A solution method of unit commitment by artificial neural networks

Hiroshi Sasaki, Masahiro Watanabe, Junji Kubokawa, Naoto Yorino, Ryuichi Yokoyama

    Research output: Contribution to journalArticle

    167 Citations (Scopus)

    Abstract

    The authors explore the possibility of applying the Hopfield neural network to combinatorial optimization problems in power systems, in particular to unit commitment. A large number of inequality constraints included in unit commitment can be handled by dedicated neural networks. As an exact mapping of the problem onto the neural network is impossible with the state of the art, a two-step solution method was developed. First, generators to be stored up at each period are determined by the network, and then their outputs are adjusted by a conventional algorithm. The proposed neural network could solve a large-scale unit commitment problem with 30 generators over 24 periods, and results obtained were very encouraging.

    Original languageEnglish
    Pages (from-to)974-981
    Number of pages8
    JournalIEEE Transactions on Power Systems
    Volume7
    Issue number3
    DOIs
    Publication statusPublished - 1992 Aug

    Fingerprint

    Neural networks
    Hopfield neural networks
    Combinatorial optimization

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering

    Cite this

    Sasaki, H., Watanabe, M., Kubokawa, J., Yorino, N., & Yokoyama, R. (1992). A solution method of unit commitment by artificial neural networks. IEEE Transactions on Power Systems, 7(3), 974-981. https://doi.org/10.1109/59.207310

    A solution method of unit commitment by artificial neural networks. / Sasaki, Hiroshi; Watanabe, Masahiro; Kubokawa, Junji; Yorino, Naoto; Yokoyama, Ryuichi.

    In: IEEE Transactions on Power Systems, Vol. 7, No. 3, 08.1992, p. 974-981.

    Research output: Contribution to journalArticle

    Sasaki, H, Watanabe, M, Kubokawa, J, Yorino, N & Yokoyama, R 1992, 'A solution method of unit commitment by artificial neural networks', IEEE Transactions on Power Systems, vol. 7, no. 3, pp. 974-981. https://doi.org/10.1109/59.207310
    Sasaki, Hiroshi ; Watanabe, Masahiro ; Kubokawa, Junji ; Yorino, Naoto ; Yokoyama, Ryuichi. / A solution method of unit commitment by artificial neural networks. In: IEEE Transactions on Power Systems. 1992 ; Vol. 7, No. 3. pp. 974-981.
    @article{d232eee174044403b4b6389e0c5533c7,
    title = "A solution method of unit commitment by artificial neural networks",
    abstract = "The authors explore the possibility of applying the Hopfield neural network to combinatorial optimization problems in power systems, in particular to unit commitment. A large number of inequality constraints included in unit commitment can be handled by dedicated neural networks. As an exact mapping of the problem onto the neural network is impossible with the state of the art, a two-step solution method was developed. First, generators to be stored up at each period are determined by the network, and then their outputs are adjusted by a conventional algorithm. The proposed neural network could solve a large-scale unit commitment problem with 30 generators over 24 periods, and results obtained were very encouraging.",
    author = "Hiroshi Sasaki and Masahiro Watanabe and Junji Kubokawa and Naoto Yorino and Ryuichi Yokoyama",
    year = "1992",
    month = "8",
    doi = "10.1109/59.207310",
    language = "English",
    volume = "7",
    pages = "974--981",
    journal = "IEEE Transactions on Power Systems",
    issn = "0885-8950",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "3",

    }

    TY - JOUR

    T1 - A solution method of unit commitment by artificial neural networks

    AU - Sasaki, Hiroshi

    AU - Watanabe, Masahiro

    AU - Kubokawa, Junji

    AU - Yorino, Naoto

    AU - Yokoyama, Ryuichi

    PY - 1992/8

    Y1 - 1992/8

    N2 - The authors explore the possibility of applying the Hopfield neural network to combinatorial optimization problems in power systems, in particular to unit commitment. A large number of inequality constraints included in unit commitment can be handled by dedicated neural networks. As an exact mapping of the problem onto the neural network is impossible with the state of the art, a two-step solution method was developed. First, generators to be stored up at each period are determined by the network, and then their outputs are adjusted by a conventional algorithm. The proposed neural network could solve a large-scale unit commitment problem with 30 generators over 24 periods, and results obtained were very encouraging.

    AB - The authors explore the possibility of applying the Hopfield neural network to combinatorial optimization problems in power systems, in particular to unit commitment. A large number of inequality constraints included in unit commitment can be handled by dedicated neural networks. As an exact mapping of the problem onto the neural network is impossible with the state of the art, a two-step solution method was developed. First, generators to be stored up at each period are determined by the network, and then their outputs are adjusted by a conventional algorithm. The proposed neural network could solve a large-scale unit commitment problem with 30 generators over 24 periods, and results obtained were very encouraging.

    UR - http://www.scopus.com/inward/record.url?scp=0026908034&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0026908034&partnerID=8YFLogxK

    U2 - 10.1109/59.207310

    DO - 10.1109/59.207310

    M3 - Article

    VL - 7

    SP - 974

    EP - 981

    JO - IEEE Transactions on Power Systems

    JF - IEEE Transactions on Power Systems

    SN - 0885-8950

    IS - 3

    ER -