A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers

  • Authors:
  • Nabil J. Sarhan;Chita R. Das

  • Affiliations:
  • -;-

  • Venue:
  • ANSS '03 Proceedings of the 36th annual symposium on Simulation
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Multimedia-on-demand (MOD) has grown dramaticallyin popularity, especially in the domains of education, business,and entertainment. Therefore, the investigation ofvarious alternatives to improve the performance of MODservers has become a major research focus. The performanceof these servers can be enhanced significantly byservicing multiple requests from a common set of resources.The exploited degrees of resource sharing depend greatly onhow servers schedule the waiting requests. By schedulingthe requests intelligently, a server can support more concurrentcustomers and can reduce their waiting times for service.In this paper, we provide a detailed analysis of existingscheduling policies and propose two new policies, calledQuantized First Come First Serve (QFCFS) and EnhancedMinimum Idling Maximum Loss (IML+). We demonstratethe effectiveness of these policies through simulation andshow that they suite different patterns of customer waitingtolerance.