Preprocessing of Time Series Data for Photovoltaic Energy Forecasting: A Case Study of Two Operational PV Plants

This work presents a robust preprocessing pipeline for photovoltaic (PV) time series forecasting aimed at improving the quality, consistency, and physical coherence of the input data used in predictive models. The proposed methodology integrates temporal lag correction, Fourier-based temporal enrichment, supervised and unsupervised outlier detection, and feature selection to adapt the preprocessing workflow to different operational conditions and data characteristics. The pipeline is validated using real-world data from two PV plants with different temporal resolutions and operating regimes. The results show that the proposed approach improves dataset coherence and strengthens the relationship between meteorological predictors and PV output, providing a reliable basis for subsequent forecasting tasks. In addition, an online forecasting validation over January 2025 shows that a Random Forest model using preprocessed inputs substantially reduces prediction errors compared with the same model using raw inputs, with MAE reductions of 54.2% for the Test Plant and 25.6% for the Production Plant, and corresponding RMSE reductions of 32.1% and 12.6%.