Bulus, KurtulusZor, Kasim2025-01-062025-01-062021978-1-6654-3649-610.1109/SIU53274.2021.94778692-s2.0-85111455449https://doi.org/10.1109/SIU53274.2021.9477869https://hdl.handle.net/20.500.14669/268029th IEEE Conference on Signal Processing and Communications Applications (SIU) -- JUN 09-11, 2021 -- ELECTR NETWORKOver the last two decades, electric load forecasting has strengthened its significant role in electric power systems due to equalising the vital balance between generation and consumption of electrical energy for all actors of deregulated electricity markets. Artificial intelligence-based techniques are frequently used for short-term electric load forecasting owing to the abstruse nature of electric loads that can be influenced by a variety of factors. In this paper, a novel hybrid deep learning algorithm that combines GMDH and GRU networks is meticulously applied for one hour-ahead load forecasting of a large hospital complex. In the proposed algorithm, GMDH and GRU networks are employed for feature selection and prediction respectively. Consequently, the obtained results have demonstrated that the proposed algorithm is capable of reducing mean absolute percentage error by 12% and computational time by 5%.trinfo:eu-repo/semantics/closedAccessload forecastingdeep learningfeature selectiongroup method of data handling (GMDH)gated recurrent unit (GRU)Conference Object0WOS:000808100700298N/A