Towards green AI-based software systems: an architecture-centric approach (GAISSA)

TL;DR

This paper presents the GAISSA project, which aims to develop architecture-centric methods and tools to create energy-efficient AI-based software systems, addressing the high computational resource demands of AI training and inference.

Contribution

It introduces the GAISSA project, proposing a novel architecture-centric approach and initial results towards designing green AI systems to improve energy efficiency.

Findings

Initial research results demonstrate potential for energy-efficient AI architectures.

GAISSA provides a framework for modeling and developing green AI systems.

The project aims to support data scientists and engineers with tool-supported methods.

Abstract

Nowadays, AI-based systems have achieved outstanding results and have outperformed humans in different domains. However, the processes of training AI models and inferring from them require high computational resources, which pose a significant challenge in the current energy efficiency societal demand. To cope with this challenge, this research project paper describes the main vision, goals, and expected outcomes of the GAISSA project. The GAISSA project aims at providing data scientists and software engineers tool-supported, architecture-centric methods for the modelling and development of green AI-based systems. Although the project is in an initial stage, we describe the current research results, which illustrate the potential to achieve GAISSA objectives.