Intelligence based Accurate Medium and Long Term Load Forecasting System

In this study, we aim to provide an efficient load prediction system projected for different local feeders predict the Medium- and Long-term Load Forecasting. This model improves future requirements expansions, equipment retailing or staff recruiting electric utility company. We aimed improve ahead forecasting by using hybrid approach optimizing parameters of our models. used Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Multilayer perceptron (MLP) methods. Root Mean Square Error (RMSE), Absolute Percentage (MAPE), (MAE) squared error comparison. To 3 months forecasting, lowermost was acquired LSTM MAPE (2.70). For 6 prediction, MLP gives highest predictions with (2.36). Moreover, 9 has been attained in terms (2.37). Likewise, 1 years (2.25) yielded six (2.49) provided MLP. The proposed methods attain stable better performance forecasting. finding indicates that can be instigated expansion requirements.