Harnessing open data for hourly power generation forecasting in newly commissioned photovoltaic power plants

Abstract

This paper introduces a novel approach for forecasting hourly outputs in photovoltaic power plants. The approach was tailored to the needs of energy cooperatives by focusing on availability/cost, ease of use, reliability, and replicability. Following the cooperative values, the proposed methodology relies entirely on open data; primarily on the data from the Photovoltaic Geographical Information System (PVGIS). Additionally, the approach was developed to perform short-term (next-day), hourly power-generation forecasts for power plants without or with limited on-site historical records. Seven predictive algorithms were utilized to model the power outputs. The algorithm that performed best (CatBoost) was optimized by using the Sequential Feature Selection and Optuna (automatic hyperparameter optimization software framework). The validation of the developed model was conducted on the actual data from three photovoltaic plants. On these samples, the model performed with a coefficient of determination ranging from 0.83 to 0.9 with only 5 input parameters. Even though the approach was designed to meet the needs of energy cooperatives, it is not limited to such purposes.