Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)

Deep Learning - Based Forecasting of Task Failures in Cloud Data Centers

Authors
P. Bharath Kumar Chowdary1, Ameti Sadhana1, 2, Chintamaneni Mahalakshmi1, 3, Kamala Priya Vege1, 4, Kalakata Yagna Reddy2, 1, *, Srija Tulasi1, 5
1Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering & Technology, Hyderabad, Telangana, 500090, India
2JPMorgan Chase & Co, Hyderabad, Telangana, 500081, India
3Experian Services India Private Limited, Hyderabad, Telangana, 500081, India
4Providence Global Center India, Hyderabad, Telangana, 500081, India
5Google India, Hyderabad, Telangana, 500084, India
*Corresponding author. Email: yagnareddy992@gmail.com
Corresponding Author
Kalakata Yagna Reddy
Available Online 21 December 2023.
DOI
10.2991/978-94-6463-314-6_17How to use a DOI?
Keywords
Task failure; Reliability; CNN-LSTM; Bi-LSTM; Hidden Markov Model
Abstract

A cloud data center empowers organizations to improve their performance, scalability and security by providing tools to store data and the infrastructure required to run applications. Its main objective is to provide high service reliability and service availability. But the lack of proper hardware and software resources may cause task and job failures which disrupt the services supported by the cloud data center. To recover to the pre-failure condition, many failures need a significant investment of time and resources.

An innovative failure prediction algorithm that harnesses the capabilities of multiple models, including the Hidden Markov Model (HMM), Hybrid CNN-LSTM (Long Short Term Memory), and Bi-LSTM (Bidirectional Long Short Term Memory) is proposed. This pioneering approach aims to proactively mitigate resource wastage in cloud environments by predicting task or job failures before they occur. Our ultimate goal is to categorize tasks as either successful or failed, and our research has shown that Bi-LSTM, among these models, emerges as the most promising choice, underscoring its potential to revolutionize task failure prediction in cloud computing.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)
Series
Atlantis Highlights in Computer Sciences
Publication Date
21 December 2023
ISBN
978-94-6463-314-6
ISSN
2589-4900
DOI
10.2991/978-94-6463-314-6_17How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - P. Bharath Kumar Chowdary
AU  - Ameti Sadhana
AU  - Chintamaneni Mahalakshmi
AU  - Kamala Priya Vege
AU  - Kalakata Yagna Reddy
AU  - Srija Tulasi
PY  - 2023
DA  - 2023/12/21
TI  - Deep Learning - Based Forecasting of Task Failures in Cloud Data Centers
BT  - Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)
PB  - Atlantis Press
SP  - 170
EP  - 178
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-314-6_17
DO  - 10.2991/978-94-6463-314-6_17
ID  - Chowdary2023
ER  -