Markov-decision-process-assisted consumer scheduling in a networked smart grid

Zhi Liu, Cheng Zhang, Mianxiong Dong, Bo Gu, Yusheng Ji, Yoshiaki Tanaka

    Research output: Contribution to journalArticle

    14 Citations (Scopus)

    Abstract

    Many recently built residential houses and factories are equipped with facilities for converting energy from green sources, such as solar energy, into electricity. Electricity consumers may input the extra electricity that they do not consume into the smart grid for sale, which is allowed by law in countries such as Japan. To reduce peak-time electricity usage, time-varying pricing schemes are usually adopted in smart grids, for both the electricity sold to consumers and the electricity purchased from consumers. Thanks to the development of cyber-physical systems and advanced technologies for communication and computation, current smart grids are typically networked, and it is possible to integrate information such as weather forecasts into such a networked smart grid. Thus, we can predict future levels of electricity generation (e.g., the energy from solar and wind sources, whose generation is predominantly affected by the weather) with high accuracy using this information and historical data. The key problem for consumers then becomes how to schedule their purchases from and sales to the networked smart grid to maximize their benefits by jointly considering the current storage status, time-varying pricing, and future electricity consumption and generation. This problem is non-trivial and is vitally important for improving smart grid utilization and attracting consumer investment in new energy generation systems, among other purposes. In this paper, we target such a networked smart grid system, in which future electricity generation is predicted with reasonable accuracy based on weather forecasts. We schedule consumers' behaviors using a Markov decision process model to optimize the consumers' net benefits. The results of extensive simulations show that the proposed scheme significantly outperforms the baseline competing scheme.

    Original languageEnglish
    Article number7739991
    Pages (from-to)2448-2458
    Number of pages11
    JournalIEEE Access
    Volume5
    DOIs
    Publication statusPublished - 2017

    Fingerprint

    Electricity
    Scheduling
    Sales
    Consumer behavior
    Solar energy
    Industrial plants
    Costs
    Communication

    Keywords

    • Markov decision process
    • scheduling algorithms
    • Smart grids
    • time-varying systems

    ASJC Scopus subject areas

    • Computer Science(all)
    • Materials Science(all)
    • Engineering(all)

    Cite this

    Markov-decision-process-assisted consumer scheduling in a networked smart grid. / Liu, Zhi; Zhang, Cheng; Dong, Mianxiong; Gu, Bo; Ji, Yusheng; Tanaka, Yoshiaki.

    In: IEEE Access, Vol. 5, 7739991, 2017, p. 2448-2458.

    Research output: Contribution to journalArticle

    Liu, Zhi ; Zhang, Cheng ; Dong, Mianxiong ; Gu, Bo ; Ji, Yusheng ; Tanaka, Yoshiaki. / Markov-decision-process-assisted consumer scheduling in a networked smart grid. In: IEEE Access. 2017 ; Vol. 5. pp. 2448-2458.
    @article{7f03513b03744bb88729ac577d74afcc,
    title = "Markov-decision-process-assisted consumer scheduling in a networked smart grid",
    abstract = "Many recently built residential houses and factories are equipped with facilities for converting energy from green sources, such as solar energy, into electricity. Electricity consumers may input the extra electricity that they do not consume into the smart grid for sale, which is allowed by law in countries such as Japan. To reduce peak-time electricity usage, time-varying pricing schemes are usually adopted in smart grids, for both the electricity sold to consumers and the electricity purchased from consumers. Thanks to the development of cyber-physical systems and advanced technologies for communication and computation, current smart grids are typically networked, and it is possible to integrate information such as weather forecasts into such a networked smart grid. Thus, we can predict future levels of electricity generation (e.g., the energy from solar and wind sources, whose generation is predominantly affected by the weather) with high accuracy using this information and historical data. The key problem for consumers then becomes how to schedule their purchases from and sales to the networked smart grid to maximize their benefits by jointly considering the current storage status, time-varying pricing, and future electricity consumption and generation. This problem is non-trivial and is vitally important for improving smart grid utilization and attracting consumer investment in new energy generation systems, among other purposes. In this paper, we target such a networked smart grid system, in which future electricity generation is predicted with reasonable accuracy based on weather forecasts. We schedule consumers' behaviors using a Markov decision process model to optimize the consumers' net benefits. The results of extensive simulations show that the proposed scheme significantly outperforms the baseline competing scheme.",
    keywords = "Markov decision process, scheduling algorithms, Smart grids, time-varying systems",
    author = "Zhi Liu and Cheng Zhang and Mianxiong Dong and Bo Gu and Yusheng Ji and Yoshiaki Tanaka",
    year = "2017",
    doi = "10.1109/ACCESS.2016.2620341",
    language = "English",
    volume = "5",
    pages = "2448--2458",
    journal = "IEEE Access",
    issn = "2169-3536",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - JOUR

    T1 - Markov-decision-process-assisted consumer scheduling in a networked smart grid

    AU - Liu, Zhi

    AU - Zhang, Cheng

    AU - Dong, Mianxiong

    AU - Gu, Bo

    AU - Ji, Yusheng

    AU - Tanaka, Yoshiaki

    PY - 2017

    Y1 - 2017

    N2 - Many recently built residential houses and factories are equipped with facilities for converting energy from green sources, such as solar energy, into electricity. Electricity consumers may input the extra electricity that they do not consume into the smart grid for sale, which is allowed by law in countries such as Japan. To reduce peak-time electricity usage, time-varying pricing schemes are usually adopted in smart grids, for both the electricity sold to consumers and the electricity purchased from consumers. Thanks to the development of cyber-physical systems and advanced technologies for communication and computation, current smart grids are typically networked, and it is possible to integrate information such as weather forecasts into such a networked smart grid. Thus, we can predict future levels of electricity generation (e.g., the energy from solar and wind sources, whose generation is predominantly affected by the weather) with high accuracy using this information and historical data. The key problem for consumers then becomes how to schedule their purchases from and sales to the networked smart grid to maximize their benefits by jointly considering the current storage status, time-varying pricing, and future electricity consumption and generation. This problem is non-trivial and is vitally important for improving smart grid utilization and attracting consumer investment in new energy generation systems, among other purposes. In this paper, we target such a networked smart grid system, in which future electricity generation is predicted with reasonable accuracy based on weather forecasts. We schedule consumers' behaviors using a Markov decision process model to optimize the consumers' net benefits. The results of extensive simulations show that the proposed scheme significantly outperforms the baseline competing scheme.

    AB - Many recently built residential houses and factories are equipped with facilities for converting energy from green sources, such as solar energy, into electricity. Electricity consumers may input the extra electricity that they do not consume into the smart grid for sale, which is allowed by law in countries such as Japan. To reduce peak-time electricity usage, time-varying pricing schemes are usually adopted in smart grids, for both the electricity sold to consumers and the electricity purchased from consumers. Thanks to the development of cyber-physical systems and advanced technologies for communication and computation, current smart grids are typically networked, and it is possible to integrate information such as weather forecasts into such a networked smart grid. Thus, we can predict future levels of electricity generation (e.g., the energy from solar and wind sources, whose generation is predominantly affected by the weather) with high accuracy using this information and historical data. The key problem for consumers then becomes how to schedule their purchases from and sales to the networked smart grid to maximize their benefits by jointly considering the current storage status, time-varying pricing, and future electricity consumption and generation. This problem is non-trivial and is vitally important for improving smart grid utilization and attracting consumer investment in new energy generation systems, among other purposes. In this paper, we target such a networked smart grid system, in which future electricity generation is predicted with reasonable accuracy based on weather forecasts. We schedule consumers' behaviors using a Markov decision process model to optimize the consumers' net benefits. The results of extensive simulations show that the proposed scheme significantly outperforms the baseline competing scheme.

    KW - Markov decision process

    KW - scheduling algorithms

    KW - Smart grids

    KW - time-varying systems

    UR - http://www.scopus.com/inward/record.url?scp=85017637064&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85017637064&partnerID=8YFLogxK

    U2 - 10.1109/ACCESS.2016.2620341

    DO - 10.1109/ACCESS.2016.2620341

    M3 - Article

    VL - 5

    SP - 2448

    EP - 2458

    JO - IEEE Access

    JF - IEEE Access

    SN - 2169-3536

    M1 - 7739991

    ER -