2011 Proceedings IEEE INFOCOM 2011
DOI: 10.1109/infcom.2011.5935062
|View full text |Cite
|
Sign up to set email alerts
|

Scheduling design and analysis for end-to-end heterogeneous flows in an avionics network

Abstract: Abstract-Avionics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
13
0

Year Published

2012
2012
2020
2020

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 18 publications
(13 citation statements)
references
References 23 publications
0
13
0
Order By: Relevance
“…This is achieved by using data concentrators that receive data from nearby sensors or other equipment on a many to one principle and then forward an assembled complex message to the final destination (cockpit) on a single cable. Different message have different periodicity or may even be aperiodic which requires the use of the concept of scheduler that is subject to intense research such as in [11] [22] [23]. It is the scheduler that computes sequence numbers.…”
Section: Fig 6 Concrete Layer Architecture For Periodic Messagesmentioning
confidence: 99%
“…This is achieved by using data concentrators that receive data from nearby sensors or other equipment on a many to one principle and then forward an assembled complex message to the final destination (cockpit) on a single cable. Different message have different periodicity or may even be aperiodic which requires the use of the concept of scheduler that is subject to intense research such as in [11] [22] [23]. It is the scheduler that computes sequence numbers.…”
Section: Fig 6 Concrete Layer Architecture For Periodic Messagesmentioning
confidence: 99%
“…Such switch architecture let multiple flows share queues, which is fundamentally different from the per-flow queueing switch architecture that this paper is about. Hua et al [22] also analyzed the real-time behavior of AFDX networks upon switches that runs deficit round robin scheduling. Such queueing mechanism is workconserving [23], which is also fundamentally different from our TDMA scheduling, which is non-work-conserving.…”
Section: Main Body Of Approximation Algorithmmentioning
confidence: 99%
“…From Formula (22) to (23) is because u max corresponds to the total utility of a feasible configuration with a single active flow (see Formula (17)), while U * is the optimum, so u max ≤ U * . As for time complexity, the approximation algorithm …”
mentioning
confidence: 99%
“…Compared with delays experienced at end systems and switches, the propagation latency over a physical link is very small and can be ignored. 10,11 Further, when the initial time jitter imposed by the MUX at source end system is introduced as shown in 'New arrival curves for data flows' section, the transmit latency at source end system is not required to be considered at the first step. Therefore, to compute the end-to-end transmission delay, first, one needs to know the service curves provided by every interconnected switch that the virtual link passes through, and then convolute all the service curves to get the whole one over the path, employing the pay burst only once principle.…”
Section: Sp Muxmentioning
confidence: 99%
“…Thus, it is necessary to consider other advanced scheduling disciplines, such as static priority (SP) queueing and weighted fair queueing. 11 As far as we are concerned, the SP scheduling algorithm with two levels has been present in the new version of the ARINC664 standard. Hence, it is important to investigate the effects of the priority scheduling discipline on the system performance.…”
Section: Introductionmentioning
confidence: 99%