Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids

Nowadays, electric load forecasting through a data analytic approach has become one of the most active and emerging research areas. It provides future consumption patterns load. Since there are large fluctuations in both electricity production use, it is difficult task to achieve balance between demand. By analyzing past records estimate upcoming load, issue fluctuating behavior can be resolved. In this study, framework for feature selection, extraction, regression put forward carry out prediction. The selection phase uses combination extreme gradient boosting (XGB) random forest (RF) determine significance each feature. Redundant features extraction removed by applying recursive elimination (RFE). We propose an enhanced support vector machine (ESVM) convolutional neural network (ECNN) component. Hyperparameters proposed approaches set using search (RS) technique. To illustrate effectiveness our strategies, comparison also performed state-of-the-art techniques. addition, we perform statistical analyses prove approaches. Simulation findings that ECNN ESVM higher accuracies 98.83% 98.7%, respectively.