论文部分内容阅读
分析了传统并行遗传算法的局限性,针对其迁移固定不变盲目性等缺点,提出了一种适合在当前多核计算机上运行的基于自适应迁移策略的并行遗传算法(AMPGA),该方法将遗传算法同当前个人计算机体系结构相结合,使新的并行遗传算法在主流计算机上并行执行,加快算法的收敛速度,充分挖掘出计算机的计算能力,很大程度地提高了传统并行遗传算法的计算性能。数据仿真实验表明,该算法与传统并行遗传算法相比,收敛速度快、求解精度高,并行效率也明显提升。
The limitations of traditional parallel genetic algorithm (GA) are analyzed. Aiming at the shortcomings of immutable blindness, a parallel genetic algorithm (AMPGA) based on adaptive migration strategy, which is suitable for running on multi-core computers, is proposed. Genetic algorithm The algorithm is combined with the current personal computer architecture to enable the parallel execution of the new parallel genetic algorithm on the mainstream computer to speed up the convergence of the algorithm and fully exploit the computing power of the computer and greatly improve the computing performance of the traditional parallel genetic algorithm . Simulation results show that compared with the traditional parallel genetic algorithm, the proposed algorithm has the advantages of fast convergence speed, high solution precision and parallel efficiency.