嵌入式实时系统周期任务能耗感知调度

Energy-aware schedule of periodic tasks in embedded real-time systems

在电池供电的嵌入式实时系统中,针对实时周期任务集在一个可变电压处理器上的能耗感知调度问题,在改进的人工鱼群算法(improved artificial fish school algorithm,IAFSA)基础上,提出了一种离线的能耗感知调度算法,该算法通过构造人工鱼的行为约束自然地满足时限和能耗约束,最大化系统总奖赏值。与贪婪算法相比,该算法提高系统的总奖赏值约47%。且随着电池能量的减少,系统能耗利用效率逐渐增大,说明该算法具有良好的能耗感知特性。

For the energy-aware schedule of battery powered real-time embedded system, a novel offline energy-aware schedule algorithm is proposed based on the improved artificial fish school algorithm （IAFSA）. The algorithm constructs the behavior constraint of the artificial fish to make the random search meet the energy constraint and deadline while maximizing the system reward. Experimental results show that the proposed algorithm improves the system reward about 47% compared with the Greedy algorithm. Besides, the energy efficiency increases while the energy budget decreases, which demonstrates the good energy-awareness efficiency of the proposed algorithm.