Search eceee proceedings
Better data and analytics enable informed decision making on building operations and decarbonization
Panel: 4. Monitoring and evaluation
This is a non-peer reviewed extended abstract. No paper available.
Author:
Tianzhen Hong, Lawrence Berkeley National Laboratory, USA
Abstract
Research-grade datasets, compliant with the FAIR (Findable, Accessible, Interoperable, and Reusable) principles, from real buildings can address essential gaps that limit our present data analytics capabilities. However, it is currently time-consuming and hard to find datasets that have adequate data coverage, good data quality, and clear documentation. This talk presents an open access dataset (https://bbd.labworks.org/project/bbd) of high-resolution performance data from 12 real buildings of diverse types. The dataset was developed from a U.S. Department of Energy funded project which is a collaborative effort led by Lawrence Berkeley National Laboratory with partnership of Pacific Northwest National Laboratory, Oak Ridge National Laboratory, and National Renewable Energy Laboratory.
The open source data pipeline used to curate, standardize and publish the dataset to comply with the FIAR principles will be introduced. The dataset has been downloaded by more than 600 users. Case studies applying data analytics to extract valuable information from the dataset for informing improvements of building operations and decarbonization will be presented. Challenges (e.g., data standards and metadata models) and opportunities (e.g., big data, AI/machine learning) in curating and using FAIR datasets will also be discussed.
Downloads
Download this presentation as pdf: 4-010-24_Hong_Pres.pdf














