Green AI in Action: Strategic Model Selection for Ensembles in Production

Nienke Nijkamp*, June Sallou, Niels van der Heijden, Luís Cruz

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

3 Downloads (Pure)

Abstract

Integrating Artificial Intelligence (AI) into software systems has significantly enhanced their capabilities while escalating energy demands. Ensemble learning, combining predictions from multiple models to form a single prediction, intensifies this problem due to cumulative energy consumption. This paper presents a novel approach to model selection that addresses the challenge of balancing the accuracy of AI models with their energy consumption in a live AI ensemble system. We explore how reducing the number of models or improving the efficiency of model usage within an ensemble during inference can reduce energy demands without substantially sacrificing accuracy. This study introduces and evaluates two model selection strategies, Static and Dynamic, for optimizing ensemble learning systems' performance while minimizing energy usage. Our results demonstrate that the Static strategy improves the F1 score beyond the baseline, reducing average energy usage from 100% from the full ensemble to 62%. The Dynamic strategy further enhances F1 scores, using on average 76% compared to 100% of the full ensemble. Moreover, we propose an approach that balances accuracy with resource consumption, significantly reducing energy usage without substantially impacting accuracy. This method decreased the average energy usage of the Static strategy from approximately 62% to 14%, and for the Dynamic strategy, from around 76% to 57%. Our field study of Green AI using an operational AI system developed by a large professional services provider shows the practical applicability of adopting energy-conscious model selection strategies in live production environments.
Original languageEnglish
Title of host publicationAIware 2024
Subtitle of host publicationProceedings of the 1st ACM International Conference on AI-Powered Software
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery (ACM)
Pages50-58
Number of pages9
ISBN (Electronic)979-8-4007-0685-1
DOIs
Publication statusPublished - 2024
Event1st ACM International Conference on AI-Powered Software, AIware 2024 - Hotel Armação, Porto de Galinhas, Brazil
Duration: 15 Jul 202416 Jul 2024
https://2024.aiwareconf.org

Conference

Conference1st ACM International Conference on AI-Powered Software, AIware 2024
Abbreviated titleFSE 2024
Country/TerritoryBrazil
CityPorto de Galinhas
Period15/07/2416/07/24
Internet address

Keywords

  • Ensemble Learning
  • Green AI
  • Information Extraction
  • Model Selection

Fingerprint

Dive into the research topics of 'Green AI in Action: Strategic Model Selection for Ensembles in Production'. Together they form a unique fingerprint.

Cite this