“…It is worth noting that power systems parameters often feature sharply variable non-stationary behaviour, which limits the efficiency of the stated technologies for forecasting of time series. Studies have shown that hybrid approaches, that is a combination of different intelligent techniques, have great potential and are worth pursuing [29]. Previously, several hybrid forecasting approaches have been proposed, including ARIMA-ANN models [1], Fuzzy-ANN-based models [14], Wavelet-ANN-based models [26], Fuzzyexpert system-based models [4] among others [6].…”