Long-term load forecasting using improved recurrent neural network

Yasuhiro Hayashi, Shinichi Iwamoto

    Research output: Contribution to journalArticle

    7 Citations (Scopus)

    Abstract

    In general, electric power companies must prepare power supply capability for maximum electric load demand because it is very difficult at present to store electric power. It takes several years and requires a great amount of money to construct power generation and transmission facilities. Therefore, it is necessary to forecast long-term load demand exactly in order to plan or operate power systems efficiently. Several methods have been investigated so far for the long-term load forecasting. However, because the electric loads consist of many complex factors, good forecasting has been very difficult. This paper proposes a long-term load forecasting method using a recurrent neural network (RNN). This is a mutually connected network that has the ability of learning patterns and past records. In general, when interpolation is used for unlearned data sets, the neural network provides reasonably good outputs. However, when extrapolation is used, such as in long-term load forecasting, some kind of tunings have been necessary to obtain good results. Therefore, to solve the problem, a method is proposed in which growth rates are used as input and output data. Using the proposed method, successful results have been obtained and comparisons have been made with the conventional methods.

    Original languageEnglish
    Pages (from-to)41-54
    Number of pages14
    JournalElectrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)
    Volume114
    Issue number8
    Publication statusPublished - 1994 Jan 1

    Fingerprint

    Recurrent neural networks
    Electric loads
    Power transmission
    Extrapolation
    Power generation
    Interpolation
    Tuning
    Neural networks
    Industry

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering

    Cite this

    Long-term load forecasting using improved recurrent neural network. / Hayashi, Yasuhiro; Iwamoto, Shinichi.

    In: Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi), Vol. 114, No. 8, 01.01.1994, p. 41-54.

    Research output: Contribution to journalArticle

    @article{9bd9ece9370e4188b468800d0ae89a2c,
    title = "Long-term load forecasting using improved recurrent neural network",
    abstract = "In general, electric power companies must prepare power supply capability for maximum electric load demand because it is very difficult at present to store electric power. It takes several years and requires a great amount of money to construct power generation and transmission facilities. Therefore, it is necessary to forecast long-term load demand exactly in order to plan or operate power systems efficiently. Several methods have been investigated so far for the long-term load forecasting. However, because the electric loads consist of many complex factors, good forecasting has been very difficult. This paper proposes a long-term load forecasting method using a recurrent neural network (RNN). This is a mutually connected network that has the ability of learning patterns and past records. In general, when interpolation is used for unlearned data sets, the neural network provides reasonably good outputs. However, when extrapolation is used, such as in long-term load forecasting, some kind of tunings have been necessary to obtain good results. Therefore, to solve the problem, a method is proposed in which growth rates are used as input and output data. Using the proposed method, successful results have been obtained and comparisons have been made with the conventional methods.",
    author = "Yasuhiro Hayashi and Shinichi Iwamoto",
    year = "1994",
    month = "1",
    day = "1",
    language = "English",
    volume = "114",
    pages = "41--54",
    journal = "Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)",
    issn = "0424-7760",
    publisher = "John Wiley and Sons Inc.",
    number = "8",

    }

    TY - JOUR

    T1 - Long-term load forecasting using improved recurrent neural network

    AU - Hayashi, Yasuhiro

    AU - Iwamoto, Shinichi

    PY - 1994/1/1

    Y1 - 1994/1/1

    N2 - In general, electric power companies must prepare power supply capability for maximum electric load demand because it is very difficult at present to store electric power. It takes several years and requires a great amount of money to construct power generation and transmission facilities. Therefore, it is necessary to forecast long-term load demand exactly in order to plan or operate power systems efficiently. Several methods have been investigated so far for the long-term load forecasting. However, because the electric loads consist of many complex factors, good forecasting has been very difficult. This paper proposes a long-term load forecasting method using a recurrent neural network (RNN). This is a mutually connected network that has the ability of learning patterns and past records. In general, when interpolation is used for unlearned data sets, the neural network provides reasonably good outputs. However, when extrapolation is used, such as in long-term load forecasting, some kind of tunings have been necessary to obtain good results. Therefore, to solve the problem, a method is proposed in which growth rates are used as input and output data. Using the proposed method, successful results have been obtained and comparisons have been made with the conventional methods.

    AB - In general, electric power companies must prepare power supply capability for maximum electric load demand because it is very difficult at present to store electric power. It takes several years and requires a great amount of money to construct power generation and transmission facilities. Therefore, it is necessary to forecast long-term load demand exactly in order to plan or operate power systems efficiently. Several methods have been investigated so far for the long-term load forecasting. However, because the electric loads consist of many complex factors, good forecasting has been very difficult. This paper proposes a long-term load forecasting method using a recurrent neural network (RNN). This is a mutually connected network that has the ability of learning patterns and past records. In general, when interpolation is used for unlearned data sets, the neural network provides reasonably good outputs. However, when extrapolation is used, such as in long-term load forecasting, some kind of tunings have been necessary to obtain good results. Therefore, to solve the problem, a method is proposed in which growth rates are used as input and output data. Using the proposed method, successful results have been obtained and comparisons have been made with the conventional methods.

    UR - http://www.scopus.com/inward/record.url?scp=0028706722&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0028706722&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:0028706722

    VL - 114

    SP - 41

    EP - 54

    JO - Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)

    JF - Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)

    SN - 0424-7760

    IS - 8

    ER -