Optimizationn of Structural Systems by Adaptive Distributed Parallel Genetic Algorithm

自适应分布式并行遗传算法结构系统优化

• 批准号: 10650104
• 负责人: MIKI Mitsunori
• 金额: $ 1.47万
• 依托单位: Doshisha University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 1998
• 资助国家: 日本
• 起止时间: 1998 至 1999
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-10650104/
• 关键词: Parallel Processing; Genetic Algorithms; Optimum Design; Crossover rate; Mutation rate; Stuructural Optimization; PC cluster; Evolutionary computation; 分散処理; 移住

Genetic algorithms (GA) are useful methods for complicated optimization problems.However, their main drawback is computationally expensive. Therefore, parallel processing is inevitable, but the researches on parallel genetic algorithms are not enough. This research aims to evaluate the effectiveness of parallel genetic algorithms and to propose a new distributed GA which shows a high efficiency in parallel processing.First, some distributed GA models with divided sub-populations are compared and the performance of the models are investigated. The effect of the GA parameters are investigated, and a new approach is proposed. The following are the summaries of the search.1) The distributed population model with divided sub-populations with migration is suitable for parallel processing and its performance for providing good solutions in very high. The distribution population model suppress the early convergence.2) The optimum crossover and mutation rates for the distributed GA are different from those for single population GA, and a new distributed GA model with distributed environment is proposed to relive the difficulty in choosing optimum parameters.

遗传算法是求解复杂优化问题的有效方法，但其主要缺点是计算量大。因此，并行处理是必然的，但目前对并行遗传算法的研究还不够。本研究的目的是评估并行遗传算法的有效性，并提出一种新的分布式遗传算法，显示出高效率的并行处理。首先，比较了几种分布式遗传算法模型，并研究了模型的性能。研究了遗传算法参数的影响，并提出了一种新的方法。以下是研究的总结。1）具有迁移的子种群划分的分布式种群模型适合于并行处理，并且其提供良好解的性能非常高。分布种群模型抑制了早期收敛; 2）分布式遗传算法的最优交叉率和变异率不同于单种群遗传算法，提出了一种新的分布式环境下的分布式遗传算法模型，解决了最优参数选择困难的问题。

项目成果

M.Miki, T.Hiroyasu, T.Ikeda: "Parallel Distributed Optimization by Resource Addition and Reduction" Proc.Int.Symposium on High Performance computing'99 (ISHPC). (印刷中). (1999)

M.Miki、T.Hiroyasu、T.Ikeda：“通过资源添加和减少进行并行分布式优化”Proc.Int.Symposium on High PerformanceComputing99 (ISHPC)（出版中）。

T.Hiroyasu, M.Miki, M.Negami: "Distributed Genetic Algorithms with Randomized Migration Rate"Proc. of the 1999 IEEE International Conference on Systems, Man, and Cybernetics. Vol. 1. 695-700 (1999)

T.Hiroyasu、M.Miki、M.Negami：“具有随机迁移率的分布式遗传算法”Proc。

M. Miki: "Parallel Genetic Algorithm with Parameter-Free Approach"Modeling and Simulation Based Engineering, Tech Science Press. Vol.1. 582-587 (1998)

M. Miki：“无参数方法的并行遗传算法”基于建模和仿真的工程，技术科学出版社。

三木光範、廣安知之、笠井誠之: "連続温度並列シミュレーテッドアニーリングの応用" 情報処理学会並列処理シンポジウムJSPP'99論文集. (1999)

Mitsunori Miki、Tomoyuki Hiroyasu、Masayuki Kasai：“连续温度并行模拟退火的应用”日本信息处理学会并行处理研讨会 JSPP99 论文集（1999 年）。

T.Hiroyasu,M.Miki,ほか1名: "Distributed Genetic Algorithms with a New Sharing Approach in Multiobjective Optimization Problems"Proc.IEEE The 1999 Congress on Evolutionary Computation. 1. 69-76 (1999)

T. Hiroyasu、M. Miki 和其他 1 人：“多目标优化问题中采用新共享方法的分布式遗传算法”Proc。 IEEE 1999 年进化计算大会 1. 69-76 (1999)。