffic offloading problem is modeled by a discrete-time Markov decision process (DTMDP). Based on the traffic observations and the traffic offloading operations, the network controller learns to solve the optimal traffic offloading strategy with no prior knowledge of the DTMDP statistics. To deal with the curse of dimensionality, we design a centralized Q-learning with compact state representation algorithm, which is named as QC-learning. Moreover, a decentralized QC-learning algorithm is developed such that the macro-cell base stations (BSs) can independently manage the operations of small-cell BSs by making use of the network information obtained from the network controller. Simulations validate the proposed studies.
    Original languageEnglish
    Title of host publicationCommunications (ICC), 2015 IEEE International Conference on
    PublisherIEEE Institute of Electrical and Electronic Engineers
    Pages3347-3351
    ISBN (Electronic)978-1-4673-6432-4, 978-1-4673-6431-7
    DOIs
    Publication statusPublished - 10 Sep 2015
    MoE publication typeA4 Article in a conference publication
    EventIEEE International Conference on Communications: Smart City & Smart World - London, United Kingdom
    Duration: 8 Jun 201512 Jun 2015

    Conference

    ConferenceIEEE International Conference on Communications
    Abbreviated titleICC
    CountryUnited Kingdom
    CityLondon
    Period8/06/1512/06/15

    Fingerprint

    Base stations
    Energy utilization
    Controllers
    Learning algorithms
    Macros
    Quality of service
    Statistics

    Keywords

    • heterogeneous cellular networks
    • HCN

    Cite this

    Chen, X., Wu, C., Zhou, Y., & Zhang, H. (2015). A learning approach for traffic offloading in stochastic heterogeneous cellular networks. In Communications (ICC), 2015 IEEE International Conference on (pp. 3347-3351). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ICC.2015.7248841
    Chen, Xianfu ; Wu, Celimuge ; Zhou, Yifan ; Zhang, Honggang. / A learning approach for traffic offloading in stochastic heterogeneous cellular networks. Communications (ICC), 2015 IEEE International Conference on. IEEE Institute of Electrical and Electronic Engineers , 2015. pp. 3347-3351
    @inproceedings{45276731973448ae913b5b6ca33713b8,
    title = "A learning approach for traffic offloading in stochastic heterogeneous cellular networks",
    abstract = "This paper addresses energy-aware traffic offloading in stochastic heterogeneous cellular networks (HCNs). The objective is to minimize energy consumption of the HCN while maintaining Quality-of-Service experienced by the mobile users. For each cell, the energy consumption depends on its associated system load, which is coupled with system loads in other cells due to the sharing over a common spectrum band. Such a traffic offloading problem is modeled by a discrete-time Markov decision process (DTMDP). Based on the traffic observations and the traffic offloading operations, the network controller learns to solve the optimal traffic offloading strategy with no prior knowledge of the DTMDP statistics. To deal with the curse of dimensionality, we design a centralized Q-learning with compact state representation algorithm, which is named as QC-learning. Moreover, a decentralized QC-learning algorithm is developed such that the macro-cell base stations (BSs) can independently manage the operations of small-cell BSs by making use of the network information obtained from the network controller. Simulations validate the proposed studies.",
    keywords = "heterogeneous cellular networks, HCN",
    author = "Xianfu Chen and Celimuge Wu and Yifan Zhou and Honggang Zhang",
    note = "Project : 101914",
    year = "2015",
    month = "9",
    day = "10",
    doi = "10.1109/ICC.2015.7248841",
    language = "English",
    pages = "3347--3351",
    booktitle = "Communications (ICC), 2015 IEEE International Conference on",
    publisher = "IEEE Institute of Electrical and Electronic Engineers",
    address = "United States",

    }

    Chen, X, Wu, C, Zhou, Y & Zhang, H 2015, A learning approach for traffic offloading in stochastic heterogeneous cellular networks. in Communications (ICC), 2015 IEEE International Conference on. IEEE Institute of Electrical and Electronic Engineers , pp. 3347-3351, IEEE International Conference on Communications, London, United Kingdom, 8/06/15. https://doi.org/10.1109/ICC.2015.7248841

    A learning approach for traffic offloading in stochastic heterogeneous cellular networks. / Chen, Xianfu; Wu, Celimuge; Zhou, Yifan; Zhang, Honggang.

    Communications (ICC), 2015 IEEE International Conference on. IEEE Institute of Electrical and Electronic Engineers , 2015. p. 3347-3351.

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

    TY - GEN

    T1 - A learning approach for traffic offloading in stochastic heterogeneous cellular networks

    AU - Chen, Xianfu

    AU - Wu, Celimuge

    AU - Zhou, Yifan

    AU - Zhang, Honggang

    N1 - Project : 101914

    PY - 2015/9/10

    Y1 - 2015/9/10

    N2 - This paper addresses energy-aware traffic offloading in stochastic heterogeneous cellular networks (HCNs). The objective is to minimize energy consumption of the HCN while maintaining Quality-of-Service experienced by the mobile users. For each cell, the energy consumption depends on its associated system load, which is coupled with system loads in other cells due to the sharing over a common spectrum band. Such a traffic offloading problem is modeled by a discrete-time Markov decision process (DTMDP). Based on the traffic observations and the traffic offloading operations, the network controller learns to solve the optimal traffic offloading strategy with no prior knowledge of the DTMDP statistics. To deal with the curse of dimensionality, we design a centralized Q-learning with compact state representation algorithm, which is named as QC-learning. Moreover, a decentralized QC-learning algorithm is developed such that the macro-cell base stations (BSs) can independently manage the operations of small-cell BSs by making use of the network information obtained from the network controller. Simulations validate the proposed studies.

    AB - This paper addresses energy-aware traffic offloading in stochastic heterogeneous cellular networks (HCNs). The objective is to minimize energy consumption of the HCN while maintaining Quality-of-Service experienced by the mobile users. For each cell, the energy consumption depends on its associated system load, which is coupled with system loads in other cells due to the sharing over a common spectrum band. Such a traffic offloading problem is modeled by a discrete-time Markov decision process (DTMDP). Based on the traffic observations and the traffic offloading operations, the network controller learns to solve the optimal traffic offloading strategy with no prior knowledge of the DTMDP statistics. To deal with the curse of dimensionality, we design a centralized Q-learning with compact state representation algorithm, which is named as QC-learning. Moreover, a decentralized QC-learning algorithm is developed such that the macro-cell base stations (BSs) can independently manage the operations of small-cell BSs by making use of the network information obtained from the network controller. Simulations validate the proposed studies.

    KW - heterogeneous cellular networks

    KW - HCN

    U2 - 10.1109/ICC.2015.7248841

    DO - 10.1109/ICC.2015.7248841

    M3 - Conference article in proceedings

    SP - 3347

    EP - 3351

    BT - Communications (ICC), 2015 IEEE International Conference on

    PB - IEEE Institute of Electrical and Electronic Engineers

    ER -

    Chen X, Wu C, Zhou Y, Zhang H. A learning approach for traffic offloading in stochastic heterogeneous cellular networks. In Communications (ICC), 2015 IEEE International Conference on. IEEE Institute of Electrical and Electronic Engineers . 2015. p. 3347-3351 https://doi.org/10.1109/ICC.2015.7248841