A Task Migration Constrained Energy-Efficient Scheduling Algorithm for Multiprocessor Real-time Systems

This paper presents a multiprocessor energy-efficient scheduling algorithm for the real-time periodic tasks with task migration constrained policies. We separate periodic tasks into fixed tasks and migration ones, and constrain the number of migration tasks and destination processors executing migration tasks. The algorithm is composed of two phases. Firstly, choosing a processor to sort all of the periodic tasks in a non-increasing order of task utilization, then distributing them to other processors. Secondly, scheduling the migration tasks with the virtual execution windows in the first place, and scheduling the fixed tasks with EDF algorithm in the next place. The experiment results show that compared with arbitrary task migration and no task migration allowed, the performance of energy consumption saving in multiprocessor scheduling is improved greatly with our algorithm.