Authors:
Paul Albert Leroy
and
Toon Goedemé
Affiliation:
PSI-EAVISE, KU Leuven, Campus De Nayer, Belgium
Keyword(s):
Fog Computing, Edge, Cloud, CNN Model Partitioning.
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 conclud
e that a balance between the choice of instances and the calculation mechanism used should be made.
(More)