CONTINUER: maintaining distributed DNN services during edge failures

Ayesha Abdul Majeed, Peter Kilpatrick, Ivor Spence, Blesson Varghese

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Downloads (Pure)

Abstract

Partitioning and deploying Deep Neural Networks (DNNs) across edge nodes may be used to meet performance objectives of applications. However, the failure of a single node may result in cascading failures that will adversely impact the delivery of the service and will result in failure to meet specific objectives. The impact of these failures needs to be minimised at runtime. Three techniques are explored in this paper, namely repartitioning, early-exit and skip-connection. When an edge node fails, the repartitioning technique will repartition and redeploy the DNN thus avoiding the failed nodes. The early exit technique makes provision for a request to exit (early)before the failed node. The skip connection technique dynamically routes the request by skipping the failed nodes. This paper will leverage trade-offs in accuracy, end-to-end latency and downtime for selecting the best technique given user-defined objectives(accuracy, latency and downtime thresholds) when an edge node fails. To this end, CONTINUER is developed. Two key activities of the framework are estimating the accuracy and latency when using the techniques for distributed DNNs and selecting the best technique. It is demonstrated on a lab-based experimental testbed that CONTINUER estimates accuracy and latency when using the techniques with no more than an average error of 0.28% and13.06%, respectively and selects the suitable technique with a low overhead of no more than 16.82 milliseconds and an accuracy of up to 99.86%.
Original languageEnglish
Title of host publication2022 IEEE International conference on edge computing and communications (EDGE 2022)
EditorsClaudio Agostino Ardagna, Hongyi Bian, Carl K. Chang, Rong N. Chang, Ernesto Damiani, Gabriele Elia, Qiang He, Vicenç Puig, Robert Ward, Fatos Xhafa, Jia Zhang
Place of PublicationPiscataway, NJ
PublisherIEEE Computer Society
Pages143-152
Number of pages10
ISBN (Electronic)9781665481403
ISBN (Print)9781665481410
DOIs
Publication statusPublished - 24 Aug 2022
EventIEEE International Conference on Edge Computing and Communications - Barcelona, Spain
Duration: 11 Jul 202216 Jul 2022
https://conferences.computer.org/edge/2022/

Publication series

NameIEEE International conference on edge computing and communications
ISSN (Print)2767-990X
ISSN (Electronic)2767-9918

Conference

ConferenceIEEE International Conference on Edge Computing and Communications
Abbreviated titleIEEE EDGE 2022
Country/TerritorySpain
CityBarcelona
Period11/07/2216/07/22
Internet address

Keywords

  • Distributed DNNs
  • Edge computing
  • Failures

Fingerprint

Dive into the research topics of 'CONTINUER: maintaining distributed DNN services during edge failures'. Together they form a unique fingerprint.

Cite this