随着可移动嵌入式系统大量而广泛的使用,嵌入式软件能耗已成为嵌入式系统设计的一个重要因素,而如何评价嵌入式软件能耗优化方法的综合效果是一项重要工作.针对评价过程中信息不完备性和不确切性的问题,采用基于层次灰色评价理论建立的评价模型,通过仿真实验数据分析在源程序结构级的优化方法对嵌入式软件三项指标(包括能耗、运行时间以及指令数目)的影响程度,进而评价优化方法取得的效果和所属等级,并考虑了能耗与运行时间的负相关情况.实验结果表明,此评价方法是有效的,根据评价的反馈结果,可进一步指导并完善相应的嵌入式软件能耗优化方法.
With the numerous and wide application of mobile embedded systems, energy consumption of embedded software has become a key factor in the design of embedded systems, and how to evaluate the total effects of optimization methods of embedded software is an important task. As there is inaccurate and incomplete information in the evaluation process, based on the hierarchy-gray model, the influence of three indexes (including energy consumption, execution time and instruction number) on the sourcecode level is analyzed by the simulation experiments. Then, the affecting results and rank of each opti- mization method can be further evaluated. Meanwhile, a negative correlation case between energy con- sumption and execution time is considered. The experiment results show that the evaluation method is effective, and the corresponding optimization methods can be further improved according to the feedback result.