Synthetic Photovoltaic and Wind Power Forecasting Data

Photovoltaic and wind power forecasts in power systems with a high share of renewable energy are essential in several applications. These include stable grid operation, profitable power trading, and forward-looking system planning. However, there is a lack of publicly available datasets for research on machine learning based prediction methods. This dataset provides an openly accessible time series dataset, as detailed in https://doi.org/10.48550/arXiv.2204.00411, with realistic synthetic power data. Other publicly and non-publicly available datasets often lack precise geographic coordinates, timestamps, or static power plant information, e.g., to protect business secrets. On the opposite, this dataset provides these. The dataset comprises 120 photovoltaic and 273 wind power plants with distinct sides all over Germany from 500 days in hourly resolution. This large number of available sides allows forecasting experiments to include spatial correlations and run experiments in transfer and multi-task learning. It includes side-specific, power source-dependent, non-synthetic input features from the ICON-EU weather model. A simulation of virtual power plants with physical models and actual meteorological measurements provides realistic synthetic power measurement time series. These time series correspond to the power output of virtual power plants at the location of the respective weather measurements. Since the synthetic time series are based exclusively on weather measurements, possible errors in the weather forecast are comparable to those in actual power data. We are incredibly thankful to Enercon (www.enercon.de) for providing information on turbine characteristics. We are also grateful to the German weather service - DWD (www.dwd.de), for providing an open and excellent API to access weather forecasts. IMPORTANT: In case you use the data please cite our corresponding article https://doi.org/10.48550/arXiv.2204.00411.

高可再生能源渗透率的电力系统中，光伏与风电功率预测在诸多场景中至关重要，涵盖电网稳定运行、盈利性电力交易以及前瞻性系统规划等应用。然而当前面向基于机器学习的预测方法研究的公开可用数据集仍较为匮乏。本数据集为公开可获取的时间序列数据集，详细信息见https://doi.org/10.48550/arXiv.2204.00411，包含贴合实际场景的合成功率数据。多数现有公开与非公开数据集往往缺乏精准的地理坐标、时间戳或静态电厂信息，此类缺失常源于商业机密保护需求。与之相反，本数据集完整涵盖上述三类信息。本数据集包含德国全境120座光伏电站与273座风电场的逐小时功率数据，时间跨度达500天。丰富的站点数量支持开展包含空间相关性的预测实验，也可用于迁移学习与多任务学习相关研究。数据集包含来自ICON-EU数值天气预报模式的、针对不同站点且与发电类型相关的非合成输入特征。本数据集通过物理模型模拟虚拟电厂，并结合实际气象观测数据生成贴合真实场景的合成功率时间序列，该序列与对应气象观测点位处虚拟电厂的实际出力相匹配。由于合成时间序列完全基于气象观测数据生成，其存在的气象预报误差与实际功率数据中的误差水平具备可比性。我们衷心感谢Enercon（www.enercon.de）提供涡轮机特性相关信息，同时感谢德国气象局（DWD）（www.dwd.de）开放并提供优质的天气预报API接口。重要提示：若您使用本数据集，请引用对应研究论文：https://doi.org/10.48550/arXiv.2204.00411。

搜集汇总

背景与挑战

背景概述

该数据集是一个公开可访问的光伏和风力发电预测合成时间序列数据集，包含德国393个发电站500天的每小时数据，支持机器学习研究，特别是空间相关性、迁移学习和多任务学习实验。数据集基于实际气象测量和天气模型，提供了精确的地理和时间信息，弥补了其他数据集的不足。