Optimal Distribution of CNN Computations on Edge and Cloud

Paul Leroy, Toon Goedemé

2021

Abstract

In this paper we study the optimal distribution of CNN computations between an edge device and the cloud for a complex IoT application. We propose a pipeline in which we perform experiments with a Jetson Nano and a Raspberry Pi 3B+ as the edge device, and a T2.micro instance from Amazon EC2 as a cloud instance. To answer this generic question, we performed exhaustive experiments on a typical use case, a mobile camera- based street litter detection and mapping application based on a MobilenetV2 model. For our research, we split the computations of the CNN model and divided them over the edge and cloud instances using model partitioning, also including the edge-only and cloud-only configurations. We studied the influence of the specifications of the instances, the input size of the model, the partitioning location of the model and the available network bandwidth on the optimal split position. Depending on the choice of gaining either an economic or performance advantage, we can conclude that a balance between the choice of instances and the calculation mechanism used should be made.

Paper Citation

in Harvard Style

Leroy P. and Goedemé T. (2021). Optimal Distribution of CNN Computations on Edge and Cloud.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 604-613. DOI: 10.5220/0010203706040613

in Bibtex Style

@conference{icaart21,
author={Paul Leroy and Toon Goedemé},
title={Optimal Distribution of CNN Computations on Edge and Cloud},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={604-613},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010203706040613},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Optimal Distribution of CNN Computations on Edge and Cloud
SN - 978-989-758-484-8
AU - Leroy P.
AU - Goedemé T.
PY - 2021
SP - 604
EP - 613
DO - 10.5220/0010203706040613