Cost of Robustness of Independent WCRT Analysis for CBS of Ethernet AVB Using Eligible Intervals

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

1 Downloads (Pure)

Abstract

The existing worst-case response time (WCRT) analysis for individual priority classes under credit-based shaping (CBS) in Ethernet AVB based on so-called eligible intervals is both independent and tight. This WCRT analysis does not rely on any assumptions on interfering inter-priority streams other than those enforced by the Ethernet standard. A major advantage of this independent analysis is that CBS may be viewed as resource reservation, where allocated bandwidth is both guaranteed and enforced. Although independent analysis provides inter-priority class robustness, it comes at a cost of over-provisioning bandwidth. We illustrate this cost of inter-priority class robustness by means of an example that requires 7.8 times the amount of bandwidth reservation for a given set of streams compared to a different analysis that takes knowledge of inter-priority streams into account.

Original languageEnglish
Title of host publication2023 IEEE 19th International Workshop on Factory Communication Systems, WFCS 2023
EditorsFrank Golatowski, Sampath Kumar Veera Ragavan, Tullio Facchinetti, Lukasz Wisniewski, Marco Porta, Stefano Scanzio
PublisherInstitute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9781665464321
DOIs
Publication statusPublished - 2023
Event19th IEEE International Workshop on Factory Communication Systems, WFCS 2023 - Pavia, Italy
Duration: 26 Apr 202328 Apr 2023

Conference

Conference19th IEEE International Workshop on Factory Communication Systems, WFCS 2023
Country/TerritoryItaly
CityPavia
Period26/04/2328/04/23

Keywords

  • AVB
  • IEEE Ethernet
  • real-Time systems
  • TSN

Fingerprint

Dive into the research topics of 'Cost of Robustness of Independent WCRT Analysis for CBS of Ethernet AVB Using Eligible Intervals'. Together they form a unique fingerprint.

Cite this