Forecasting photovoltaic production with neural networks and weather features
Stéphane Goutte, Klemens Klotzner, Hoang-Viet Le, Hans‐Jörg von Mettenheim
Abstract
In this paper, we address the refinement of solar energy forecasting within a 2-day window by integrating weather forecast data and strategically employing entity embedding, with a specific focus on the Multilayer Perceptron (MLP) algorithm. Through the analysis of two years of hourly solar energy production data from 16 power plants in Northern Italy (2020–2021), our research underscores the substantial impact of weather variables on solar energy production. Notably, we explore the augmentation of forecasting models by incorporating entity embedding, with a particular emphasis on embedding techniques for both general weather descriptors and individual power plants. By highlighting the nuanced integration of entity embedding within the MLP algorithm, our study reveals a significant enhancement in forecasting accuracy compared to popular machine learning algorithms like XGBoost and LGBM, showcasing the potential of this approach for more precise solar energy forecasts. • Machine Learning is effective in forecasting photovoltaic production up to 2 days ahead. • Neural networks tend to outperform standard methods. • Entity embedding enhances solar forecast accuracy. • Entity embedding reveals insights into the impact of weather categorical descriptors. • Weather data integration key for forecasting.