Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?

TL;DR

This paper systematically investigates how design decisions in AI-enabled mobile applications affect their accuracy, resource consumption, and environmental impact, aiming to promote greener AI deployment on resource-constrained devices.

Contribution

It provides an empirical framework to assess the trade-offs between accuracy and complexity in mobile AI models and validates profiling tools for greener AI practices.

Findings

Quantifies the impact of design choices on AI model performance and resource use.

Develops tools to help practitioners optimize for greener AI in mobile applications.

Provides empirical data on accuracy-resource trade-offs in neural network deployment.

Abstract

Background: The construction, evolution and usage of complex artificial intelligence (AI) models demand expensive computational resources. While currently available high-performance computing environments support well this complexity, the deployment of AI models in mobile devices, which is an increasing trend, is challenging. Mobile applications consist of environments with low computational resources and hence imply limitations in the design decisions during the AI-enabled software engineering lifecycle that balance the trade-off between the accuracy and the complexity of the mobile applications. Objective: Our objective is to systematically assess the trade-off between accuracy and complexity when deploying complex AI models (e.g. neural networks) to mobile devices, which have an implicit resource limitation. We aim to cover (i) the impact of the design decisions on the achievement of high-accuracy and low resource-consumption implementations; and (ii) the validation of profiling tools for systematically promoting greener AI. Method: This confirmatory registered report consists of a plan to conduct an empirical study to quantify the implications of the design decisions on AI-enabled applications performance and to report experiences of the end-to-end AI-enabled software engineering lifecycle. Concretely, we will implement both image-based and language-based neural networks in mobile applications to solve multiple image classification and text classification problems on different benchmark datasets. Overall, we plan to model the accuracy and complexity of AI-enabled applications in operation with respect to their design decisions and will provide tools for allowing practitioners to gain consciousness of the quantitative relationship between the design decisions and the green characteristics of study.