Optimizing Short Term Load Forecast: A study on Machine Learning Model Accuracy and Predictor Selection

This paper focuses on the importance of choosing the proper predictors when training a Machine Learning model for Short Term Load Forecasting, as well as to demonstrate the usefulness of Machine Learning in the field of power load forecasting. For the goals of the study, a correlation analysis was performed in order to observe the impact of some factors on the changes of power consumption. In addition, a number of models were created using machine learning where combinations of predictors were used based on their correlation to power load. The performance of these models was evaluated and the results are shown in this paper.