雲頂温度とビジョントランスフォーマーを用いたマイクログリッドにおける短期太陽光発電予測
Short-term solar PV forecasting in microgrids using cloud top temperature and vision transformer based models (原題)
Surathunmanun, Surasak, Ongsakul, Weerakorn, Singh, Jai Govind, Mehran, Kamyar
🤖 gxceed AI 要約
日本語
本論文は、センサー制約のあるマイクログリッド向けに、衛星画像の雲頂温度とVision Transformerを組み合わせた短期太陽光発電予測フレームワーク（CTT–ViT–Transformer）を提案。実運用データで評価し、MAE 15.99 kW、R² 0.97と高い精度を達成。地上センサー不要で導入障壁を低減し、再生可能エネルギーの統合と化石燃料削減に貢献する。
English
This paper proposes a novel framework (CTT–ViT–Transformer) integrating satellite cloud top temperature imagery with Vision Transformer and Transformer models for short-term solar PV forecasting in sensor-constrained microgrids. Evaluated on real operational data, it achieves MAE of 15.99 kW and R² of 0.97, outperforming baselines. It requires no ground-based sensors, lowering adoption barriers and supporting renewable integration and fossil fuel reduction.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本の離島や遠隔地のマイクログリッドでも、地上センサー不足が課題となる中、衛星データとAIを活用した本手法は、再生可能エネルギー導入拡大とコスト削減に寄与する。SSBJ開示やカーボンニュートラル目標に向けた再生可能エネルギー比率向上の実証事例として参考になる。
In the global GX context
Globally, this work addresses the challenge of renewable energy forecasting in data-scarce regions, aligning with ISSB and CSRD disclosure requirements for reliable emissions reduction. It demonstrates scalable AI solutions for microgrids, supporting energy transition and climate goals in developing regions and island communities.
👥 読者別の含意
🔬研究者:Provides a novel AI-based forecasting method that combines satellite data and transformers, offering a benchmark for sensor-constrained renewable forecasting.
🏢実務担当者:Offers a cost-effective forecasting solution for microgrid operators to optimize battery scheduling and reduce diesel use, lowering operational costs.
🏛政策担当者:Highlights the potential of satellite-based AI forecasting to support renewable integration in remote areas, informing policies for energy access and decarbonization.
📄 Abstract（原文）
Introduction Expanding clean-energy microgrids in remote areas is essential for achieving global decarbonisation and energy transition goals. Accurate short-term solar photovoltaic (PV) forecasting plays a key role in reducing diesel dependence, improving battery scheduling, and enabling reliable integration of renewable energy. However, forecasting remains challenging in many developing regions due to the lack of ground-based irradiance sensors, cloud cameras, and real-time monitoring infrastructure. Methods This paper proposes a novel forecasting framework, termed CTT–ViT–Transformer, which integrates Generative AI techniques to enhance short-term solar PV forecasting in sensor-constrained microgrids. The framework employs Cloud Top Temperature (CTT) satellite imagery, capturing cloud height and thermal characteristics, processed through a Vision Transformer (ViT) for spatial feature extraction and a Transformer model for time-series prediction. Results The proposed framework is evaluated using operational data from a real-world islanded microgrid. Results indicate that a standard Transformer model outperforms LSTM and CNN-LSTM baselines, achieving a mean absolute error (MAE) of 23.45 kW, root mean square error (RMSE) of 28.24 kW, and R² of 0.93. The CTT–ViT–Transformer further improves forecasting accuracy, reducing errors to an MAE of 15.99 kW and RMSE of 24.28 kW with an R² of 0.97, and consistently outperforms models relying on RGB satellite imagery. High predictive accuracy is maintained across four-step-ahead forecasts, with R² values exceeding 0.96. Discussion The proposed approach requires no ground-based irradiance sensors, lowering adoption barriers for resource-constrained microgrids while remaining compatible with sensor-based data when available. Its scalability supports proactive energy management in the carbon-neutral microgrid on Koh Paluay Island by enabling more efficient scheduling of renewable generation and energy storage, thereby reducing fossil fuel use and operational costs. By enabling ...
🔗 Provenance — このレコードを発見したソース
- base https://doi.org/10.3389/fenrg.2025.1691881first seen 2026-09-01 12:04:24
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。