The Building Data Genome Directory provides a rich and comprehensive dataset collection for building energy research, covering ontologies, models, and data from energy, water, electric vehicles, BIM, FDD and occupant sensors.
by Arne Hansen
Key Outcomes
BDG and BDG2 incorporate over 3,000 electricity meters from over 1,600 buildings, principally in the United States of America, and covers years 2016-2017. Down to an hourly resolution, the datasets provide researchers and product development teams the ability to test models and optimisation on a wide array of real-world builing topologies.
Machine learning competitions are run by ASHRAE against the datasets, known as the “Great Energy Predictor” with GEPIII run in 2019.
“This data set can be used to benchmark various statistical learning algorithms and other data science techniques. It can also be used simply as a teaching or learning tool to practice dealing with measured performance data from large numbers of non-residential buildings.”
Dr Clayton Miller, National University of Singapore
Building Data Genome Project
Building Data Genome Project 2 on Github