Home // ICAS 2012, The Eighth International Conference on Autonomic and Autonomous Systems // View article

A Dynamic Load Balancing Model Based on Negative Feedback and Exponential Smoothing Estimation

Authors:
Di Yuan
Shuai Wang
Xinya Sun

Keywords: load balancing; dynamic algorithm; negative feedback; exponential smoothing estimation; throughput

Abstract:
Server clusters can be used to manage the massive number of requests that a hot website will receive, so as to meet the rapid development of Internet application. The Linux Virtual Server provides a good solution for cluster revision, and there is software that can be used for management and monitoring. However, the scheduling algorithms of Linux Virtual Server are not sufficient to deal with the heavy load balancing required today. A dynamic load balancing scheduling algorithm has been proposed to solve the problems of static algorithms, but we find that there are some drawbacks in actual use. In this paper, we suggest an improved dynamic load balancing model that overcomes the limits or drawbacks of the simple dynamic algorithm. In the suggested model, negative feedback and exponential smoothing estimation methods have been used to improve the load balancing effect. Besides, service response time has been used to adjust the weight variation to achieve better effect. The suggested model is implemented in our dynamic load balancing algorithm. Experiments show that, our algorithm can achieve better performance than the existing static and dynamic algorithms.

Pages: 32 to 37

Copyright: Copyright (c) IARIA, 2012

Publication date: March 25, 2012

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-187-8

Location: St. Maarten, The Netherlands Antilles

Dates: from March 25, 2012 to March 30, 2012