BATS: An Energy-Efficient Approach to Real-Time Scheduling and Synchronization

Abstract

In this paper, we are interested in the energy-efficient scheduling of real-time tasks on a non-ideal DVS processor. We assume that tasks are periodic, pre-emptive, dynamic priority, and may concurrent access to a set of shared resources. Based on the well-known earliest deadline first (EDF) algorithm and the stack resource policy (SRP), we propose an approach, called blocking-aware two-speed (BATS) algorithm, to calculate appropriate speeds for task execution. In particular, tasks are executed at a static low speed when blocking does not occur, and a high speed will be calculated dynamically whenever a task blocks a higher priority task. The processor must run at the high speed from the beginning of the blocking until the deadline of the blocked task or the processor becomes idle. The low speed and the high speed are derived based on the theoretical analysis of the schedulability of tasks so that the energy consumption can be reduced without violating the timing constraints of tasks. Compare with existing work, BATS achieves more energy saving because its derived high speeds are lower than that of existing work and the processor has less time to execute tasks at the high speeds.