Exploring the Impact of K-Anonymisation on the Energy Efficiency of Machine Learning Algorithms

Aug 4, 2026

Upload by Skyler

With the increased use of Artificial Intelligence (AI), concerns about AI’s energy consumption are increasing. This paper investigates how k-anonymisation and dataset characteristics influence energy use during machine learning (ML) training. Using three UCI datasets, the study evaluates energy efficiency of Random Forest (RF), k-Nearest Neighbours (KNN), and Logistic Regression (LR) on both original and k-anonymised data. Results show that k-anonymisation significantly reduces energy consumption for RF and LR, and increases energy savings for LR when more features are present, while KNN savings are largely not observed except in a one-feature setting.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Background: AI energy consumption

Policy and sustainability initiatives

Research gap and motivation

VU Research Portal Exploring the Impact of K-Anonymisation on the Energy Efficiency of Machine Learning Algorithms Zemanek, Vit; Hu, Yixin; De Reus, Pepijn; Oprescu, Ana; Malavolta, Ivano published in 2024 10th International Conference on ICT for Sustainability (ICT4S) 2024 DOI (link to publisher) 10.1109/ICT4S64576.2024.00022 document version Publisher's PDF, also known as Version of record document license Article 25fa Dutch Copyright Act Link to publication in VU Research Portal citation for published version (APA) Zemanek, V. , Hu, Y. , De Reus, P. , Oprescu, A. , & Malavolta, I. (2024) . Exploring the Impact of K-Anonymisationon the Energy Efficiency of Machine Learning Algorithms. In 2024 10th International Conference on ICT for Sustainability (ICT4S): [Proceedings](pp. 128-137) . Institute of Electrical and Electronics Engineers Inc.. [https://doi.org/10.1109/ICT4S64576.2024.00022](https://doi.org/10.1109/ICT4S64576.2024.00022) General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal Take down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. E-mail address: [vuresearchportal.ub@vu.nl](vuresearchportal.ub@vu.nl) [Download date: 16](Download date: 16) . May. 2026 2024 10th International Conference on ICT for Sustainability (ICT4S) ©2024 IEEE DOI: 10.1109/ICT4S64576.2024.00022| 979-8-3315-0528-8/24/$31.00 | 2024 10th International Conference on ICT for Sustainability (ICT4S) Exploring the Impact of K-Anonymisation on the Energy Ef􀀂ciency of Machine Learning Algorithms Vit Zemanek􀀃 Master Computer Science University of Amsterdam Amsterdam, Netherlands [vit.zemanek@student.uva.nl](vit.zemanek@student.uva.nl) Yixin Hu􀀃 Master Computer Science Vrije Universiteit Amsterdam, Netherlands [y.hu5@student.vu.nl](y.hu5@student.vu.nl) Pepijn de Reus Master Arti􀀂cial Intelligence University of Amsterdam Amsterdam, Netherlands [p.dereus@uva.nl](p.dereus@uva.nl) Ana Oprescu Complex Cyber Infrastructure University of Amsterdam Amsterdam, Netherlands [a.m.oprescu@uva.nl](a.m.oprescu@uva.nl) Ivano Malavolta S2 research group Vrije Universiteit Amsterdam, Netherlands [i.malavolta@vu.nl](i.malavolta@vu.nl) Abstract—With the increased use of Arti􀀂cial Intelligence (AI), concerns about AI’s energy consumption are increasing as well. This paper investigates the impact of k-anonymisation and dataset characteristics on energy consumption during machine learning (ML) training. Using three datasets from the UCI Machine Learning Repository, we analyze the energy ef􀀂ciency of ML algorithms—Random Forest (RF), k-Nearest neighbours (KNN), and Logistic Regression (LR)—trained on both kanonymised and original datasets. Our experiment reveals that kanonymisation signi􀀂cantly reduces energy consumption during Random Forest (RF) and Logistic Regression (LR) training. Additionally, we 􀀂nd that k-anonymisation leads to greater energy savings in Logistic Regression (LR) training if more features are present in the dataset. However, we also 􀀂nd that the energy savings do not hold in the KNN case, except for one feature case. These 􀀂ndings are backed by Aligned Ranked Transform Analysis of Variance on empirically measured energy consumption data. Our work strengthens the need for further empirical exploration into energy

FAQs

What does the paper analyze regarding machine learning energy use?

It studies how k-anonymisation and dataset characteristics affect energy consumption during ML training, focusing on different algorithms and data variants.

Which machine learning algorithms are evaluated in the experiments?

Random Forest (RF), k-Nearest Neighbours (KNN), and Logistic Regression (LR) are trained on both original and k-anonymised datasets.

What key findings does the paper report about k-anonymisation?

k-anonymisation significantly reduces energy consumption for RF and LR, increases energy savings for LR with more dataset features, and does not generally hold for KNN except in a one-feature case.

Aug 4, 2026

Upload by Skyler