VMD-TFT: A Variational Mode Decomposition- Augmented Temporal Fusion Transformer for Multi-Horizon Solar Irradiance Forecasting
IEEE Access, cilt.14, ss.137929-137942, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 14
- Basım Tarihi: 2026
- Doi Numarası: 10.1109/access.2026.3730818
- Dergi Adı: IEEE Access
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
- Sayfa Sayıları: ss.137929-137942
- Anahtar Kelimeler: deep learning, multi-horizon, renewable energy, Solar irradiance, TFT, VMD
- Bilecik Şeyh Edebali Üniversitesi Adresli: Evet
Özet
Accurate short-term solar irradiance forecasting is necessary for the effective grid integration of photovoltaic systems. This study proposes a novel two-stage framework, VMD-TFT, which integrates the Variational Mode Decomposition (VMD) with the Temporal Fusion Transformer (TFT) for multi-horizon forecasting of direct normal irradiance (DNI). In the first stage, the input signal is decomposed into intrinsic mode functions (IMFs) using VMD, enabling the separation of multi-scale temporal patterns. In the second stage, each IMF is modeled using a dedicated TFT sub-network, and the final prediction is obtained through reconstruction of all components. The proposed approach is evaluated on two benchmark datasets (Folsom, California, and NREL SRRL, Colorado) across multiple forecasting horizons (1h, 3h, and 6h). Experimental results demonstrate that VMD-TFT consistently outperforms six baseline models, including statistical, machine learning, and deep learning approaches. For the 1-hour horizon, the model achieves an R2 of 0.991 and an RMSE of 12.5 W/m2, showing significant improvement over the vanilla TFT baseline. The performance gain becomes more pronounced at longer horizons, with a 20.3% RMSE reduction at the 6 hour horizon. In addition to point forecasting, the framework provides probabilistic predictions via quantile regression and demonstrates robustness through cross-site validation. The results indicate that integrating signal decomposition with attention-based deep learning improves both forecasting accuracy and model stability for complex, non-stationary solar irradiance signals. On the Folsom benchmark, the proposed VMD-TFT yields R2 values of 0.991, 0.972, and 0.948, and RMSE values of 12.5, 28.3, and 42.1 W/m2, respectively, across the investigated horizons. The framework achieves a 29.8% reduction in 1-hour RMSE over the vanilla TFT baseline, demonstrating statistical significance under the Diebold-Mariano test (p < 0.001).