System identification-informed Transparent and Explainable Machine Learning with application to power consumption forecasting

Aug 3, 2026

Upload by Patrick

System identification (SysID) addresses dynamic data modelling by deriving models from input–output behavior, offering transparent and parsimonious structures useful for interpretation and analysis. With machine learning’s rapid growth and rising demand for transparency, explainability, and interpretability, the study develops a System Identification-informed Transparent and Explainable Machine Learning framework (SITEMAL). A case study using an areal power consumption dataset demonstrates how the framework supports power consumption forecasting while retaining interpretive modelling properties.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Introduction

System identification and machine learning interplay

Assumptions and data requirements for SysID

Proposed framework and case study

Power consumption forecasting example

This is a repository copy of System identification-informed transparent and explainable machine learning with application to power consumption forecasting. White Rose Research Online URL for this paper: [https://eprints.whiterose.ac.uk/201102/](https://eprints.whiterose.ac.uk/201102/) [Version: Accepted Version](Version: Accepted Version) Proceedings Paper: Wei, [H.-L. orcid.org/0000-0002-4704-7346](H.-L. orcid.org/0000-0002-4704-7346) (2023) System identification-informed transparent and explainable machine learning with application to power consumption forecasting. In: 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) Proceedings. 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 19-21 Jul 2023, Tenerife, Canary Island, Spain. Institute of Electrical and Electronics Engineers (IEEE) . ISBN 9798350322989 [https://doi.org/10.1109/ICECCME57830.2023.10252535](https://doi.org/10.1109/ICECCME57830.2023.10252535) © 2023 The Authors. Except as otherwise noted, this author-accepted version of a paper published in 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) Proceedings is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/) 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/) Final Accepted Manuscript 06/04/2023. Proc. of the International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME 2023) 19-20 July 2023, Tenerife, Canary Islands, Spain System Identification-informed Transparent and Explainable Machine Learning with Application to Power Consumption Forecasting Hua-Liang Wei 1,2,3,4 1 Dept. Automatic Control and Systems Engineering 2 Energy Institute; 3 Centre of Machine Intelligence 4 Centre for Signal Processing and Cpmplex Systems The University of Sheffield Sheffield, UK [w.hualiang@sheffield.ac.uk](w.hualiang@sheffield.ac.uk); ORCID: 0000-0002-4704-7346 Abstract—System identification (SysID) is the art and science of dealing with dynamic data modelling problems from systems science perspectives. It has been an active field and is still very active today, due to its wide range of applications, especially its basic principles of finding transparent, interpretable and parsimonious models for different purposes. The past decades have witnessed the explosive growth in machine learning (ML) and its applications in all areas of science and engineering. Meanwhile, there has been an increasing demand for the development of transparent, explainable and/or interpretable ML models. This paper proposes a new framework for developing System Identification-informed Transparent and Explainable MAchine Learning (SITEMAL) models. A case study, involving areal power consumptio

FAQs

What problem does system identification (SysID) focus on?

SysID focuses on dynamic data modelling by determining a system model from input and output data within a specified class of systems, enabling transparent and parsimonious structures.

Why does the paper emphasize transparent and explainable machine learning?

Demand for transparency and interpretability has increased alongside machine learning’s growth; many ML models, especially deep learning, can achieve strong predictions but are often black-box and hard to interpret.

What framework does the paper propose and what does it demonstrate?

The paper proposes the SITEMAL framework—System Identification-informed Transparent and Explainable Machine Learning. It demonstrates its application using an areal power consumption dataset to support power consumption forecasting.

Aug 3, 2026

Upload by Patrick