论文部分内容阅读
为了解决嵌入式实时系统如何节省电能的问题,针对具有两种运行状态的微处理器提出了最优的动态电压调节(DV S)算法。对具有周期性硬实时任务集的嵌入式系统,引进了部分降频的新概念,建立了精确实用的数学模型,在此基础上证明了该算法的最优性。分别从实例实验、仿真试验两个方面,证实了该算法的正确性和有效性。实验结果表明,采用这种最优DV S算法的系统,比不采用DV S算法的系统明显地节省能量,具体减少的数值依赖于任务集的构成和处理器状态,但是减少量平均达到20%以上。和其他类似的调度算法相比,也能更好地减少能耗。
In order to solve the problem of how to save power in embedded real-time system, the optimal Dynamic Voltage Regulation (DVS) algorithm is proposed for the microprocessor with two operating states. For embedded systems with periodic hard real-time task sets, a new concept of partial frequency reduction is introduced and an accurate and practical mathematical model is established. Based on this, the optimality of the proposed algorithm is proved. From the example experiment and the simulation experiment respectively, the correctness and validity of the algorithm are verified. The experimental results show that the system using this optimal DVS algorithm can save energy significantly compared to the system without DVS algorithm. The specific reduction depends on the composition of the task set and the processor state, but the average decrease of 20% the above. Compared with other similar scheduling algorithms, it can also reduce energy consumption better.