EdgeTuner: Fast Scheduling Algorithm Tuning for Dynamic Edge-Cloud Workloads and Resources

Rui Han, Shilin Wen, Chi Harold Liu, Ye Yuan, Guoren Wang, Lydia Y. Chen

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

15 Citations (Scopus)

Abstract

Edge-cloud jobs are rapidly prevailing in many application domains, posing the challenge of using both resource-strenuous edge devices and elastic cloud resources. Efficient resource allocation on such jobs via scheduling algorithms is essential to guarantee their performance, e.g. latency. Deep reinforcement learning (DRL) is increasingly adopted to make scheduling decisions but faces the conundrum of achieving high rewards at a low training overhead. It is unknown if such a DRL can be applied to timely tune the scheduling algorithms that are adopted in response to fast changing workloads and resources. In this paper, we propose EdgeTuner to effectively leverage DRL to select scheduling algorithms online for edge-cloud jobs. The enabling features of EdgeTuner are sophisticated DRL model that captures complex dynamics of Edge-Cloud jobs/tasks and an effective simulator to emulate the response times of short-running jobs in accordance to dynamically changing scheduling algorithms. EdgeTuner trains DRL agents offline by directly interacting with the simulator. We implement EdgeTuner on Kubernetes scheduler and extensively evaluate it on Kubernetes cluster testbed driven by the production traces. Our results show that EdgeTuner outperforms prevailing scheduling algorithms by achieving significant lower job response time while accelerating DRL training speed by more than 180x.

Original languageEnglish
Title of host publicationINFOCOM 2022 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages880-889
Number of pages10
ISBN (Electronic)9781665458221
DOIs
Publication statusPublished - 2022
Event41st IEEE Conference on Computer Communications, INFOCOM 2022 - Virtual, Online, United Kingdom
Duration: 2 May 20225 May 2022

Publication series

NameProceedings - IEEE INFOCOM
Volume2022-May
ISSN (Print)0743-166X

Conference

Conference41st IEEE Conference on Computer Communications, INFOCOM 2022
Country/TerritoryUnited Kingdom
CityVirtual, Online
Period2/05/225/05/22

Keywords

  • DRL
  • Edge-cloud workloads
  • Kubernetes
  • run-time tuning
  • scheduling algorithm

Fingerprint

Dive into the research topics of 'EdgeTuner: Fast Scheduling Algorithm Tuning for Dynamic Edge-Cloud Workloads and Resources'. Together they form a unique fingerprint.

Cite this