基于Spark的分布式并行MOEA/D

2017 International Conference on Computing Intelligence and Information System (CIIS) Pub Date : 2017-04-01 DOI:10.1109/CIIS.2017.12

W. Ying, Shiyun Chen, Bingshen Wu, Yuehong Xie, Yu Wu

{"title":"基于Spark的分布式并行MOEA/D","authors":"W. Ying, Shiyun Chen, Bingshen Wu, Yuehong Xie, Yu Wu","doi":"10.1109/CIIS.2017.12","DOIUrl":null,"url":null,"abstract":"The multi-objective evolutionary algorithm based on decomposition (MOEA/D) has shown remarkable performance for multi-objective optimization problems (MOPs). However, MOEA/D still consumes long time to solve MOPs with computationally intensive objective functions. This paper proposes two distributed parallel MOEA/Ds based on the popular distributed framework, Spark, to further reduce the running time of the sequential MOEA/D for MOPs. The first entirely evolved MOEA/D evolves an entire population, while the second partially evolved MOEA/D based on Spark evolves a partial subpopulation equal in size to a partition in each transformation-action process. Experimental results on DTLZ benchmark MOPs with three objectives indicate that both distributed MOEA/Ds on Spark obtains better speedup than the distributed MOEA/Ds on MapReduce and achieve the quality of solutions similar to the sequential MOEA/D.","PeriodicalId":254342,"journal":{"name":"2017 International Conference on Computing Intelligence and Information System (CIIS)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Distributed Parellel MOEA/D on Spark\",\"authors\":\"W. Ying, Shiyun Chen, Bingshen Wu, Yuehong Xie, Yu Wu\",\"doi\":\"10.1109/CIIS.2017.12\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The multi-objective evolutionary algorithm based on decomposition (MOEA/D) has shown remarkable performance for multi-objective optimization problems (MOPs). However, MOEA/D still consumes long time to solve MOPs with computationally intensive objective functions. This paper proposes two distributed parallel MOEA/Ds based on the popular distributed framework, Spark, to further reduce the running time of the sequential MOEA/D for MOPs. The first entirely evolved MOEA/D evolves an entire population, while the second partially evolved MOEA/D based on Spark evolves a partial subpopulation equal in size to a partition in each transformation-action process. Experimental results on DTLZ benchmark MOPs with three objectives indicate that both distributed MOEA/Ds on Spark obtains better speedup than the distributed MOEA/Ds on MapReduce and achieve the quality of solutions similar to the sequential MOEA/D.\",\"PeriodicalId\":254342,\"journal\":{\"name\":\"2017 International Conference on Computing Intelligence and Information System (CIIS)\",\"volume\":\"131 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 International Conference on Computing Intelligence and Information System (CIIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CIIS.2017.12\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Computing Intelligence and Information System (CIIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIIS.2017.12","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

基于分解的多目标进化算法(MOEA/D)在多目标优化问题(MOPs)中表现出了显著的性能。然而，MOEA/D在求解具有计算密集型目标函数的MOPs时仍然需要耗费较长的时间。本文提出了两种基于流行的分布式框架Spark的分布式并行MOEA/D，以进一步减少mop的顺序MOEA/D的运行时间。第一个完全进化的MOEA/D进化出了一个完整的种群，而第二个基于Spark的部分进化的MOEA/D则在每个转换操作过程中进化出一个与分区大小相等的部分子种群。在三目标DTLZ基准MOPs上的实验结果表明，Spark上的分布式MOEA/D都比MapReduce上的分布式MOEA/D获得了更好的加速，并且获得了与顺序MOEA/D相似的解决方案质量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Distributed Parellel MOEA/D on Spark

The multi-objective evolutionary algorithm based on decomposition (MOEA/D) has shown remarkable performance for multi-objective optimization problems (MOPs). However, MOEA/D still consumes long time to solve MOPs with computationally intensive objective functions. This paper proposes two distributed parallel MOEA/Ds based on the popular distributed framework, Spark, to further reduce the running time of the sequential MOEA/D for MOPs. The first entirely evolved MOEA/D evolves an entire population, while the second partially evolved MOEA/D based on Spark evolves a partial subpopulation equal in size to a partition in each transformation-action process. Experimental results on DTLZ benchmark MOPs with three objectives indicate that both distributed MOEA/Ds on Spark obtains better speedup than the distributed MOEA/Ds on MapReduce and achieve the quality of solutions similar to the sequential MOEA/D.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2017 International Conference on Computing Intelligence and Information System (CIIS)

自引率

0.00%

发文量