软实时并行应用的遗传列表调度

Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753) Pub Date : 2004-06-19 DOI:10.1109/CEC.2004.1330993

Yoginder S. Dandass

{"title":"软实时并行应用的遗传列表调度","authors":"Yoginder S. Dandass","doi":"10.1109/CEC.2004.1330993","DOIUrl":null,"url":null,"abstract":"This paper presents a hybrid algorithm that combines list scheduling with a genetic algorithm for constructing nonpreemptive schedules for soft real-time parallel applications represented as directed acyclic graphs. The execution time requirements of the applications' tasks are assumed to be stochastic and are represented as probability distribution functions. The approach presented here produces shorter schedules than two popular list scheduling approaches for a majority of sample problems. Furthermore, the stochastic schedules provide a mechanism for predicting the probability of the application completing when the execution time available is less than the worst case requirement.","PeriodicalId":152088,"journal":{"name":"Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)","volume":"54 46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Genetic list scheduling for soft real-time parallel applications\",\"authors\":\"Yoginder S. Dandass\",\"doi\":\"10.1109/CEC.2004.1330993\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a hybrid algorithm that combines list scheduling with a genetic algorithm for constructing nonpreemptive schedules for soft real-time parallel applications represented as directed acyclic graphs. The execution time requirements of the applications' tasks are assumed to be stochastic and are represented as probability distribution functions. The approach presented here produces shorter schedules than two popular list scheduling approaches for a majority of sample problems. Furthermore, the stochastic schedules provide a mechanism for predicting the probability of the application completing when the execution time available is less than the worst case requirement.\",\"PeriodicalId\":152088,\"journal\":{\"name\":\"Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)\",\"volume\":\"54 46 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-06-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CEC.2004.1330993\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CEC.2004.1330993","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

本文提出了一种结合列表调度和遗传算法的混合算法，用于构造以有向无环图表示的软实时并行应用的非抢占调度。假设应用程序任务的执行时间需求是随机的，并表示为概率分布函数。对于大多数示例问题，本文提供的方法比两种流行的列表调度方法产生更短的调度时间。此外，随机调度提供了一种机制，用于在可用的执行时间小于最坏情况要求时预测应用程序完成的概率。

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

Genetic list scheduling for soft real-time parallel applications

This paper presents a hybrid algorithm that combines list scheduling with a genetic algorithm for constructing nonpreemptive schedules for soft real-time parallel applications represented as directed acyclic graphs. The execution time requirements of the applications' tasks are assumed to be stochastic and are represented as probability distribution functions. The approach presented here produces shorter schedules than two popular list scheduling approaches for a majority of sample problems. Furthermore, the stochastic schedules provide a mechanism for predicting the probability of the application completing when the execution time available is less than the worst case requirement.

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

Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)

自引率

0.00%

发文量