Share

An efficient method for learning personalized thermal preference profiles in office spaces.

Number: pap. 3677

Author(s) : LEE S., KARAVA P., TZEMPELIKOS A., et al.

Summary

The objective of this work is to develop and demonstrate an efficient Bayesian inference algorithm to learn individual occupants’ thermal preferences in office buildings. We present an experimental study to collect data representative of thermal comfort delivery conditions for which the algorithm would be implemented in actual buildings. Subsequently, we demonstrate the efficiency of our algorithm by showing the evolution of personalized thermal preference profiles as the training data size increases and by evaluating profiles inferred with limited data.
The results show more reliable personal profiles with our approach when the training data are limited compared to typical learning approaches, training a model from scratch with maximum likelihood estimation.

Available documents

Format PDF

Pages: 8

Available

  • Public price

    20 €

  • Member price*

    15 €

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: An efficient method for learning personalized thermal preference profiles in office spaces.
  • Record ID : 30025064
  • Languages: English
  • Source: 2018 Purdue Conferences. 5th International High Performance Buildings Conference at Purdue.
  • Publication date: 2018/07/09

Links


See other articles from the proceedings (88)
See the conference proceedings

Indexing