Standard

Graph Neural Networks for Metrics Prediction in Microservice Architecture. / Головкина, Анна Геннадьевна; Ружников, Владимир Олегович; Могильников, Дмитрий Алексеевич.

Computational Science and Its Applications – ICCSA 2024 Workshops. 2024. p. 343–357 (Lecture Notes in Computer Science; Vol. 14821).

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

Harvard

Головкина, АГ, Ружников, ВО & Могильников, ДА 2024, Graph Neural Networks for Metrics Prediction in Microservice Architecture. in Computational Science and Its Applications – ICCSA 2024 Workshops. Lecture Notes in Computer Science, vol. 14821, pp. 343–357, The 24th International Conference on Computational Science and Its Applications, ICCSA 2024, Ханой, Viet Nam, 1/07/24. https://doi.org/10.1007/978-3-031-65308-7_24

APA

Головкина, А. Г., Ружников, В. О., & Могильников, Д. А. (2024). Graph Neural Networks for Metrics Prediction in Microservice Architecture. In Computational Science and Its Applications – ICCSA 2024 Workshops (pp. 343–357). (Lecture Notes in Computer Science; Vol. 14821). https://doi.org/10.1007/978-3-031-65308-7_24

Vancouver

Головкина АГ, Ружников ВО, Могильников ДА. Graph Neural Networks for Metrics Prediction in Microservice Architecture. In Computational Science and Its Applications – ICCSA 2024 Workshops. 2024. p. 343–357. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-031-65308-7_24

Author

Головкина, Анна Геннадьевна ; Ружников, Владимир Олегович ; Могильников, Дмитрий Алексеевич. / Graph Neural Networks for Metrics Prediction in Microservice Architecture. Computational Science and Its Applications – ICCSA 2024 Workshops. 2024. pp. 343–357 (Lecture Notes in Computer Science).

BibTeX

@inproceedings{ebc354f4a1d7485cb07698b93d86d8f0,
title = "Graph Neural Networks for Metrics Prediction in Microservice Architecture",
abstract = "The article examines the issues of monitoring performance in microservice architectures. We explore the problem of forecasting performance indicators as well as fault propagation in such systems, which are distributed and have independent service deployments. The paper addresses these issues by proposing a novel approach that uses multimetric time series data to establish causal relationships between microservices and build graph neural networks based on revealed system dependencies. The method{\textquoteright}s goal is to proactively forecast performance indicators and fault propagation in order to assure the resilience and reliability of microservices. Various graph neural network architectures are discussed. The best one DCRNN uses a diffusion convolutional recurrent neural network in a basis and is able to predict well both on data with and without anomalies",
keywords = "Graph neural networks, Metrics prediction, Microservice, microservice preformance",
author = "Головкина, {Анна Геннадьевна} and Ружников, {Владимир Олегович} and Могильников, {Дмитрий Алексеевич}",
year = "2024",
month = aug,
day = "22",
doi = "10.1007/978-3-031-65308-7_24",
language = "English",
isbn = "9783031653070",
series = "Lecture Notes in Computer Science",
publisher = "Springer Nature",
pages = "343–357",
booktitle = "Computational Science and Its Applications – ICCSA 2024 Workshops",
note = "The 24th International Conference on Computational Science and Its Applications, ICCSA 2024, ICCSA ; Conference date: 01-07-2024 Through 04-07-2024",
url = "https://2024.iccsa.org/",

}

RIS

TY - GEN

T1 - Graph Neural Networks for Metrics Prediction in Microservice Architecture

AU - Головкина, Анна Геннадьевна

AU - Ружников, Владимир Олегович

AU - Могильников, Дмитрий Алексеевич

PY - 2024/8/22

Y1 - 2024/8/22

N2 - The article examines the issues of monitoring performance in microservice architectures. We explore the problem of forecasting performance indicators as well as fault propagation in such systems, which are distributed and have independent service deployments. The paper addresses these issues by proposing a novel approach that uses multimetric time series data to establish causal relationships between microservices and build graph neural networks based on revealed system dependencies. The method’s goal is to proactively forecast performance indicators and fault propagation in order to assure the resilience and reliability of microservices. Various graph neural network architectures are discussed. The best one DCRNN uses a diffusion convolutional recurrent neural network in a basis and is able to predict well both on data with and without anomalies

AB - The article examines the issues of monitoring performance in microservice architectures. We explore the problem of forecasting performance indicators as well as fault propagation in such systems, which are distributed and have independent service deployments. The paper addresses these issues by proposing a novel approach that uses multimetric time series data to establish causal relationships between microservices and build graph neural networks based on revealed system dependencies. The method’s goal is to proactively forecast performance indicators and fault propagation in order to assure the resilience and reliability of microservices. Various graph neural network architectures are discussed. The best one DCRNN uses a diffusion convolutional recurrent neural network in a basis and is able to predict well both on data with and without anomalies

KW - Graph neural networks

KW - Metrics prediction

KW - Microservice

KW - microservice preformance

UR - https://www.mendeley.com/catalogue/9dc9bd55-b929-32f2-b376-fa5e17f83630/

U2 - 10.1007/978-3-031-65308-7_24

DO - 10.1007/978-3-031-65308-7_24

M3 - Conference contribution

SN - 9783031653070

T3 - Lecture Notes in Computer Science

SP - 343

EP - 357

BT - Computational Science and Its Applications – ICCSA 2024 Workshops

T2 - The 24th International Conference on Computational Science and Its Applications, ICCSA 2024

Y2 - 1 July 2024 through 4 July 2024

ER -

ID: 123266494