Data increment and enrichment to train component-based machine learning model for early stage energy prediction

This dataset is used for training of component based machine learning (CBML) models described in the article. The article examines the effect of increasing and enriching training data on machine learning model's ability to generalise. Please read the full article for the relevant details of ML models. There are seven training dataset BaseCase, E-1, E-2, E-3, I-1, I-2, and I-3 and one test dataset. The trained machine learning (ML) components are saved under 'Models' folder in each dataset.

本数据集用于训练本文所述的基于组件的机器学习（Component-Based Machine Learning, CBML）模型。本文探讨了训练数据的扩容与富集对机器学习（Machine Learning, ML）模型泛化能力的影响。如需了解机器学习模型的相关细节，请查阅本文完整内容。本数据集包含7个训练子集：BaseCase、E-1、E-2、E-3、I-1、I-2及I-3，另有1个测试子集。训练完成的机器学习组件将存储于各数据集的'Models'文件夹内。