基于免疫算法的嵌入式系统软硬件划分方法

Hardware/software partitioning method based on immune algorithm

软硬件划分是嵌入式系统协同设计的关键问题之一。提出了一种划分模型,并通过改进的免疫算法解决了在多约束条件下软硬件划分的优化问题。在该免疫算法中,引入了免疫算子,通过从以往经验中提取疫苗,在生成子代过程中注入疫苗,使划分算法得到了优化。实验表明该算法具有较快的收敛速度,并且在总体性能上优于传统遗传算法。

Hardware/software partitioning is one of the key problems in embedded system co-design. A kind of partitioning model is presented, which solves the problem of hardware/software partitioning under the multi-constraint condition through the improved immune algorithm. An idea of immune operator is introduced in this immune algorithm, which extracts vaccines from the past experience and injects them into the offspring, thereby optimizes the partitioning algorithm. Experiment shows that this approach has faster convergence speed and is better than the simple genetic algorithm as a whole.