Dynamic queue deadline first scheduling algorithm for soft real time systems

Abstract

Most embedded real time systems are based on uiniprocessor architecture, and deadline miss ratio is always a mainstay .fr anv type of real time system. This paper presents the design and analysis of a new scheduling algorithm, Dynamic Queue Deadline First (DQDF) to handle scheduling of dynamic multiple tasks in real time systems. Soft real-time processing is a realtime processing in which some or all applicati6ns are allowed to miss deadlines, particularly in situations of system load. In this paper, a new scheduler is introduced to minimize the overhead and percentage of deadline misses to improve the system utilization andfairness. We have used Earliest Deadline First (EDF) with dynamic queuing technique, as it is an optimal scheduling algorithm for uniprocessor systems. Simulation results show that with DQDF algorithm, the deadline miss ratio is improved and fairness is restored by utsing static priority approach. The comparison of the new scheduler DQDF with simple EDF scheduler results the perjbrmance improvement upto 68%.