Share Email Print

Proceedings Paper

Research of dynamic load balancing based on the UMTS-SGSN system
Author(s): Furong Wang; Zuwei Teng
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

During the distributed design of UMTS-SGSN system, the Dynamic Central Tasks Scheduling algorithm (DCTS) with good real-time property is researched to meet the hard requirements of bandwidth and latency of UMTS-SGSN system. Based on the assumption without task migration, Markov queuing network model is used to model UMTS-SGSN system instead of M/M/c queuing model. For single user with one PDP context, DCTS is optimal through the theoretic calculation and simulation. And for single user with not less than one PDP context, the performance of DCTS is discussed through the simulation. In the case of longer service time in data service, DCTS is compared with stochastic scheduling algorithm and cycle scheduling algorithm. Simulation results show that DCTS is better than other two algorithms, and when service time is shorter, three algorithms' performance is approximately same. The performances of the three algorithms in different service time are also analyzed by adjusting the parameter μ of the exponential distribution. Results show that exponential distribution's heavy-tailed effect of the service time leads to deteriorating the efficiency of load balancing and DCTS shall initiate less task migration and decrease system overhead.

Paper Details

Date Published: 28 April 2004
PDF: 10 pages
Proc. SPIE 5284, Wireless Communications and Networks, (28 April 2004); doi: 10.1117/12.523402
Show Author Affiliations
Furong Wang, Huazhong Univ. of Science and Technology (China)
Zuwei Teng, Huazhong Univ. of Science and Technology (China)

Published in SPIE Proceedings Vol. 5284:
Wireless Communications and Networks
Chih-Lin I; Jiann-An Tsai; Hequan Wu, Editor(s)

© SPIE. Terms of Use
Back to Top