Scholarlink

Abstract <p>Accurate medium-range solar irradiance forecasting in tropical regions remains highly challenging due to rapid convective development, short-lived temporal dependencies, and substantial domain mismatch between observational and forecast-driven inputs. This study proposes a two-day-ahead forecasting framework that combines an encoder-only Transformer with a transfer-learning strategy linking ground-based observations to WRF-derived predictors. The model is pertained on high-resolution observational sequences to learn physically consistent temporal representations, and subsequently fine-tuned on WRF inputs to mitigate domain shift during operational deployment. Using full-year 2019 data from Thailand, the proposed Transformer+TL architecture achieves an RMSE of 119.15 W/m<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\({}^{2}\)</EquationSource> <!--LobJMat2561540Kanphakdee-m1--> </InlineEquation>, RRMSE of 28.94<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\%\)</EquationSource> <!--LobJMat2561540Kanphakdee-m2--> </InlineEquation>, and <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(R^{2}=0.8683\)</EquationSource> <!--LobJMat2561540Kanphakdee-m3--> </InlineEquation>, outperforming a tuned XGBoost baseline with statistically significant gains. Ablation experiments confirm that self-attention and transfer learning contribute complementary improvements, while robustness analyses show stable performance across dry and monsoon regimes. Sensitivity evaluation further reveals a short predictive memory of approximately 1–2 h in tropical irradiance, with error increasing exponentially for longer lookback windows-consistent with the fast decorrelation of convective cloud systems. The resulting framework is accurate, scalable, and operationally relevant for photovoltaic scheduling, reserve management, and tropical grid reliability, providing a strong foundation for future probabilistic, multi-site, and physics-informed solar forecasting systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Transfer Learning-Enhanced Transformer for Robust Solar Irradiance Forecasting in Tropical Renewable Energy Integration

  • 期刊论文

  • 发表日期：

    2026年1月1日

查看全文
  • Nattharat Kanphakdee,
  • Wararit Panichkitkosolkul,
  • Andrei Volodin,
  • Perawut Chinnavornrungsee,
  • Kobsak Sriprapha,
  • Wichai Witayakiattilerd

摘要

Abstract

Accurate medium-range solar irradiance forecasting in tropical regions remains highly challenging due to rapid convective development, short-lived temporal dependencies, and substantial domain mismatch between observational and forecast-driven inputs. This study proposes a two-day-ahead forecasting framework that combines an encoder-only Transformer with a transfer-learning strategy linking ground-based observations to WRF-derived predictors. The model is pertained on high-resolution observational sequences to learn physically consistent temporal representations, and subsequently fine-tuned on WRF inputs to mitigate domain shift during operational deployment. Using full-year 2019 data from Thailand, the proposed Transformer+TL architecture achieves an RMSE of 119.15 W/m \({}^{2}\) , RRMSE of 28.94 \(\%\) , and \(R^{2}=0.8683\) , outperforming a tuned XGBoost baseline with statistically significant gains. Ablation experiments confirm that self-attention and transfer learning contribute complementary improvements, while robustness analyses show stable performance across dry and monsoon regimes. Sensitivity evaluation further reveals a short predictive memory of approximately 1–2 h in tropical irradiance, with error increasing exponentially for longer lookback windows-consistent with the fast decorrelation of convective cloud systems. The resulting framework is accurate, scalable, and operationally relevant for photovoltaic scheduling, reserve management, and tropical grid reliability, providing a strong foundation for future probabilistic, multi-site, and physics-informed solar forecasting systems.