Forecasting Electricity Demand in Turkey Using Optimization and Machine Learning Algorithms

Medium Neural Networks (MNN), Whale Optimization Algorithm (WAO), and Support Vector Machine (SVM) methods are frequently used in the literature for estimating electricity demand. The objective of this study was to make an estimation demand Turkey’s mainland with use mixed MNN, WAO, SVM. Imports, exports, gross domestic product (GDP), population data based on input from 1980 2019 Turkey, demands up 2040 forecasted as output value. performance analyzed using statistical error metrics Root Mean Square Error (RMSE), Absolute (MAE), R-squared, (MSE). correlation matrix utilized demonstrate relationship between actual calculated values dependent independent variables. p-value confidence interval analysis performed determine which method more effective. It observed that minimum RMSE, MSE, MAE errors 5.325 × 10−14, 28.35 10−28, 2.5 respectively. MNN showed strongest forecasting real among all applications tested.