原文信息
Transformer approach to nowcasting solar energy using geostationary satellite data
原文链接：
https://www.sciencedirect.com/science/article/pii/S0306261924017707
Highlights
(1) 提出了基于Transformer的深度学习方法（SolarFormer）用于近实时太阳辐射临近预报
(2) SolarFormer使用静止卫星观测数据作为输入，无需地面站点数据支持
(3) SolarFormer在每小时预测中表现优于其他机器学习模型
(4) 由于其计算高效性，SolarFormer表现出对未来的更长时间预测时间的潜力
Research gap
这篇文章利用transformer和静止卫星实现对地表太阳辐射的大规模、实时、准确、稳定的预报。这个方法可以使用在所有静止卫星覆盖区域。此外，此方法具有计算和内存高效性，表现出对未来更长时间预报的潜力。
Abstract
Unpredicted spatial and temporal variability of global horizontal irradiance (GHI) reaching the photovoltaic panels presents a challenge for integrating solar power into the grid stably and cost-effectively at a regional scale. Therefore, there is a recognized demand for large-scale GHI nowcasting that is both timely and accurate, an area where most existing studies fall short. This study introduces the SolarFormer model, which utilizes satellite data and incorporates a gated recurrent unit for near real-time GHI estimation. It also includes a space-time transformer to provide forecasts with a 3-h lead time at 15-min intervals, maintaining accuracy without significant degradation over extended lead times. SolarFormer requires only the selected satellite band information shared by GOES-16 and Himawari-8 as the dynamic input, enabling near-real-time application across all areas covered by these satellites. This feature makes it accessible and efficient for large-scale energy planning. We validate the forecasting result with the ground-measured GHI over seven SURFRAD stations in 2018. The model achieves an hourly prediction root-mean-square error (relative root-mean-square error) of 93.8 W/m2 (15.0 %), 118.9 W/m2 (19.8 %), and 129.1 W/m2 (24.2 %) with 1–3 h lead time respectively. These results demonstrate lower root-mean-square error compared to existing hourly updated numerical weather prediction modeling, such as High-Resolution Rapid Refresh, and deep learning models, such as ConvLSTM. Moreover, the study highlights the potential of SolarFormer for extended lead-time forecasting due to its high computation and memory efficiency compared with the above-mentioned models, potentially benefiting long-term energy planning and power market bidding and clearing. However, SolarFormer exhibits accumulated bias as the predicted lead time increases and faces challenges in predicting GHI in the early morning due to the invalid visible satellite bands during the night, suggesting areas for improvement in future studies.
Keywords
Solar energy forecasting
Photovoltaic technology
Deep learning
Transformer
Near real-time nowcasting
Geostationary satellite
Graphics
图1 SolarFormer 模型结构
图2 输入、目标值和SolarFormer预测值的一个测试样本
图3 SolarFormer模型和基准模型在每个像素点上的晴空比（CSR）验证结果
图4 SolarFormer模型和基准模型在七个SURFRAD站点上的验证结果
图5在不同绝对误差（AE）的初始条件下，预测相对均方根误差的变化。
图6在云条件改变或未改变情况下， SolarFormer对不同时长的预报能力
图7 SolarFormer在不同月份下的预报能力
图8 SolarFormer不同输入/输出时间和空间尺寸的消融实验
作者简介
第一作者简介：
李若含，博士，马里兰大学地理系博士后。从事通过结合遥感数据和深度学习对地表短波辐射进行估算和预测，在Remote Sensing of Environment, Earth System Science Data， NeurIPS等期刊和会议发表一作论文6篇
关于Applied Energy
本期小编：郑培钧；审核人：彭维柯
《Applied Energy》是世界能源领域著名学术期刊，在全球出版巨头爱思唯尔 (Elsevier) 旗下，1975年创刊，影响因子10.1，CiteScore 21.2，本刊旨在为清洁能源转换技术、能源过程和系统优化、能源效率、智慧能源、环境污染物及温室气体减排、能源与其他学科交叉融合、以及能源可持续发展等领域提供交流分享和合作的平台。开源（Open Access）姊妹新刊《Advances in Applied Energy》影响因子13.0，CiteScore 23.9。全部论文可以免费下载。在《Applied Energy》的成功经验基础上，致力于发表应用能源领域顶尖科研成果，并为广大科研人员提供一个快速权威的学术交流和发表平台，欢迎关注！
公众号团队小编招募长期开放，欢迎发送自我简介（含教育背景、研究方向等内容）至wechat@applied-energy.org
点击“阅读原文”
喜欢我们的内容？
点个“赞”或者“再看”支持下吧！
阅读原文
