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

With the emergence of edge computing, the problem of offloading jobs betweenan Edge Device (ED) and an Edge Server (ES) received significant attention inthe past. Motivated by the fact that an increasing number of applications areusing Machine Learning (ML) inference, we study the problem of offloadinginference jobs by considering the following novel aspects: 1) in contrast to atypical computational job, the processing time of an inference job depends onthe size of the ML model, and 2) recently proposed Deep Neural Networks (DNNs)for resource-constrained devices provide the choice of scaling the model size.We formulate an assignment problem with the aim of maximizing the totalinference accuracy of n data samples available at the ED, subject to a timeconstraint T on the makespan. We propose an approximation algorithm AMR2, andprove that it results in a makespan at most 2T, and achieves a total accuracythat is lower by a small constant from optimal total accuracy. As proof ofconcept, we implemented AMR2 on a Raspberry Pi, equipped with MobileNet, and isconnected to a server equipped with ResNet, and studied the total accuracy andmakespan performance of AMR2 for image classification application.

Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint