Cooperative load frequency control of generator and battery using a recurrent neural network

Takato Otani, Ryu Tanabe, Yui Koyanagi, Shinichi Iwamoto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    5 Citations (Scopus)


    A frequency issue is one of the concerns caused by renewable energies. There is a possibility of losing a balance of the demand and the supply followed by a frequency disturbance when large amounts of the renewable energies are introduced. As a countermeasure against the problem, storage battery systems for the load frequency control are beginning to be introduced. Batteries have faster response, because it is a power electronics equipment and does not have mechanical components. However, a state of the charge of the battery needs to be maintained in order to make efficient use of the battery. In this paper, in order to use the introduced storage battery effectively, a control by a recurrent neural network is proposed. Recently, neural networks are attracting attention as an innovative control method. By training the neural network with particle swarm optimization, the frequency of the power system and the state of the charge of the storage battery are maintained simultaneously.

    Original languageEnglish
    Title of host publicationTENCON 2017 - 2017 IEEE Region 10 Conference
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Number of pages6
    ISBN (Electronic)9781509011339
    Publication statusPublished - 2017 Dec 19
    Event2017 IEEE Region 10 Conference, TENCON 2017 - Penang, Malaysia
    Duration: 2017 Nov 52017 Nov 8


    Other2017 IEEE Region 10 Conference, TENCON 2017


    • battery
    • load frequency control
    • machine learning
    • power system
    • renewable energy
    • state of charge

    ASJC Scopus subject areas

    • Computer Science Applications
    • Electrical and Electronic Engineering


    Dive into the research topics of 'Cooperative load frequency control of generator and battery using a recurrent neural network'. Together they form a unique fingerprint.

    Cite this