Measuring the Environmental Cost in the Evaluation of Metaheuristics

DOI

10.2991/asum.k.210827.028How to use a DOI?

Keywords

Metaheuristic, Carbon footprint, Computational Experiments

Abstract

Several situations associated with the Sustainable Development Goals can be modeled as optimization problems that, under certain circumstances, can be solved with metaheuristics. In this paper we focus in the environmental impact (carbon footprint) that running such techniques produces. Through the simulation of two typical scenarios in the context of evolutionary optimization, we aim to raise awareness about taking into account such impact when designing experiments. In our simulations we found that a) both, the characteristics of the problem and of the solver (metaheuristics) can significantly increase electricity consumption and carbon emissions; and b) running experiments in certain countries have a higher social cost than in others. We suggest some strategies for reducing the environmental impact when conducting experiments in this field.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Pavel Novoa-Hernández
AU  - Amilkar Puris
AU  - David A. Pelta
PY  - 2021
DA  - 2021/08/30
TI  - Measuring the Environmental Cost in the Evaluation of Metaheuristics
BT  - Joint Proceedings of the 19th World Congress of the International Fuzzy Systems Association (IFSA), the 12th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), and the 11th International Summer School on Aggregation Operators (AGOP)
PB  - Atlantis Press
SP  - 203
EP  - 210
SN  - 2589-6644
UR  - https://doi.org/10.2991/asum.k.210827.028
DO  - 10.2991/asum.k.210827.028
ID  - Novoa-Hernández2021
ER  -