Skip to main navigation Skip to search Skip to main content

ECSRL: A Learning-Based Scheduling Framework for AI Workloads in Heterogeneous Edge-Cloud Systems

  • Changyao Lin
  • , Ziyang Zhang
  • , Huan Li
  • , Jie Liu
  • Harbin Institute of Technology
  • Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent advances in both lightweight models and edge computing make it possible for inference tasks to be executed concurrently on resource-constrained edge devices. However, our preliminary experiments show that the execution of different lightweight models on edge devices may lead to a performance downgrade. In this paper, we propose a Learning-Based Scheduling Framework - -ECSRL, to optimize the latency and power consumption for those inference tasks running in heterogeneous Edge-Cloud systems.

Original languageEnglish
Title of host publicationSenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems
PublisherAssociation for Computing Machinery, Inc
Pages386-387
Number of pages2
ISBN (Electronic)9781450390972
DOIs
StatePublished - 15 Nov 2021
Externally publishedYes
Event19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021 - Hybrid, Coimbra, Portugal
Duration: 15 Nov 202117 Nov 2021

Publication series

NameSenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems

Conference

Conference19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021
Country/TerritoryPortugal
CityHybrid, Coimbra
Period15/11/2117/11/21

Keywords

  • Heterogeneous Edge Computing
  • Reinforcement Learning
  • Task Scheduling

Fingerprint

Dive into the research topics of 'ECSRL: A Learning-Based Scheduling Framework for AI Workloads in Heterogeneous Edge-Cloud Systems'. Together they form a unique fingerprint.

Cite this