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 growing deployment of Internet of Things (IoT) and machine learning (ML)applications, which need to leverage computation on edge and cloud resources,it is important to develop algorithms and tools to place these distributedcomputations to optimize their performance. We address the problem of optimallyplacing computations (described as directed acyclic graphs (DAGs)) on a set ofmachines to maximize the steady-state throughput for pipelined inputs.Traditionally, such optimization has focused on a different metric, minimizingsingle-shot makespan, and a well-known algorithm is the Heterogeneous EarliestFinish Time (HEFT) algorithm. Maximizing throughput however, is more suitablefor many real-time, edge, cloud and IoT applications, we present a differentscheduling algorithm, namely Throughput HEFT (TPHEFT). Further, we present twothroughput-oriented enhancements which can be applied to any baseline schedule,that we refer to as "node splitting" (SPLIT) and "task duplication" (DUP). Inorder to implement and evaluate these algorithms, we built new subsystems andplugins for an open-source dispersed computing framework called Jupiter.Experiments with varying DAG structures indicate that: 1) TPHEFT cansignificantly improve throughput performance compared to HEFT (up to 2.3 timesin our experiments), with greater gains when there is less degree ofparallelism in the DAG, 2) Node splitting can potentially improve performanceover a baseline schedule, with greater gains when there's an imbalancedallocation of computation or inter-task communication, and 3) Task duplicationgenerally gives improvements only when running upon a baseline that placescommunication over slow links. To our knowledge, this is the first study topresent a systematic experimental implementation and exploration ofthroughput-enhancing techniques for dispersed computing on real testbeds.

Design and Experimental Evaluation of Algorithms for Optimizing the Throughput of Dispersed Computing