Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

External Research Organisations

  • Delft University of Technology
View graph of relations

Details

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024
Subtitle of host publicationProceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI
Pages222-233
Number of pages12
ISBN (electronic)9798400705915
Publication statusPublished - 11 Jun 2024
EventCAIN 2024: 3rd International Conference on AI Engineering – Software Engineering for AI - Lisbon, Portugal
Duration: 14 Apr 202415 Apr 2024

Abstract

Anomaly detection techniques are essential in automating the monitoring of IT systems and operations. These techniques imply that machine learning algorithms are trained on operational data corresponding to a specific period of time and that they are continuously evaluated on newly emerging data. Operational data is constantly changing over time, which affects the performance of deployed anomaly detection models. Therefore, continuous model maintenance is required to preserve the performance of anomaly detectors over time. In this work, we analyze two different anomaly detection model maintenance techniques in terms of the model update frequency, namely blind model retraining and informed model retraining. We further investigate the effects of updating the model by retraining it on all the available data (full-history approach) and only the newest data (sliding window approach). Moreover, we investigate whether a data change monitoring tool is capable of determining when the anomaly detection model needs to be updated through retraining.

Keywords

    AIOps, anomaly detection, concept drift detection, model maintenance, model monitoring

ASJC Scopus subject areas

Cite this

Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World. / Poenaru-Olaru, Lorena; Karpova, Natalia; Miranda da Cruz, Luis et al.
Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI. 2024. p. 222-233.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Poenaru-Olaru, L, Karpova, N, Miranda da Cruz, L, Rellermeyer, JS & Deursen, AV 2024, Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World. in Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI. pp. 222-233, CAIN 2024, Lisbon, Portugal, 14 Apr 2024. https://doi.org/10.1145/3644815.3644961
Poenaru-Olaru, L., Karpova, N., Miranda da Cruz, L., Rellermeyer, J. S., & Deursen, A. V. (2024). Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World. In Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI (pp. 222-233) https://doi.org/10.1145/3644815.3644961
Poenaru-Olaru L, Karpova N, Miranda da Cruz L, Rellermeyer JS, Deursen AV. Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World. In Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI. 2024. p. 222-233 doi: 10.1145/3644815.3644961
Poenaru-Olaru, Lorena ; Karpova, Natalia ; Miranda da Cruz, Luis et al. / Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World. Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI. 2024. pp. 222-233
Download
@inproceedings{eb03077a740e4281855daf2c035d0b17,
title = "Is Your Anomaly Detector Ready for Change?: Adapting AIOps Solutions to the Real World",
abstract = "Anomaly detection techniques are essential in automating the monitoring of IT systems and operations. These techniques imply that machine learning algorithms are trained on operational data corresponding to a specific period of time and that they are continuously evaluated on newly emerging data. Operational data is constantly changing over time, which affects the performance of deployed anomaly detection models. Therefore, continuous model maintenance is required to preserve the performance of anomaly detectors over time. In this work, we analyze two different anomaly detection model maintenance techniques in terms of the model update frequency, namely blind model retraining and informed model retraining. We further investigate the effects of updating the model by retraining it on all the available data (full-history approach) and only the newest data (sliding window approach). Moreover, we investigate whether a data change monitoring tool is capable of determining when the anomaly detection model needs to be updated through retraining.",
keywords = "AIOps, anomaly detection, concept drift detection, model maintenance, model monitoring",
author = "Lorena Poenaru-Olaru and Natalia Karpova and {Miranda da Cruz}, Luis and Rellermeyer, {Jan S.} and Deursen, {Arie van}",
note = "Publisher Copyright: {\textcopyright} 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.; CAIN 2024 : 3rd International Conference on AI Engineering – Software Engineering for AI ; Conference date: 14-04-2024 Through 15-04-2024",
year = "2024",
month = jun,
day = "11",
doi = "10.1145/3644815.3644961",
language = "English",
pages = "222--233",
booktitle = "Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024",

}

Download

TY - GEN

T1 - Is Your Anomaly Detector Ready for Change?

T2 - CAIN 2024

AU - Poenaru-Olaru, Lorena

AU - Karpova, Natalia

AU - Miranda da Cruz, Luis

AU - Rellermeyer, Jan S.

AU - Deursen, Arie van

N1 - Publisher Copyright: © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

PY - 2024/6/11

Y1 - 2024/6/11

N2 - Anomaly detection techniques are essential in automating the monitoring of IT systems and operations. These techniques imply that machine learning algorithms are trained on operational data corresponding to a specific period of time and that they are continuously evaluated on newly emerging data. Operational data is constantly changing over time, which affects the performance of deployed anomaly detection models. Therefore, continuous model maintenance is required to preserve the performance of anomaly detectors over time. In this work, we analyze two different anomaly detection model maintenance techniques in terms of the model update frequency, namely blind model retraining and informed model retraining. We further investigate the effects of updating the model by retraining it on all the available data (full-history approach) and only the newest data (sliding window approach). Moreover, we investigate whether a data change monitoring tool is capable of determining when the anomaly detection model needs to be updated through retraining.

AB - Anomaly detection techniques are essential in automating the monitoring of IT systems and operations. These techniques imply that machine learning algorithms are trained on operational data corresponding to a specific period of time and that they are continuously evaluated on newly emerging data. Operational data is constantly changing over time, which affects the performance of deployed anomaly detection models. Therefore, continuous model maintenance is required to preserve the performance of anomaly detectors over time. In this work, we analyze two different anomaly detection model maintenance techniques in terms of the model update frequency, namely blind model retraining and informed model retraining. We further investigate the effects of updating the model by retraining it on all the available data (full-history approach) and only the newest data (sliding window approach). Moreover, we investigate whether a data change monitoring tool is capable of determining when the anomaly detection model needs to be updated through retraining.

KW - AIOps

KW - anomaly detection

KW - concept drift detection

KW - model maintenance

KW - model monitoring

UR - http://www.scopus.com/inward/record.url?scp=85196547715&partnerID=8YFLogxK

U2 - 10.1145/3644815.3644961

DO - 10.1145/3644815.3644961

M3 - Conference contribution

SP - 222

EP - 233

BT - Proceedings - 2024 IEEE/ACM 3rd International Conference on AI Engineering - Software Engineering for AI, CAIN 2024

Y2 - 14 April 2024 through 15 April 2024

ER -

By the same author(s)