Investigating the Effects of Schedulability Conditions on the Power Efficiency of Task Scheduling in an Embedded System

Abstract

Power consumption, performance and reliability are the most important parameters in modern safety-critical distributed real-time embedded systems. This paper evaluates and compares different schedulability conditions in fault-tolerant Rate-Monotonic (RM) and Earliest-Deadline-First (EDF) algorithms, with respect to their power efficiency. The primary-backup scheme is used to implement fault tolerance in the algorithms. To evaluate the algorithms, a software tool is developed that can simulate an embedded system consisting of n processors and m periodic tasks. The results show that depending on the different schedulability conditions, the EDF algorithm implemented with the Best-Fit policy is on average 9.6% more power efficient than other algorithms when n=1500 and m=1000. between the two selected schedulability conditions in the RM algorithm, the Utilization Oriented (UO) condition implemented with the Best-Fit policy is on average 5% more power efficient than the other schedulability condition.