Can I read Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations on EtoBox?

Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations by Sánchez-Mompó, Adrián; Mavromatis, Ioannis; Li, Peizheng; Katsaros, Konstantinos; Khan, Aftab is a scholarly article available to read on EtoBox.

What is Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations about?

This study presents an empirical investigation into the energy consumption of Discriminative and Generative AI models within real-world MLOps pipelines. For Discriminative models, we examine various architectures and hyperparameters during training and inference and identify energy-efficient practices. For Generative AI, Large Language Models (LLMs) are assessed, focusing primarily on energy consumption across different model sizes and varying service requests. Our study employs software-based power measurements, ensuring ease of replication across diverse configurations, models, and datasets. We analyse multiple models and hardware setups to uncover correlations among various metrics, identifying key contributors to energy consumption. The results indicate that for Discriminative models, optimising architectures, hyperparameters, and hardware can significantly reduce energy consumption without sacrificing performance. For LLMs, energy efficiency depends on balancing model size, reasoning complexity, and request-handling capacity, as larger models do not necessarily consume more energy when utilisation remains low. This analysis provides practical guidelines for designing green and

Author

Sánchez-Mompó, Adrián; Mavromatis, Ioannis; Li, Peizheng; Katsaros, Konstantinos; Khan, Aftab

Published

2025

Language

EN