ESAVE: Estimating Server and Virtual Machine Energy

Abstract

Sustainable software engineering has received a lot of attention in recent times, as we witness an ever-growing slice of energy use, for example, at data centers, as software systems utilize the underlying infrastructure. Characterizing servers for their energy use accurately without being intrusive, is therefore important to make sustainable software deployment choices. In this paper, we introduce ESAVE which is a machine learning-based approach that leverages a small set of hardware attributes to characterize a server or virtual machine's energy usage across different levels of utilization. This is based upon an extensive exploration of multiple ML approaches, with a focus on a minimal set of required attributes, while showcasing good accuracy. Early validations show that ESAVE has only around 12% average prediction error, despite being non-intrusive.

arXiv comment3 pages. To be published in the proceedings of 37th IEEE/ACM International Conference on Automated Software Engineering: Late Breaking Results Track (ASE '22), October 10-14, 2022, Michigan, USA

References in corpus (2)

• XGBoost: A Scalable Tree Boosting System
• Mean Absolute Percentage Error for regression models

Cited by in corpus (3)

• Assessing the Impact of Refactoring Energy-Inefficient Code Patterns on Software Sustainability: An Industry Case Study
• Towards a Knowledge Base of Common Sustainability Weaknesses in Green Software Development
• Calculating Software's Energy Use and Carbon Emissions: A Survey of the State of Art, Challenges, and the Way Ahead