Hybrid model for short-term forecasting of loads and load control responses

Pekka Koponen, Harri Niska

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    2 Citations (Scopus)

    Abstract

    A hybrid model for short-term forecasting of aggregated thermal loads and their load control responses is studied in this paper using field test data. Inputs include temperature measurement and forecast, measured power and control signals. The hybrid model comprises 1) partly physically based forecasting of the responses of the controlled thermal loads and the non-controlled power, and 2) forecasting the residual using Support Vector Machine (SVM). Their summation gives the hourly interval power forecast. Here partly physically based means that the model structure models thermal dynamics of houses. The response forecasting needs as inputs the daily heating energy demand and controllable power range, which are forecast by partly physically based models. Weekly load pattern is used to forecast the non-controllable power. SVM forecasts the residual. Alternative configurations are compared. The response forecasting model improved the forecasting accuracy most and adding the SVM for the residual further improved the accuracy.
    Original languageEnglish
    Title of host publicationPES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE
    PublisherIEEE Institute of Electrical and Electronic Engineers
    Pages1-6
    ISBN (Electronic)978-1-5090-3358-4, 978-1-5090-3357-7
    ISBN (Print)978-1-5090-3359-1
    DOIs
    Publication statusPublished - 2 Jul 2016
    MoE publication typeA4 Article in a conference publication
    EventIEEE PES Innovative Smart Grid Technologies, Europe - Ljubljana, Slovenia
    Duration: 9 Oct 201612 Oct 2016

    Conference

    ConferenceIEEE PES Innovative Smart Grid Technologies, Europe
    Abbreviated titleISGT 2016
    CountrySlovenia
    CityLjubljana
    Period9/10/1612/10/16

    Fingerprint

    Support vector machines
    Thermal load
    Model structures
    Temperature measurement
    Heating
    Hot Temperature

    Keywords

    • demand response
    • forecasting
    • hybrid models
    • machine learning
    • physical models

    Cite this

    Koponen, P., & Niska, H. (2016). Hybrid model for short-term forecasting of loads and load control responses. In PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE (pp. 1-6). [7856320] IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ISGTEurope.2016.7856320
    Koponen, Pekka ; Niska, Harri. / Hybrid model for short-term forecasting of loads and load control responses. PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE . IEEE Institute of Electrical and Electronic Engineers , 2016. pp. 1-6
    @inproceedings{7eae71c11c0e4fa08791a51721157f4d,
    title = "Hybrid model for short-term forecasting of loads and load control responses",
    abstract = "A hybrid model for short-term forecasting of aggregated thermal loads and their load control responses is studied in this paper using field test data. Inputs include temperature measurement and forecast, measured power and control signals. The hybrid model comprises 1) partly physically based forecasting of the responses of the controlled thermal loads and the non-controlled power, and 2) forecasting the residual using Support Vector Machine (SVM). Their summation gives the hourly interval power forecast. Here partly physically based means that the model structure models thermal dynamics of houses. The response forecasting needs as inputs the daily heating energy demand and controllable power range, which are forecast by partly physically based models. Weekly load pattern is used to forecast the non-controllable power. SVM forecasts the residual. Alternative configurations are compared. The response forecasting model improved the forecasting accuracy most and adding the SVM for the residual further improved the accuracy.",
    keywords = "demand response, forecasting, hybrid models, machine learning, physical models",
    author = "Pekka Koponen and Harri Niska",
    note = "SDA: MIP: Intelligent Energy Grids",
    year = "2016",
    month = "7",
    day = "2",
    doi = "10.1109/ISGTEurope.2016.7856320",
    language = "English",
    isbn = "978-1-5090-3359-1",
    pages = "1--6",
    booktitle = "PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE",
    publisher = "IEEE Institute of Electrical and Electronic Engineers",
    address = "United States",

    }

    Koponen, P & Niska, H 2016, Hybrid model for short-term forecasting of loads and load control responses. in PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE ., 7856320, IEEE Institute of Electrical and Electronic Engineers , pp. 1-6, IEEE PES Innovative Smart Grid Technologies, Europe, Ljubljana, Slovenia, 9/10/16. https://doi.org/10.1109/ISGTEurope.2016.7856320

    Hybrid model for short-term forecasting of loads and load control responses. / Koponen, Pekka; Niska, Harri.

    PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE . IEEE Institute of Electrical and Electronic Engineers , 2016. p. 1-6 7856320.

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    TY - GEN

    T1 - Hybrid model for short-term forecasting of loads and load control responses

    AU - Koponen, Pekka

    AU - Niska, Harri

    N1 - SDA: MIP: Intelligent Energy Grids

    PY - 2016/7/2

    Y1 - 2016/7/2

    N2 - A hybrid model for short-term forecasting of aggregated thermal loads and their load control responses is studied in this paper using field test data. Inputs include temperature measurement and forecast, measured power and control signals. The hybrid model comprises 1) partly physically based forecasting of the responses of the controlled thermal loads and the non-controlled power, and 2) forecasting the residual using Support Vector Machine (SVM). Their summation gives the hourly interval power forecast. Here partly physically based means that the model structure models thermal dynamics of houses. The response forecasting needs as inputs the daily heating energy demand and controllable power range, which are forecast by partly physically based models. Weekly load pattern is used to forecast the non-controllable power. SVM forecasts the residual. Alternative configurations are compared. The response forecasting model improved the forecasting accuracy most and adding the SVM for the residual further improved the accuracy.

    AB - A hybrid model for short-term forecasting of aggregated thermal loads and their load control responses is studied in this paper using field test data. Inputs include temperature measurement and forecast, measured power and control signals. The hybrid model comprises 1) partly physically based forecasting of the responses of the controlled thermal loads and the non-controlled power, and 2) forecasting the residual using Support Vector Machine (SVM). Their summation gives the hourly interval power forecast. Here partly physically based means that the model structure models thermal dynamics of houses. The response forecasting needs as inputs the daily heating energy demand and controllable power range, which are forecast by partly physically based models. Weekly load pattern is used to forecast the non-controllable power. SVM forecasts the residual. Alternative configurations are compared. The response forecasting model improved the forecasting accuracy most and adding the SVM for the residual further improved the accuracy.

    KW - demand response

    KW - forecasting

    KW - hybrid models

    KW - machine learning

    KW - physical models

    UR - http://www.scopus.com/inward/record.url?scp=85017561442&partnerID=8YFLogxK

    U2 - 10.1109/ISGTEurope.2016.7856320

    DO - 10.1109/ISGTEurope.2016.7856320

    M3 - Conference article in proceedings

    SN - 978-1-5090-3359-1

    SP - 1

    EP - 6

    BT - PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE

    PB - IEEE Institute of Electrical and Electronic Engineers

    ER -

    Koponen P, Niska H. Hybrid model for short-term forecasting of loads and load control responses. In PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2016 IEEE . IEEE Institute of Electrical and Electronic Engineers . 2016. p. 1-6. 7856320 https://doi.org/10.1109/ISGTEurope.2016.7856320