Optimization of Anomaly Detection in a Microservice System Through Continuous Feedback from Development
(2022) 2022 IEEE/ACM 10th International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS) p.13-20- Abstract
- Monitoring a microservice system may bring a lot of benefits to development teams such as early detection of run-time errors and various performance anomalies. In this study, we explore deep learning (DL) solutions for detection of anomalous system's behavior based on collected monitoring data that consists of applications' and systems' performance metrics. The study is conducted in a collaboration with a Swedish company responsible for ticket and payment management in public transportation. Moreover, we specifically address a shortage of approaches for evaluating DL models without any ground truth data. Hence, we propose a solution design for anomaly detection and reporting alerts inspired by state-of-the-art DL solutions. Furthermore, we... (More)
- Monitoring a microservice system may bring a lot of benefits to development teams such as early detection of run-time errors and various performance anomalies. In this study, we explore deep learning (DL) solutions for detection of anomalous system's behavior based on collected monitoring data that consists of applications' and systems' performance metrics. The study is conducted in a collaboration with a Swedish company responsible for ticket and payment management in public transportation. Moreover, we specifically address a shortage of approaches for evaluating DL models without any ground truth data. Hence, we propose a solution design for anomaly detection and reporting alerts inspired by state-of-the-art DL solutions. Furthermore, we propose a plan for its in-context implementation and evaluation empowered by feedback from the development team. Through continuous feedback from development, the labeled data is generated and used for optimization of the DL model. In this way, a microservice system may leverage DL solutions to address rising challenges within its architecture. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/e024c495-ee65-4f3a-a167-0bd0aff6c9c3
- author
- Hrusto, Adha LU ; Engström, Emelie LU and Runeson, Per LU
- organization
- publishing date
- 2022-05-16
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- IEEE/ACM 10th International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS 2022)
- pages
- 13 - 20
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2022 IEEE/ACM 10th International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS)
- conference location
- Pittsburgh, PA, United States
- conference dates
- 2022-05-16 - 2022-05-16
- external identifiers
-
- scopus:85135201073
- ISBN
- 978-1-4503-9334-8
- 978-1-6654-6238-9
- DOI
- 10.1145/3528229.3529382
- project
- Continuous system testing using autonomous monitors
- language
- English
- LU publication?
- yes
- id
- e024c495-ee65-4f3a-a167-0bd0aff6c9c3
- alternative location
- https://ieeexplore.ieee.org/document/9808684
- date added to LUP
- 2022-08-15 10:31:49
- date last changed
- 2024-09-18 16:14:53
@inproceedings{e024c495-ee65-4f3a-a167-0bd0aff6c9c3, abstract = {{Monitoring a microservice system may bring a lot of benefits to development teams such as early detection of run-time errors and various performance anomalies. In this study, we explore deep learning (DL) solutions for detection of anomalous system's behavior based on collected monitoring data that consists of applications' and systems' performance metrics. The study is conducted in a collaboration with a Swedish company responsible for ticket and payment management in public transportation. Moreover, we specifically address a shortage of approaches for evaluating DL models without any ground truth data. Hence, we propose a solution design for anomaly detection and reporting alerts inspired by state-of-the-art DL solutions. Furthermore, we propose a plan for its in-context implementation and evaluation empowered by feedback from the development team. Through continuous feedback from development, the labeled data is generated and used for optimization of the DL model. In this way, a microservice system may leverage DL solutions to address rising challenges within its architecture.}}, author = {{Hrusto, Adha and Engström, Emelie and Runeson, Per}}, booktitle = {{IEEE/ACM 10th International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems (SESoS 2022)}}, isbn = {{978-1-4503-9334-8}}, language = {{eng}}, month = {{05}}, pages = {{13--20}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Optimization of Anomaly Detection in a Microservice System Through Continuous Feedback from Development}}, url = {{http://dx.doi.org/10.1145/3528229.3529382}}, doi = {{10.1145/3528229.3529382}}, year = {{2022}}, }