An empirical study on the Performance and Energy Consumption of AI Containerization Strategies for Computer-Vision Tasks on the Edge

Raluca Maria Hampau, Maurits Kaptein, Robin Van Emden, Thomas Rost, Ivano Malavolta

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Context. The rise of use cases of AI catered towards the Edge, where devices have limited computation power and storage capabilities, motivates the need for better understating of how AI performs and consumes energy. Goal. The aim of this paper is to empirically assess the impact of three different AI containerization strategies on the energy consumption, execution time, CPU, and memory usage for computer-vision tasks on the Edge. Method. In this paper we conduct an experiment with the used containerization strategy as main factor, with three treatments: ONNX Runtime, WebAssembly, and Docker. The subjects of the experiment are four widely-used computer-vision algorithms. We then orchestrate a series of runs where we deploy the four subjects on different generations of Raspberry Pi devices, with different hardware capabilities. A total of 120 runs (per device) are recorded to gather data on energy, execution time, CPU, and memory. Results. We found a statistically significant difference between the three containerization strategies on all dependent variables. Specifically, WebAssembly proves to be a valuable alternative for devices with reduced disk space and computation power. Conclusions. For computer-vision tasks with limited disk space and RAM memory requirements, developers should prefer WebAssembly for deployment. The (non-dockerized) ONNX Runtime resulted to be the best choice in terms of energy consumption and execution time.

Original languageEnglish
Title of host publicationEASE 2022
Subtitle of host publicationProceedings of the ACM International Conference on Evaluation and Assessment in Software Engineering 2022
PublisherAssociation for Computing Machinery
Pages50-59
Number of pages10
ISBN (Electronic)9781450396134
DOIs
Publication statusPublished - Jun 2022
Event26th ACM International Conference on Evaluation and Assessment in Software Engineering, EASE 2022 - Gothenburg, Sweden
Duration: 13 Jun 202215 Jun 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference26th ACM International Conference on Evaluation and Assessment in Software Engineering, EASE 2022
Country/TerritorySweden
CityGothenburg
Period13/06/2215/06/22

Bibliographical note

Funding Information:
As future work, we are planning to investigate on how energy correlates with (additional) performance-related metrics, replicate the experiment by using other AI-based tasks (e.g., conversational AI) and other configurations/hardware platforms. ACKNOWLEDGMENTS This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 871342.

Funding Information:
This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 871342.

Publisher Copyright:
© 2022 Owner/Author.

Funding

As future work, we are planning to investigate on how energy correlates with (additional) performance-related metrics, replicate the experiment by using other AI-based tasks (e.g., conversational AI) and other configurations/hardware platforms. ACKNOWLEDGMENTS This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 871342. This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 871342.

Fingerprint

Dive into the research topics of 'An empirical study on the Performance and Energy Consumption of AI Containerization Strategies for Computer-Vision Tasks on the Edge'. Together they form a unique fingerprint.

Cite this