Modelling short-term appliance energy use with interpretable machine learning - a system identification approach

Aug 3, 2026

Upload by Himbo

Appliance energy use (AEU) modelling for residential buildings supports energy consumption control, energy management, maintenance planning, and building performance evaluation. While traditional machine learning can achieve high prediction accuracy, many models are not interpretable and cannot attribute variations in AEU to appliance factors individually or jointly. An interpretable learning framework is proposed based on the nonlinear autoregressive moving average with eXogenous inputs (NARMAX), providing transparent, physically meaningful factor contributions and enabling energy-saving insights for improving AEU efficiency.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Keywords

Introduction

Related Work and Background

Proposed Interpretable Approach

Experiments and Results

Discussion

Conclusions

This is a repository copy of Modelling short-term appliance energy use with interpretable machine learning: a system identification approach. White Rose Research Online URL for this paper: [https://eprints.whiterose.ac.uk/200865/](https://eprints.whiterose.ac.uk/200865/) Version: Published Version Article: Gu, Y. and Wei, [H.-L. orcid.org/0000-0002-4704-7346](H.-L. orcid.org/0000-0002-4704-7346) (2023) Modelling short-term appliance energy use with interpretable machine learning: a system identification approach. Arabian Journal for Science and Engineering, 48 (11) . pp. 15667-15678. ISSN 1319-8025 [https://doi.org/10.1007/s13369-023-08084-1](https://doi.org/10.1007/s13369-023-08084-1) Reuse This article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence allows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the authors for the original work. More information and the full terms of the licence here: [https://creativecommons.org/licenses/](https://creativecommons.org/licenses/) Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request. [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/) Arabian Journal for Science and Engineering [https://doi.org/10.1007/s13369-023-08084-1](https://doi.org/10.1007/s13369-023-08084-1) Modelling Short-Term Appliance Energy Use with Interpretable Machine Learning: A System Identiﬁcation Approach Yuanlin Gu1 · Hua-Liang Wei2,3 Received: 1 June 2022 / Accepted: 18 June 2023 © The Author(s) 2023 Abstract The modelling and analysis of appliance energy use (AEU) of residential buildings are important for energy consumption control, energy management and maintenance, building performance evaluation, and so on. Although some traditional machine learning methods have been applied to produce good prediction results, these models are usually not interpretable, in that they fail to explain how appliance factors make contributions to the variation of AEU individually and interactively. Explicitly knowing the role played by each of the appliance factors in explaining AEU, however, is very important for energy saving. Motivated by this observation, this study introduces an interpretable machine learning approach which is built upon the nonlinear autoregressive moving average with eXogenous inputs model. The advantage of the proposed model is that in comparison with other state-of-the-art machine learning methods, for example, feedforward neural network, recurrent neural network (e.g., gated recurrent unit), and long short-term memory network, the established model is not only able to produce more accurate energy use prediction, but more importantly, also fully transparent and physically interpretable, clearly and explicitly indicating which factors signiﬁcantly affect the variation of AEU. The ﬁndings of this study provide meaningful insights for improving the AEU efﬁciency. Keywords Appliance energy use · Residual building · Modelling · Forecasting · Interpretable machine learning · NARMAX model 1 Introduction Extensive attention has been paid to the analysis and modelling of appliance energy use (AEU) in the literature [1–3] . Revealing and establishing the inherent dependency relationship of AEU on potential drivers is very useful for energy control and management [4, 5], building performance analysis through simulations [6, 7], and energy consumption control [8] . Many methods have been proposed for AEU modelling and analysis, such as multiple linear regression [3], artiﬁcial neural networks [9, 10], outlier detection [11], support vector machines [12], and model ensembles [13] . AEU is determine

FAQs

Why is interpretable modelling important for appliance energy use (AEU)?

Because many prediction-focused machine learning models are black-boxes and cannot explain how appliance factors individually or interactively drive AEU variation, limiting actionable energy saving decisions.

What modelling approach does the study use?

The study proposes an interpretable machine learning approach built on the nonlinear autoregressive moving average with eXogenous inputs (NARMAX) framework.

How does the proposed model differ from common neural network methods?

Compared with feedforward, recurrent neural networks, and long short-term memory networks, the proposed model emphasizes transparency and physical interpretability, not only prediction accuracy.

Aug 3, 2026

Upload by Himbo