An Improvement of Multi-Cluster Stability of Private Cloud Systems through LSTM-Based CPU Usage Prediction 


Vol. 47,  No. 8, pp. 1081-1095, Aug.  2022
10.7840/kics.2022.47.8.1081


PDF
  Abstract

In this paper, when building a cluster in a Private-cloud introduced by several companies, and architecture using dedicated available resources configured for HA as a shared virtual cluster that is used jointly by multiple clusters was proposed and designed and verified through performance demonstration. In this study, to solve the problem of the dedicated file system for each vendor, the dependency problem was solved by applying the file system based on the IETF standard technology without changing the current operating environment. In addition, performance tests have demonstrated the practicality of reducing disaster recovery time by approximately 75% compared to demonstrating service recovery within two hours in an environment. In particular, after measuring the variable resource utilization of each cluster to ensure the performance of the service, the optimal cluster for continuity can be selected through the LSTM based on the RNN algorithm.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. Park and Y. Kim, "An Improvement of Multi-Cluster Stability of Private Cloud Systems through LSTM-Based CPU Usage Prediction," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 8, pp. 1081-1095, 2022. DOI: 10.7840/kics.2022.47.8.1081.

[ACM Style]

Seon-cheol Park and Young-han Kim. 2022. An Improvement of Multi-Cluster Stability of Private Cloud Systems through LSTM-Based CPU Usage Prediction. The Journal of Korean Institute of Communications and Information Sciences, 47, 8, (2022), 1081-1095. DOI: 10.7840/kics.2022.47.8.1081.

[KICS Style]

Seon-cheol Park and Young-han Kim, "An Improvement of Multi-Cluster Stability of Private Cloud Systems through LSTM-Based CPU Usage Prediction," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 8, pp. 1081-1095, 8. 2022. (https://doi.org/10.7840/kics.2022.47.8.1081)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880