Investigation of Electric Load Forecasting Methods: A Weka Application (Regression and Optimization)

Electric load forecasting plays an important role in the planning of power systems. Therefore, it is necessary to develop effective and simple electric load forecasting methods. In this study, a simple and effective method for short-term load forecasting was developed. In the developed method, the highest success with the least input features was aimed. The regression feature of the Random Forest (RF) algorithm and the Correlation Attribute Eval (CAE) feature selection method were used to achieve this. The simulation results proved that the proposed method was successful. While WEKA program was used for RF and CAE algorithms, real-time data was obtained from Spain.