A Comparison of the Performance of Supervised Learning Algorithms for Solar Power Prediction

Science seeks strategies to mitigate global warming and reduce the negative impacts of long-term use fossil fuels for power generation. In this sense, implementing promoting renewable energy in different ways becomes one most effective solutions. The inaccuracy prediction generation from photovoltaic (PV) systems is a significant concern planning operational stages interconnected electric networks promotion large-scale PV installations. This study proposes Machine Learning techniques model production system Medellín, Colombia. Four forecasting models were generated compatible with Artificial Intelligence methods: K-Nearest Neighbors (KNN), Linear Regression (LR), Neural Networks (ANN) Support Vector Machines (SVM). results obtained indicate that four methods produced adequate estimations However, best estimate according RMSE MAE ANN model. proposed Learning-based demonstrated be practical solutions forecast Medellin.