Predicting Socio-Demographic Characteristics from Load Profiles with Varying Time Granularities

Dejan Radovanovic, Dejan Radovanovic, Maximilian Schirl, Andreas Unterweger, Andreas Unterweger, Günther Eibl

2025

Abstract

Energy consumption data from smart meters has been shown to infer socio-demographic characteristics, which impacts privacy. However, the impact of time granularity on the ability to classify such characteristics has not yet been investigated in existing literature. In this paper, we answer this question by analyzing a dataset of more than 1,000 households over one year. We obtain three main findings: (i) While a coarser time granularity leads to decreased classification performance, we find that, unexpectedly, classification performance only varies insignificantly within two relatively large granularity intervals. For example, one-hour granularity exhibits nearly the same classification performance as 15-minute granularity. This indicates that, depending on the use case, data collection can be minimized, as any resolution between 15 minutes and one hour can be used without significantly impacting prediction performance. (ii) We propose a new evaluation methodology where an interpretable classification algorithm can predict a household’s socio-demographic characteristics from a load profile of a single, arbitrary week of the year. Compared to existing methodologies, where training and testing data are sampled from a single known week, using arbitrary weeks as input makes classification harder, thus requiring more sophisticated classification algorithms. (iii) We present such an interpretable classification algorithm, which outperforms those that train and evaluate classifiers separately for each week. At the same time, our algorithm exhibits a comparable performance to approaches that require a load profile of the whole year instead of a single, arbitrary week.

Paper Citation

in Harvard Style

Radovanovic D., Schirl M., Unterweger A. and Eibl G. (2025). Predicting Socio-Demographic Characteristics from Load Profiles with Varying Time Granularities. In Proceedings of the 14th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS; ISBN 978-989-758-751-1, SciTePress, pages 87-98. DOI: 10.5220/0013217400003953

in Bibtex Style

@conference{smartgreens25,
author={Dejan Radovanovic and Maximilian Schirl and Andreas Unterweger and Günther Eibl},
title={Predicting Socio-Demographic Characteristics from Load Profiles with Varying Time Granularities},
booktitle={Proceedings of the 14th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS},
year={2025},
pages={87-98},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013217400003953},
isbn={978-989-758-751-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS
TI - Predicting Socio-Demographic Characteristics from Load Profiles with Varying Time Granularities
SN - 978-989-758-751-1
AU - Radovanovic D.
AU - Schirl M.
AU - Unterweger A.
AU - Eibl G.
PY - 2025
SP - 87
EP - 98
DO - 10.5220/0013217400003953
PB - SciTePress