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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Edge computing enables smart IoT-based systems via concurrent and continuousexecution of latency-sensitive machine learning (ML) applications. Theseedge-based machine learning systems are often battery-powered (i.e.,energy-limited). They use heterogeneous resources with diverse computingperformance (e.g., CPU, GPU, and/or FPGAs) to fulfill the latency constraintsof ML applications. The challenge is to allocate user requests for different MLapplications on the Heterogeneous Edge Computing Systems (HEC) with respect toboth the energy and latency constraints of these systems. To this end, we studyand analyze resource allocation solutions that can increase the on-time taskcompletion rate while considering the energy constraint. Importantly, weinvestigate edge-friendly (lightweight) multi-objective mapping heuristics thatdo not become biased toward a particular application type to achieve theobjectives; instead, the heuristics consider "fairness" across the concurrentML applications in their mapping decisions. Performance evaluations demonstratethat the proposed heuristic outperforms widely-used heuristics in heterogeneoussystems in terms of the latency and energy objectives, particularly, at low tomoderate request arrival rates. We observed 8.9% improvement in on-time taskcompletion rate and 12.6% in energy-saving without imposing any significantoverhead on the edge system.

FELARE: Fair Scheduling of Machine Learning Tasks on Heterogeneous Edge Systems