The SOLETE dataset

Author: Daniel Vázquez Pombo ([e-mail]), ORCID: https://orcid.org/0000-0001-5664-9421 ------------------------------------------------------------------------------- This item includes the SOLETE dataset which is disclosed to increase the transparency and replicability of [1] and [2], which are at different stages of the review process. <br> SOLETE includes 15 months of 5 minute and hourly measurements from the 1st June 2018 to 1st September 2019 covering: Timestamp, air temperature, relative humidity, pressure, wind speed, wind direction, global horizontal irradiance, plane of array irradiance, and active power recorded from an 11 kW Gaia wind turbine and a 10 kW PV inverter. <br> The origin of the data is SYSLAB, part of DTU Elektro. If you want to learn more about the dataset, you should check out [3].<br> <br> You can use the SOLETE dataset with the codes available here: https://doi.org/10.11583/DTU.17040626 <br> The different scripts have various functions. One allows to import SOLETE and show some plots. Another is a platform where you can play with different Machine Learning models for time series forecasting. The application focuses on predicting PV power, but it can be easily edited by the user.<br> <br> The publications related to this item are:<br> <br> [1] D. V. Pombo, H. W. Bindner, S. V. Spataru, P. E. Sørensen, P. Bacher, Increasing the Accuracy of Hourly Multi-Output Solar Power Forecast with Physics-Informed Machine Learning, Sensors 22 (3) (2022) 749. <br> [2] D.V. Pombo, P. Bacher, C. Ziras, H.W. Bindner, S.V. Spataru, P. Sørensen, Benchmarking Physics-Informed Machine Learning-based Short Term PV-Power Forecasting Tools, Under Review. <br> [3] D.V. Pombo, O.G. Gehrke, H.W. Bindner, (2022). SOLETE, a 15-month long holistic dataset including: Meteorology, co-located wind and solar PV power from. <em>Data in Brief</em>, 108046. <br> ------------------------------------------------------------------------------- <br> To cite this item: @misc{Pombo2022SOLETE, author = "Daniel Vazquez Pombo", title = "{The SOLETE dataset}", year = "2022", month = "Feb", url = "https://data.dtu.dk/articles/dataset/The_SOLETE_dataset/17040767", doi = "10.11583/DTU.17040767", note = {Retrieved from {DTU-Data}, \url{https://data.dtu.dk/articles/dataset/The_SOLETE_dataset/17040767}, {DOI}: {10.11583/DTU.17040767}}, }<br>

作者：丹尼尔·巴斯克斯·蓬博（Daniel Vázquez Pombo），邮箱：[e-mail]，ORCID：https://orcid.org/0000-0001-5664-9421
-------------------------------------------------------------------------------
本数据集包含SOLETE数据集（SOLETE Dataset），其公开目的是提升文献[1]与[2]的透明度与可复现性，两篇文献目前处于不同的审稿阶段。
SOLETE数据集涵盖2018年6月1日至2019年9月1日共计15个月的5分钟级与小时级观测数据，包含以下内容：时间戳、气温、相对湿度、气压、风速、风向、总水平辐照度、阵列平面辐照度，以及一台11 kW Gaia风力涡轮机和一台10 kW光伏逆变器记录的有功功率。
本数据集的数据源自SYSLAB实验室，该实验室隶属于丹麦技术大学电气系（DTU Elektro）。如需了解该数据集的更多信息，请查阅文献[3]。

用户可通过以下链接提供的代码使用SOLETE数据集：https://doi.org/10.11583/DTU.17040626。不同脚本具备不同功能：其一可导入SOLETE数据集并生成可视化图表；其二为一个交互式平台，支持用户针对时间序列预测任务调试多种机器学习模型，该应用聚焦于光伏功率预测，但用户可自行对其进行修改以适配其他需求。

与本数据集相关的出版物如下：

[1] D. V. Pombo, H. W. Bindner, S. V. Spataru, P. E. Sørensen, P. Bacher. 基于物理信息机器学习的小时级多输出太阳能功率预测精度提升[J]. Sensors, 2022, 22(3): 749.
[2] D.V. Pombo, P. Bacher, C. Ziras, H.W. Bindner, S.V. Spataru, P. Sørensen. 基于物理信息机器学习的短期光伏功率预测工具基准测试. （稿件待审）
[3] D.V. Pombo, O.G. Gehrke, H.W. Bindner. (2022). SOLETE：一份包含气象数据、共址风电与光伏功率的15个月全维度数据集[J]. Data in Brief, 108046.

-------------------------------------------------------------------------------
本数据集的引用格式如下：
@misc{Pombo2022SOLETE,
author = "Daniel Vázquez Pombo",
title = "{SOLETE数据集}",
year = "2022",
month = "Feb",
url = "https://data.dtu.dk/articles/dataset/The_SOLETE_dataset/17040767",
doi = "10.11583/DTU.17040767",
note = {数据源自{DTU-Data}，获取链接：url{https://data.dtu.dk/articles/dataset/The_SOLETE_dataset/17040767}，DOI：{10.11583/DTU.17040767}},
}

搜集汇总

背景与挑战

背景概述

SOLETE数据集是一个包含15个月气象和可再生能源发电数据的综合数据集，涵盖多种环境参数和发电记录，旨在支持物理信息机器学习和时间序列预测研究。数据集来自DTU Elektro的SYSLAB，并附有相关代码平台以促进研究应用。