Study of Load Balancing Technique with Variable Threshold on Server Status in SDN Environment 


Vol. 49,  No. 11, pp. 1566-1573, Nov.  2024
10.7840/kics.2024.49.11.1566


PDF
  Abstract

AI, big data, deep learning, and cloud technologies have made modern network environments complex, necessitating the flow of diverse data. In such environments, handling users' diverse data requires an efficient network configuration of data centers composed of numerous servers, rather than a single server. However, traditional network methods are vendor-dependent, managing each server individually, which increases the management overhead for data center servers. To address this efficiently, SDN technology has gained attention, emphasizing the importance of load balancing techniques for handling data requests across servers. This paper proposes a load balancing technique that addresses these delay issues by monitoring server load levels and redirecting data processing to other servers with relatively lower loads when a server reaches a certain threshold, thereby enhancing the availability of all servers. Specifically, by automatically calculating and dynamically applying thresholds based on the average load of all servers, the proposed method aims to achieve optimal load balancing for the current network traffic. Through the experiment, it was confirmed that the server's load rate did not exceed the threshold and become overloaded. In the case of the comparison method, with a fixed threshold, one server's load rate increased to 96.39% when a large number of packets were received. However, with the proposed method, all servers recorded a load rate of below 90%. This demonstrates that optimal load balancing is achieved without the administrator needing to find the optimal threshold.

  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.


  Related Articles
  Cite this article

[IEEE Style]

K. Lee and T. Kwon, "Study of Load Balancing Technique with Variable Threshold on Server Status in SDN Environment," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 11, pp. 1566-1573, 2024. DOI: 10.7840/kics.2024.49.11.1566.

[ACM Style]

Kang-uk Lee and Tae-wook Kwon. 2024. Study of Load Balancing Technique with Variable Threshold on Server Status in SDN Environment. The Journal of Korean Institute of Communications and Information Sciences, 49, 11, (2024), 1566-1573. DOI: 10.7840/kics.2024.49.11.1566.

[KICS Style]

Kang-uk Lee and Tae-wook Kwon, "Study of Load Balancing Technique with Variable Threshold on Server Status in SDN Environment," The Journal of Korean Institute of Communications and Information Sciences, vol. 49, no. 11, pp. 1566-1573, 11. 2024. (https://doi.org/10.7840/kics.2024.49.11.1566)
Vol. 49, No. 11 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880