A hybrid model for forecasting the consumption of electrical energy in a smart grid
Felix Ghislain Yem Souhe, Camille Franklin Mbey, Alexandre Teplaira Boum, Pierre Ele, Vinny Junior Foba Kakeu
Abstract
Abstract This paper develops a novel hybrid model for forecasting electrical consumption based on several deep learning and optimization models such as Support Vector Regression (SVR), Firefly Algorithm (FA) and Adaptive Neuro‐Fuzzy Inference System (ANFIS). The process is focused on the minimization of error and risk. FA is used to optimize the forecasting performance using its higher optimization ability. The proposed SVR‐FA‐ANFIS model is based on historical data from smart meters in order to estimate and improve the accuracy of forecasting electrical consumption. Several accuracy coefficients such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used to characterize the superior performance of the proposed model. The consumption data in Cameroon over the 24‐year period are used to evaluate the performance of the models. The simulation results show that the proposed method outperforms other models such as Long Short‐Term Memory (LSTM) and Random Forest (RF).