Abstract
Deep Neural Networks (DNNs) are an application class that benefit from being distributed across the edge and cloud. A DNN is partitioned such that specific layers of the DNN are deployed onto the edge and the cloud to meet performance and privacy objectives. However, there is limited understanding of: whether and how evolving operational conditions (increased CPU and memory utilization at the edge or reduced data transfer rates between the edge and cloud) affect the performance of already deployed DNNs, and whether a new partition configuration is required to maximize performance. A DNN that adapts to changing operational conditions is referred to as an 'adaptive DNN'. This paper investigates whether there is a case for adaptive DNNs by considering four questions: (i) Are DNNs sensitive to operational conditions? (ii) How sensitive are DNNs to operational conditions? (iii) Do individual or a combination of operational conditions equally affect DNNs? (iv) Is DNN partitioning sensitive to hardware architectures? The exploration is carried out in the context of 8 pre-Trained DNN models and the results presented are from analyzing nearly 8 million data points. The results highlight that network conditions affect DNN performance more than CPU or memory related operational conditions. Repartitioning is noted to provide a performance gain in a number of cases, but a specific trend is not noted in relation to the underlying hardware architecture. Nonetheless, the need for adaptive DNNs is confirmed.
Original language | English |
---|---|
Title of host publication | Proceedings - 2021 IEEE 14th International Conference on Cloud Computing, CLOUD 2021 |
Editors | Claudio Agostino Ardagna, Carl K. Chang, Ernesto Daminai, Rajiv Ranjan, Zhongjie Wang, Robert Ward, Jia Zhang, Wensheng Zhang |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 43-52 |
Number of pages | 10 |
ISBN (Electronic) | 9781665400602 |
DOIs | |
Publication status | Published - 13 Nov 2021 |
Event | 14th IEEE International Conference on Cloud Computing, CLOUD 2021 - Virtual, Online, United States Duration: 05 Sept 2021 → 11 Sept 2021 |
Publication series
Name | IEEE International Conference on Cloud Computing, CLOUD |
---|---|
Volume | 2021-September |
ISSN (Print) | 2159-6182 |
ISSN (Electronic) | 2159-6190 |
Conference
Conference | 14th IEEE International Conference on Cloud Computing, CLOUD 2021 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 05/09/2021 → 11/09/2021 |
Bibliographical note
Publisher Copyright:© 2021 IEEE.
Keywords
- n/a
ASJC Scopus subject areas
- Artificial Intelligence
- Information Systems
- Software