Modelling Fault Dependencies when Execution Time Budgets are Exceeded

David Griffin; Benjamin Lesage; Frank Soboczenski; Iain Bate; Robert I. Davis

doi:10.1145/2834848.2834870

Modelling Fault Dependencies when Execution Time Budgets are Exceeded

David Griffin, Benjamin Lesage, Frank Soboczenski, Iain Bate, Robert I. Davis

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Given that real-time systems are specified to a degree of confidence, budget overruns should be expected to occur in a system at some point. When a budget overrun occurs, it is necessary to understand how long such a state persists, in order to determine if the fault tolerance of the system is adequate to handle the problem. However, given the rarity of budget overruns in testing, it cannot be assumed that sufficient data will be available to build an accurate model. Hence this paper presents a new application of Markov Chain based modelling techniques combined with forecasting techniques to determine an appropriate fault model, using Lossy Compression to fit the model to the available data. In addition, a new algorithm, DepET, for generating job execution times with dependencies is given for use in task simulators.

Original language	English
Title of host publication	Proceedings of the 23rd International Conference on Real-Time Networks and Systems
Subtitle of host publication	Proceedings of the 23rd International Conference on Real Time and Networks Systems
Place of Publication	New York
Publisher	ACM
Pages	65-74
ISBN (Print)	978-1-4503-3591-1
DOIs	https://doi.org/10.1145/2834848.2834870
Publication status	Published - Nov 2015
Event	23rd International conference on Real-Time Networks and Systems (RTNS 2015) - , United Kingdom Duration: 4 Nov 2015 → 6 Nov 2015

Conference

Conference	23rd International conference on Real-Time Networks and Systems (RTNS 2015)
Country/Territory	United Kingdom
Period	4/11/15 → 6/11/15

Access to Document

10.1145/2834848.2834870

INRIA International Chair
Davis, R. I.
1/10/14 → 30/09/19
Project: Other project › Research collaboration
PROXIMA - Probabilistic real-time control of mixed criticality multicore and manycore systems
Bate, I. J. & Davis, R. I.
EUROPEAN COMMISSION
1/10/13 → 30/09/16
Project: Research project (funded) › Research

Cite this

Griffin, D., Lesage, B., Soboczenski, F., Bate, I., & Davis, R. I. (2015). Modelling Fault Dependencies when Execution Time Budgets are Exceeded. In Proceedings of the 23rd International Conference on Real-Time Networks and Systems: Proceedings of the 23rd International Conference on Real Time and Networks Systems (pp. 65-74). ACM. https://doi.org/10.1145/2834848.2834870

@inproceedings{0b454748f4884c34818209cb4e9e8eba,

title = "Modelling Fault Dependencies when Execution Time Budgets are Exceeded",

abstract = "Given that real-time systems are specified to a degree of confidence, budget overruns should be expected to occur in a system at some point. When a budget overrun occurs, it is necessary to understand how long such a state persists, in order to determine if the fault tolerance of the system is adequate to handle the problem. However, given the rarity of budget overruns in testing, it cannot be assumed that sufficient data will be available to build an accurate model. Hence this paper presents a new application of Markov Chain based modelling techniques combined with forecasting techniques to determine an appropriate fault model, using Lossy Compression to fit the model to the available data. In addition, a new algorithm, DepET, for generating job execution times with dependencies is given for use in task simulators.",

author = "David Griffin and Benjamin Lesage and Frank Soboczenski and Iain Bate and Davis, {Robert I.}",

year = "2015",

month = nov,

doi = "10.1145/2834848.2834870",

language = "English",

isbn = "978-1-4503-3591-1",

pages = "65--74",

booktitle = "Proceedings of the 23rd International Conference on Real-Time Networks and Systems",

publisher = "ACM",

address = "United States",

note = "23rd International conference on Real-Time Networks and Systems (RTNS 2015) ; Conference date: 04-11-2015 Through 06-11-2015",

}

Griffin, D , Lesage, B , Soboczenski, F , Bate, I & Davis, RI 2015, Modelling Fault Dependencies when Execution Time Budgets are Exceeded. in Proceedings of the 23rd International Conference on Real-Time Networks and Systems: Proceedings of the 23rd International Conference on Real Time and Networks Systems. ACM, New York , pp. 65-74, 23rd International conference on Real-Time Networks and Systems (RTNS 2015), United Kingdom, 4/11/15. https://doi.org/10.1145/2834848.2834870

Modelling Fault Dependencies when Execution Time Budgets are Exceeded. / Griffin, David ; Lesage, Benjamin ; Soboczenski, Frank et al.
Proceedings of the 23rd International Conference on Real-Time Networks and Systems: Proceedings of the 23rd International Conference on Real Time and Networks Systems. New York : ACM, 2015. p. 65-74.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Modelling Fault Dependencies when Execution Time Budgets are Exceeded

AU - Griffin, David

AU - Lesage, Benjamin

AU - Soboczenski, Frank

AU - Bate, Iain

AU - Davis, Robert I.

PY - 2015/11

Y1 - 2015/11

N2 - Given that real-time systems are specified to a degree of confidence, budget overruns should be expected to occur in a system at some point. When a budget overrun occurs, it is necessary to understand how long such a state persists, in order to determine if the fault tolerance of the system is adequate to handle the problem. However, given the rarity of budget overruns in testing, it cannot be assumed that sufficient data will be available to build an accurate model. Hence this paper presents a new application of Markov Chain based modelling techniques combined with forecasting techniques to determine an appropriate fault model, using Lossy Compression to fit the model to the available data. In addition, a new algorithm, DepET, for generating job execution times with dependencies is given for use in task simulators.

AB - Given that real-time systems are specified to a degree of confidence, budget overruns should be expected to occur in a system at some point. When a budget overrun occurs, it is necessary to understand how long such a state persists, in order to determine if the fault tolerance of the system is adequate to handle the problem. However, given the rarity of budget overruns in testing, it cannot be assumed that sufficient data will be available to build an accurate model. Hence this paper presents a new application of Markov Chain based modelling techniques combined with forecasting techniques to determine an appropriate fault model, using Lossy Compression to fit the model to the available data. In addition, a new algorithm, DepET, for generating job execution times with dependencies is given for use in task simulators.

U2 - 10.1145/2834848.2834870

DO - 10.1145/2834848.2834870

M3 - Conference contribution

SN - 978-1-4503-3591-1

SP - 65

EP - 74

BT - Proceedings of the 23rd International Conference on Real-Time Networks and Systems

PB - ACM

CY - New York

T2 - 23rd International conference on Real-Time Networks and Systems (RTNS 2015)

Y2 - 4 November 2015 through 6 November 2015

ER -

Modelling Fault Dependencies when Execution Time Budgets are Exceeded

Abstract

Conference

Access to Document

Projects

INRIA International Chair

PROXIMA - Probabilistic real-time control of mixed criticality multicore and manycore systems

Cite this