Engineering professor SENMC LAs Cruces, New Mexico, United States
Electric power generated from Solar Photovoltaic (PV) panels is estimated to have increased by 22% in 2019, to 720 TWatt. It is now considered the third-largest renewable energy technology after wind and hydro powers. The primary reason for this growth is the need to utilize free energy resources that are also environmentally clean. PV-generated power, however, is uncertain and varies from time to time and season to season. Dealing with this uncertainty requires having predictive and forecasting models that accurately estimate generated power from historical data. This paper reports on an in-progress research project that explores weather-related variables such as humidity, temperature, and wind speed and uses them to predict and forecast generated power using a dataset collected over three years by a weather station at Southeast New Mexico College at Carlsbad. Various predictive and forecasting models are built, trained, and evaluated. The goal is to explore these variables and report on what makes a good predictive model and how such a model behaves over time.
