Home > Research > Publications & Outputs > Providing Fault Tolerance via Complex Event Pro...

Research

Electronic data

  • pft

    Rights statement: © ACM, 2019. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the 9th International Conference on the Internet of Things, IoT 2019 http://doi.acm.org/10.1145/3365871.3365872

    Accepted author manuscript, 3.15 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems. / Power, Alexander; Kotonya, Gerald.
Proceedings of the 9th International Conference on the Internet of Things, IoT 2019. New York: ACM, 2019. 1.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Power, A & Kotonya, G 2019, Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems. in Proceedings of the 9th International Conference on the Internet of Things, IoT 2019., 1, ACM, New York. https://doi.org/10.1145/3365871.3365872

APA

Power, A., & Kotonya, G. (2019). Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems. In Proceedings of the 9th International Conference on the Internet of Things, IoT 2019 Article 1 ACM. https://doi.org/10.1145/3365871.3365872

Vancouver

Power A, Kotonya G. Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems. In Proceedings of the 9th International Conference on the Internet of Things, IoT 2019. New York: ACM. 2019. 1 doi: 10.1145/3365871.3365872

Author

Power, Alexander ; Kotonya, Gerald. / Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems. Proceedings of the 9th International Conference on the Internet of Things, IoT 2019. New York : ACM, 2019.

Bibtex

@inproceedings{14988cc4fc264627b139f12bb2715de5,
title = "Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems",
abstract = "Fault-tolerance (FT) support is a key challenge for ensuring dependable Internet of Things (IoT) systems. Many existing FT-support mechanisms in IoT are static, tightly coupled, inflexible implementations that struggle to adapt in dynamic IoT environments. This paper proposes Complex Patterns of Failure (CPoF), an approach to providing reactive and proactive FT using Complex Event Processing (CEP) and Machine Learning (ML). Error-detection strategies are defined as nondeterministic finite automata (NFA) and implemented via CEP systems. Reactive-FT support is monitored and learned from to train ML models that proactively handle imminent future occurrences of known errors. We evaluated CPoF on an indoor agriculture system with experiments that used time and error correlations to preempt battery-depletion failures. We trained predictive models to learn from reactive-FT support and provide preemptive error recovery.",
author = "Alexander Power and Gerald Kotonya",
note = "{\textcopyright} ACM, 2019. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the 9th International Conference on the Internet of Things, IoT 2019 http://doi.acm.org/10.1145/3365871.3365872",
year = "2019",
month = oct,
day = "22",
doi = "10.1145/3365871.3365872",
language = "English",
booktitle = "Proceedings of the 9th International Conference on the Internet of Things, IoT 2019",
publisher = "ACM",

}

RIS

TY - GEN

T1 - Providing Fault Tolerance via Complex Event Processing and Machine Learning for IoT Systems

AU - Power, Alexander

AU - Kotonya, Gerald

N1 - © ACM, 2019. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the 9th International Conference on the Internet of Things, IoT 2019 http://doi.acm.org/10.1145/3365871.3365872

PY - 2019/10/22

Y1 - 2019/10/22

N2 - Fault-tolerance (FT) support is a key challenge for ensuring dependable Internet of Things (IoT) systems. Many existing FT-support mechanisms in IoT are static, tightly coupled, inflexible implementations that struggle to adapt in dynamic IoT environments. This paper proposes Complex Patterns of Failure (CPoF), an approach to providing reactive and proactive FT using Complex Event Processing (CEP) and Machine Learning (ML). Error-detection strategies are defined as nondeterministic finite automata (NFA) and implemented via CEP systems. Reactive-FT support is monitored and learned from to train ML models that proactively handle imminent future occurrences of known errors. We evaluated CPoF on an indoor agriculture system with experiments that used time and error correlations to preempt battery-depletion failures. We trained predictive models to learn from reactive-FT support and provide preemptive error recovery.

AB - Fault-tolerance (FT) support is a key challenge for ensuring dependable Internet of Things (IoT) systems. Many existing FT-support mechanisms in IoT are static, tightly coupled, inflexible implementations that struggle to adapt in dynamic IoT environments. This paper proposes Complex Patterns of Failure (CPoF), an approach to providing reactive and proactive FT using Complex Event Processing (CEP) and Machine Learning (ML). Error-detection strategies are defined as nondeterministic finite automata (NFA) and implemented via CEP systems. Reactive-FT support is monitored and learned from to train ML models that proactively handle imminent future occurrences of known errors. We evaluated CPoF on an indoor agriculture system with experiments that used time and error correlations to preempt battery-depletion failures. We trained predictive models to learn from reactive-FT support and provide preemptive error recovery.

U2 - 10.1145/3365871.3365872

DO - 10.1145/3365871.3365872

M3 - Conference contribution/Paper

BT - Proceedings of the 9th International Conference on the Internet of Things, IoT 2019

PB - ACM

CY - New York

ER -