Prediction errors and balancing costs for wind power production in Finland

Hannele Holttinen, Pirkko Saarikivi, Sami Repo, Jussi Ikäheimo, Göran Koreneff

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

    Abstract

    In Finland, as there is no feed-in tariff, the wind power producers have to make contracts on how the electricity is sold and also make contracts for balance settlement. For this paper, wind power production is estimated 1–38 hours ahead for wind turbines located in 4 small clusters about 380 km apart on the West coast of Finland. Wind speed forecasts from the very-high-resolution ETA meteorological forecast model run by Foreca Ltd are used together with two production forecast models, which employ neural networks developed by Cybersoft and time series modeling by VTT. To show the effect of even more spread wind power production in Finland, prediction errors are determined for both one site, one producer and for the whole West Coast of Finland. Balancing costs resulting from day-ahead forecasts are estimated with year 2004 price data. Some example weeks are taken to examine the possibilities of improving the meteorological prediction for wind speeds.
    Original languageEnglish
    Title of host publicationProceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms
    Subtitle of host publicationDelft, Netherland, 26-28 October 2006
    Pages113-120
    Publication statusPublished - 2006
    MoE publication typeA4 Article in a conference publication

    Fingerprint

    wind power
    prediction
    cost
    wind velocity
    coast
    wind turbine
    electricity
    time series
    forecast
    modeling
    contract

    Keywords

    • Forecasting
    • neural network applications
    • time series
    • wind energy
    • weather forecasting
    • electricity markets
    • balancing costs

    Cite this

    Holttinen, H., Saarikivi, P., Repo, S., Ikäheimo, J., & Koreneff, G. (2006). Prediction errors and balancing costs for wind power production in Finland. In Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms: Delft, Netherland, 26-28 October 2006 (pp. 113-120)
    Holttinen, Hannele ; Saarikivi, Pirkko ; Repo, Sami ; Ikäheimo, Jussi ; Koreneff, Göran. / Prediction errors and balancing costs for wind power production in Finland. Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms: Delft, Netherland, 26-28 October 2006. 2006. pp. 113-120
    @inproceedings{f20e18b4073740c2b7d898eb6f7427d0,
    title = "Prediction errors and balancing costs for wind power production in Finland",
    abstract = "In Finland, as there is no feed-in tariff, the wind power producers have to make contracts on how the electricity is sold and also make contracts for balance settlement. For this paper, wind power production is estimated 1–38 hours ahead for wind turbines located in 4 small clusters about 380 km apart on the West coast of Finland. Wind speed forecasts from the very-high-resolution ETA meteorological forecast model run by Foreca Ltd are used together with two production forecast models, which employ neural networks developed by Cybersoft and time series modeling by VTT. To show the effect of even more spread wind power production in Finland, prediction errors are determined for both one site, one producer and for the whole West Coast of Finland. Balancing costs resulting from day-ahead forecasts are estimated with year 2004 price data. Some example weeks are taken to examine the possibilities of improving the meteorological prediction for wind speeds.",
    keywords = "Forecasting, neural network applications, time series, wind energy, weather forecasting, electricity markets, balancing costs",
    author = "Hannele Holttinen and Pirkko Saarikivi and Sami Repo and Jussi Ik{\"a}heimo and G{\"o}ran Koreneff",
    year = "2006",
    language = "English",
    pages = "113--120",
    booktitle = "Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms",

    }

    Holttinen, H, Saarikivi, P, Repo, S, Ikäheimo, J & Koreneff, G 2006, Prediction errors and balancing costs for wind power production in Finland. in Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms: Delft, Netherland, 26-28 October 2006. pp. 113-120.

    Prediction errors and balancing costs for wind power production in Finland. / Holttinen, Hannele; Saarikivi, Pirkko; Repo, Sami; Ikäheimo, Jussi; Koreneff, Göran.

    Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms: Delft, Netherland, 26-28 October 2006. 2006. p. 113-120.

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

    TY - GEN

    T1 - Prediction errors and balancing costs for wind power production in Finland

    AU - Holttinen, Hannele

    AU - Saarikivi, Pirkko

    AU - Repo, Sami

    AU - Ikäheimo, Jussi

    AU - Koreneff, Göran

    PY - 2006

    Y1 - 2006

    N2 - In Finland, as there is no feed-in tariff, the wind power producers have to make contracts on how the electricity is sold and also make contracts for balance settlement. For this paper, wind power production is estimated 1–38 hours ahead for wind turbines located in 4 small clusters about 380 km apart on the West coast of Finland. Wind speed forecasts from the very-high-resolution ETA meteorological forecast model run by Foreca Ltd are used together with two production forecast models, which employ neural networks developed by Cybersoft and time series modeling by VTT. To show the effect of even more spread wind power production in Finland, prediction errors are determined for both one site, one producer and for the whole West Coast of Finland. Balancing costs resulting from day-ahead forecasts are estimated with year 2004 price data. Some example weeks are taken to examine the possibilities of improving the meteorological prediction for wind speeds.

    AB - In Finland, as there is no feed-in tariff, the wind power producers have to make contracts on how the electricity is sold and also make contracts for balance settlement. For this paper, wind power production is estimated 1–38 hours ahead for wind turbines located in 4 small clusters about 380 km apart on the West coast of Finland. Wind speed forecasts from the very-high-resolution ETA meteorological forecast model run by Foreca Ltd are used together with two production forecast models, which employ neural networks developed by Cybersoft and time series modeling by VTT. To show the effect of even more spread wind power production in Finland, prediction errors are determined for both one site, one producer and for the whole West Coast of Finland. Balancing costs resulting from day-ahead forecasts are estimated with year 2004 price data. Some example weeks are taken to examine the possibilities of improving the meteorological prediction for wind speeds.

    KW - Forecasting

    KW - neural network applications

    KW - time series

    KW - wind energy

    KW - weather forecasting

    KW - electricity markets

    KW - balancing costs

    M3 - Conference article in proceedings

    SP - 113

    EP - 120

    BT - Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms

    ER -

    Holttinen H, Saarikivi P, Repo S, Ikäheimo J, Koreneff G. Prediction errors and balancing costs for wind power production in Finland. In Proceedings of 6th International Workshop on Large-scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms: Delft, Netherland, 26-28 October 2006. 2006. p. 113-120