BIROn - Birkbeck Institutional Research Online

    A hybrid model for forecasting short-term electricity demand

    Athanasopoulou, Maria Eleni and Deveikyte, Justina and Mosca, Alan and Peri, Ilaria and Provetti, Alessandro (2021) A hybrid model for forecasting short-term electricity demand. In: 2nd ACM International Conference on AI in Finance, 03-05 Nov 2021, London, UK. (In Press)

    This is the latest version of this item.

    Hyena__Hybrid_Energy_Analyser.pdf - Author's Accepted Manuscript

    Download (622kB) | Preview


    Currently the UK Electric market is guided by load (demand) forecasts published every thirty minutes by the regulator. A key factor in predicting demand is weather conditions, with forecasts published every hour. We present HYENA: a hybrid predictive model that combines feature engineering (selection of the candidate predictor features), mobile-window predictors and finally LSTM encoder-decoders to achieve higher accuracy with respect to mainstream models from the literature. HYENA decreased MAPE loss by 16% and RMSE loss by 10% over the best available benchmark model, thus establishing a new state of the art for the UK electric load (and price) forecasting.


    Item Type: Conference or Workshop Item (Paper)
    Keyword(s) / Subject(s): Hybrid models, Neural Networks, Regression, Feature Engineering
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    School of Business, Economics & Informatics > Economics, Mathematics and Statistics
    Depositing User: Alessandro Provetti
    Date Deposited: 25 Jan 2022 18:16
    Last Modified: 29 Jan 2022 20:07

    Available Versions of this Item

    • A hybrid model for forecasting short-term electricity demand. (deposited 25 Jan 2022 18:16) [Currently Displayed]


    Activity Overview
    6 month trend
    6 month trend

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item