论文部分内容阅读
针对带宽和时延约束的低能耗片上网络(NoC)映射问题,提出了一种自适应的混沌遗传退火映射算法.该算法利用Boltzmann更新机制选择遗传个体,引入自适应混沌方法优化适应度较差个体,采用多邻域的退火策略优化较优个体.实验结果表明,所提算法有效地避免了早熟收敛,提高了算法收敛速度,与标准遗传算法和混沌遗传算法相比,平均节能分别为45%和22.6%,有效地降低了NoC系统通信能耗.
In order to solve the NoC mapping problem with bandwidth and delay constraints, an adaptive chaotic genetic annealing mapping algorithm is proposed. This algorithm uses Boltzmann update mechanism to select genetic individuals and introduces adaptive chaos method to optimize the fitness Individuals using multiple neighborhood annealing strategy to optimize the better individuals.The experimental results show that the proposed algorithm effectively avoids premature convergence and improve the convergence speed of the algorithm, compared with the standard genetic algorithm and chaos genetic algorithm, the average energy savings were 45 % And 22.6%, effectively reducing NoC system communication energy consumption.