Accessibility navigation


Using neural networks to model long-term dependencies in occupancy behavior

Kleinebrahm, M., Torriti, J. ORCID: https://orcid.org/0000-0003-0569-039X, McKenna, R., Ardone, A. and Fichtner, W. (2021) Using neural networks to model long-term dependencies in occupancy behavior. Energy and Buildings, 240. 110879. ISSN 0378-7788

[img]
Preview
Text - Accepted Version
· Available under License Creative Commons Attribution Non-commercial No Derivatives.
· Please see our End User Agreement before downloading.

4MB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1016/j.enbuild.2021.110879

Abstract/Summary

Models simulating household energy demand based on different occupant and household types and their behavioral patterns have received increasing attention over the last years due the need to better understand fundamental characteristics that shape the demand side. Most of the models described in the literature are based on Time Use Survey data and Markov chains. Due to the nature of the underlying data and the Markov property, it is not sufficiently possible to consider long-term dependencies over several days in occupant behavior. An accurate mapping of longterm dependencies in behavior is of increasing importance, e.g. for the determination of flexibility potentials of individual households urgently needed to compensate supplyside fluctuations of renewable based energy systems. The aim of this study is to bridge the gap between social practice theory, energy related activity modelling and novel machine learning approaches. The weaknesses of existing approaches are addressed by combining time use survey data with mobility data, which provide information about individual mobility behavior over periods of one week. In social practice theory, emphasis is placed on the sequencing and repetition of practices over time. This suggests that practices have a memory. Transformer models based on the attention mechanism and Long short-term memory (LSTM) based neural networks define the state of the art in the field of natural language processing (NLP) and are for the first time introduced in this paper for the generation of weekly activity profiles. In a first step an autoregressive model is presented, which generates synthetic weekly mobility schedules of individual occupants and thereby captures long-term dependencies in mobility behavior. In a second step, an imputation model enriches the weekly mobility schedules with detailed information about energy relevant at home activities. The weekly activity profiles build the basis for multiple use cases one of which is modelling consistent electricity, heat and mobility demand profiles of households. The approach developed provides the basis for making high-quality weekly activity data available to the general public without having to carry out complex application procedures.

Item Type:Article
Refereed:Yes
Divisions:Interdisciplinary centres and themes > Energy Research
Science > School of the Built Environment > Energy and Environmental Engineering group
ID Code:96645
Uncontrolled Keywords:activity modelling, mobility behavior, neural networks, synthetic data
Publisher:Elsevier

Downloads

Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation