Machine learning applied to failure detection

Wenbin Qi; Jingyi Zhao

doi:10.1117/12.3004136

11 October 2023 Machine learning applied to failure detection

Wenbin Qi, Jingyi Zhao

Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 1280021 (2023) https://doi.org/10.1117/12.3004136
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China

Abstract

The operation of distributed systems highly depends on reliable and continuous communication between nodes. The failure detection phase thus plays an important role in system unavailability. Previous studies have shown potentials for LSTM based failure detectors but the heavy computation cost remains a problem. We propose a technique to reduce the computation time of LSTM based FD by performing forecasting instead of making one prediction at a time (i.e. predicting multiple timestamps at once). Our method achieves better computation time compared to previous LSTM FDs but falls short of BFD. We discuss the heavy computation cost of back-propagation of LSTM and the high frequency nature of FD tasks and conclude that LSTM isn’t likely to be the best fit for Machine Learning based FD.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Wenbin Qi and Jingyi Zhao "Machine learning applied to failure detection", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 1280021 (11 October 2023); https://doi.org/10.1117/12.3004136

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Machine learning

Computation time

Systems modeling

Neural networks

Performance modeling

Computer science

RELATED CONTENT

Development of dialogue system based on deep learning
Proceedings of SPIE (March 07 2022)

Predicting the dynamics of a capsule shaped equilibrium curve chaotic...
Proceedings of SPIE (June 07 2024)

Research on credit assessment and prediction based on deep learning
Proceedings of SPIE (October 13 2022)

Sparse heterogeneous grid traffic prediction with cross adaptive multi graph...
Proceedings of SPIE (December 01 2023)

Evaluation of CNN as anthropomorphic model observer
Proceedings of SPIE (March 10 2017)

Active learning with deep Bayesian neural network for laser control
Proceedings of SPIE (September 07 2018)

Fault location estimation of power grid using graph attention networks
Proceedings of SPIE (March 27 2024)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years