Data Driven Approaches for Prediction of Building Energy Consumption at Urban Level

• Published in: Energy procedia 2015-11, Vol.78, p.3378-3383
• Main Authors: Tardioli, Giovanni, Kerrigan, Ruth, Oates, Mike, O‘Donnell, James, Finn, Donal
• Format: Article
• Language: English
• Subjects: building energy consumption estimation; buildings clustering; energy mapping; large scale data-driven models
• ISSN: 1876-6102; 1876-6102
• DOI: 10.1016/j.egypro.2015.11.754

The ability to predict building energy consumption in an urban environment context, using a variety of performance metrics for different building categories and granularities, across varying geographic scales, is critical for future energy scenario planning. The increased quantity and quality of data collected across urban districts facilitates the utilization of data-driven approaches, thereby realizing the potential for energy prediction as a complementary or alternative option to the more traditional physics based approaches. The majority of research to date that exploits data-driven approaches, has mainly focused on analysis at an individual building level. There are few examples in the literature of studies that utilize data-driven models for building energy prediction at an urban scale. The current paper provides a literature review of the recent applications of data-driven models at an urban scale, underlining the opportunities for further research in this context.