Deploy-Safe Day-Ahead Multi-Step PV Power Forecasting Using Meteo-Only Inputs
Year: 2026
Type: article
Abstract: This study investigates day-ahead multi-step photovoltaic (PV) power forecasting with 15-minute resolution in a realistic deployment-safe framework based solely on meteorological inputs. Using real-world field data from December 2020–January 2025 for a PV plant with a capacity of approximately 110 kWe–129 kWp located in Konya, Turkey, a 96-step generation profile is predicted sequentially for each day. Unlike previous studies, delayed plant measurements are completely excluded, and only meteorological variables and deterministic time features are used. The proposed end-to-end workflow includes day-level quality control, input-output alignment analysis, deploy-safe feature engineering, and two-stage feature selection. Deep learning (BiLSTM, LSTM, Transformer), classical machine learning (Boosting, ElasticNet, ExtraTrees, MLP), and NBEATSx-based models are compared under a common evaluation protocol. Experimental results show that the many-to-many BiLSTM architecture provides the best performance (RMSE = 9.487 kW, R² = 0.92) and that boosting-based classical methods offer a robust alternative with similar accuracy. The residual correction module added to NBEATSx improved performance by up to 4%, particularly in absolute error metrics. Log-error analyses reveal heavy-tailed behavior driven by operational noise across all models. The findings confirm the superiority of deep trailing models in safe deployment scenarios operating with only meteorological inputs, while also highlighting the practical applicability of classical methods.
Source: IEEE Access
Authors: G. Tulum, V. Esen, A. S. Sarkin, T. Dindar, E. Alp
Language: English
Field: Energy
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W7143474580