Bayesian CNN-BiLSTM and Vine-GMCM Based Probabilistic Forecasting of Hour-Ahead Wind Farm Power Outputs (Input dataset)

The dataset represents the input data on which the article Bayesian CNN-BiLSTM and Vine-GMCM Based Probabilistic Forecasting of Hour-Ahead Wind Farm Power Outputs, is based. The data consist of a two-year hourly time series of measured wind speed and direction, air density, and production of two wind farms (WTs) in Croatia (Bruška and Jelinak). In addition to the two listed WTs, measurements of two nearby WTs (Glunca and Zelengrad) are also attached in training files (these WPPs are not directly analyzed in the article). Datasets are divided into a training set (4 WTs) and a test set (Bruska and Jelinak only). To extend the test dataset, additional data (extended_test files) were used in the paper, in which the timestamps used for the validation of proposed forecasting models are indicated.

本数据集构成了论文《基于贝叶斯CNN-BiLSTM和Vine-GMCM的小时级风电场发电量概率预测》所依赖的输入数据。数据包括克罗地亚两座风电场（Bruška和Jelinak）两年内的每小时风速和风向、空气密度以及发电量时间序列。此外，训练文件中还附带了附近两座风电场（Glunca和Zelengrad）的测量数据（这些风电场在文章中未直接进行分析）。数据集被划分为训练集（包含4座风电场）和测试集（仅Bruška和Jelinak）。为了扩展测试数据集，论文中使用了额外的数据（扩展测试文件），其中指明了用于验证所提出预测模型的验证时间戳。