Transient stability multi swing step-out prediction with online data mining

Takuya Omi, Hiroto Kakisaka, Shinichi Iwamoto

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    Recently, electric power systems become more complex and that makes it more difficult to control power systems. Due to development of WAMS(Wide Area Measurement System), power system data are available online. In this paper, we propose a novel method that can predict transient stability multi swing step-out using anomaly detection with data mining. Especially we focus our attention on the theory of ChangeFinder which uses SDAR algorithm and the two step learning model. The forgetting parameter r used in SDAR is set by supervised learning. Active powers obtained by transient stability simulations are inputted to ChangeFinder and the proposed method can detect multi swing step-out. We verify the validity of the proposed method by simulations on the IEEJ 10 machine 47 bus-system.

    Original languageEnglish
    Pages (from-to)137-144
    Number of pages8
    JournalIEEJ Transactions on Power and Energy
    Volume136
    Issue number2
    DOIs
    Publication statusPublished - 2016

    Fingerprint

    Data mining
    Electric power system measurement
    Supervised learning
    Electric power systems
    Power control

    Keywords

    • Anomaly detection
    • Data mining
    • Multi swing step-out
    • Online analysis
    • Transient stability
    • Wide area measurement system

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Energy Engineering and Power Technology

    Cite this

    Transient stability multi swing step-out prediction with online data mining. / Omi, Takuya; Kakisaka, Hiroto; Iwamoto, Shinichi.

    In: IEEJ Transactions on Power and Energy, Vol. 136, No. 2, 2016, p. 137-144.

    Research output: Contribution to journalArticle

    Omi, Takuya ; Kakisaka, Hiroto ; Iwamoto, Shinichi. / Transient stability multi swing step-out prediction with online data mining. In: IEEJ Transactions on Power and Energy. 2016 ; Vol. 136, No. 2. pp. 137-144.
    @article{a7068bba1a8044238c2784f3a97fb4be,
    title = "Transient stability multi swing step-out prediction with online data mining",
    abstract = "Recently, electric power systems become more complex and that makes it more difficult to control power systems. Due to development of WAMS(Wide Area Measurement System), power system data are available online. In this paper, we propose a novel method that can predict transient stability multi swing step-out using anomaly detection with data mining. Especially we focus our attention on the theory of ChangeFinder which uses SDAR algorithm and the two step learning model. The forgetting parameter r used in SDAR is set by supervised learning. Active powers obtained by transient stability simulations are inputted to ChangeFinder and the proposed method can detect multi swing step-out. We verify the validity of the proposed method by simulations on the IEEJ 10 machine 47 bus-system.",
    keywords = "Anomaly detection, Data mining, Multi swing step-out, Online analysis, Transient stability, Wide area measurement system",
    author = "Takuya Omi and Hiroto Kakisaka and Shinichi Iwamoto",
    year = "2016",
    doi = "10.1541/ieejpes.136.137",
    language = "English",
    volume = "136",
    pages = "137--144",
    journal = "IEEJ Transactions on Power and Energy",
    issn = "0385-4213",
    publisher = "The Institute of Electrical Engineers of Japan",
    number = "2",

    }

    TY - JOUR

    T1 - Transient stability multi swing step-out prediction with online data mining

    AU - Omi, Takuya

    AU - Kakisaka, Hiroto

    AU - Iwamoto, Shinichi

    PY - 2016

    Y1 - 2016

    N2 - Recently, electric power systems become more complex and that makes it more difficult to control power systems. Due to development of WAMS(Wide Area Measurement System), power system data are available online. In this paper, we propose a novel method that can predict transient stability multi swing step-out using anomaly detection with data mining. Especially we focus our attention on the theory of ChangeFinder which uses SDAR algorithm and the two step learning model. The forgetting parameter r used in SDAR is set by supervised learning. Active powers obtained by transient stability simulations are inputted to ChangeFinder and the proposed method can detect multi swing step-out. We verify the validity of the proposed method by simulations on the IEEJ 10 machine 47 bus-system.

    AB - Recently, electric power systems become more complex and that makes it more difficult to control power systems. Due to development of WAMS(Wide Area Measurement System), power system data are available online. In this paper, we propose a novel method that can predict transient stability multi swing step-out using anomaly detection with data mining. Especially we focus our attention on the theory of ChangeFinder which uses SDAR algorithm and the two step learning model. The forgetting parameter r used in SDAR is set by supervised learning. Active powers obtained by transient stability simulations are inputted to ChangeFinder and the proposed method can detect multi swing step-out. We verify the validity of the proposed method by simulations on the IEEJ 10 machine 47 bus-system.

    KW - Anomaly detection

    KW - Data mining

    KW - Multi swing step-out

    KW - Online analysis

    KW - Transient stability

    KW - Wide area measurement system

    UR - http://www.scopus.com/inward/record.url?scp=84958061107&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84958061107&partnerID=8YFLogxK

    U2 - 10.1541/ieejpes.136.137

    DO - 10.1541/ieejpes.136.137

    M3 - Article

    AN - SCOPUS:84958061107

    VL - 136

    SP - 137

    EP - 144

    JO - IEEJ Transactions on Power and Energy

    JF - IEEJ Transactions on Power and Energy

    SN - 0385-4213

    IS - 2

    ER -