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

arXiv: https://arxiv.org/abs/2405.17451 · HTML: https://mlsanity.com/paper/2405.17451/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 21 May 2024.

## Builds on (most cited first, 18 of 18)

- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [A Benchmark for Lease Contract Review](https://mlsanity.com/paper/2010.10386/) (2020)
- [Watt For What: Rethinking Deep Learning's Energy-Performance Relationship](https://mlsanity.com/paper/2310.06522/) (2023)
- [Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks](https://mlsanity.com/paper/2202.11782/) (2022)
- [Towards Inference Efficient Deep Ensemble Learning](https://mlsanity.com/paper/2301.12378/) (2023)
- [Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks](https://mlsanity.com/paper/1907.12659/) (2019)
- [Differentiable Model Selection for Ensemble Learning](https://mlsanity.com/paper/2211.00251/) (2022)
- [A post-selection algorithm for improving dynamic ensemble selection methods](https://mlsanity.com/paper/2309.14307/) (2023)

## Built on by (most cited first, 2 of 2)

- [Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices](https://mlsanity.com/paper/2506.01774/) (2025)
- [Choosing to Be Green: Advancing Green AI via Dynamic Model Selection](https://mlsanity.com/paper/2509.19996/) (2025)

## Abstract (arXiv)

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.