English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Edge computing offers an additional layer of compute infrastructure closer tothe data source before raw data from privacy-sensitive and performance-criticalapplications is transferred to a cloud data center. Deep Neural Networks (DNNs)are one class of applications that are reported to benefit from collaborativelycomputing between the edge and the cloud. A DNN is partitioned such thatspecific layers of the DNN are deployed onto the edge and the cloud to meetperformance and privacy objectives. However, there is limited understanding of:(a) whether and how evolving operational conditions (increased CPU and memoryutilization at the edge or reduced data transfer rates between the edge and thecloud) affect the performance of already deployed DNNs, and (b) whether a newpartition configuration is required to maximize performance. A DNN that adaptsto changing operational conditions is referred to as an 'adaptive DNN'. Thispaper investigates whether there is a case for adaptive DNNs in edge computingby considering three questions: (i) Are DNNs sensitive to operationalconditions? (ii) How sensitive are DNNs to operational conditions? (iii) Doindividual or a combination of operational conditions equally affect DNNs? (iv)Is DNN partitioning sensitive to hardware architectures on the cloud/edge? Theexploration is carried out in the context of 8 pre-trained DNN models and theresults presented are from analyzing nearly 8 million data points. The resultshighlight that network conditions affects DNN performance more than CPU ormemory related operational conditions. Repartitioning is noted to provide aperformance gain in a number of cases, but a specific trend was not noted inrelation to its correlation to the underlying hardware architecture.Nonetheless, the need for adaptive DNNs is confirmed.

A Case For Adaptive Deep Neural Networks in Edge Computing