Towards data-driven energy consumption forecasting of multi-family residential buildings: Feature selection via the Lasso

R. K. Jain, T. Damoulas, C. E. Kontokosta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Buildings constitute a large portion of energy consumption in the United States. Accurate forecasting of building energy consumption is integral to the implementation of energy efficiency initiatives and intermittent renewable energy supplies. The availability of high-resolution energy consumption data has allowed researchers to utilize machine learning techniques that forego domain-specific knowledge (e.g., building construction materials, geometric properties) to forecast energy consumption. While there is a growing body of literature surrounding the use of machines learning to forecast building energy consumption, previous research has yet to explore the use of feature selection to determine the most important subset of variables and produce interpretable predictive models. In this paper, we explore the use of Lasso, a shrinkage and selection method for linear regression that estimates sparse coefficients, to select the most important feature subset of a residential energy forecasting model. We evaluate the selected subset on an empirical data set from a multi-family residential building in New York City and compare the results to previous forecasting models without feature selection. Results of this work has implications on the data acquisition and sensing systems required to yield accurate predictions of residential energy consumption.

Original languageEnglish (US)
Title of host publicationComputing in Civil and Building Engineering - Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering
EditorsR. Raymond Issa, Ian Flood
PublisherAmerican Society of Civil Engineers (ASCE)
Pages1675-1682
Number of pages8
ISBN (Electronic)9780784413616
DOIs
StatePublished - 2014
Event2014 International Conference on Computing in Civil and Building Engineering - Orlando, United States
Duration: Jun 23 2014Jun 25 2014

Publication series

NameComputing in Civil and Building Engineering - Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering

Other

Other2014 International Conference on Computing in Civil and Building Engineering
CountryUnited States
CityOrlando
Period6/23/146/25/14

ASJC Scopus subject areas

  • Computer Science Applications
  • Civil and Structural Engineering
  • Building and Construction

Fingerprint Dive into the research topics of 'Towards data-driven energy consumption forecasting of multi-family residential buildings: Feature selection via the Lasso'. Together they form a unique fingerprint.

  • Cite this

    Jain, R. K., Damoulas, T., & Kontokosta, C. E. (2014). Towards data-driven energy consumption forecasting of multi-family residential buildings: Feature selection via the Lasso. In R. R. Issa, & I. Flood (Eds.), Computing in Civil and Building Engineering - Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (pp. 1675-1682). (Computing in Civil and Building Engineering - Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering). American Society of Civil Engineers (ASCE). https://doi.org/10.1061/9780784413616.208