PCM预测软件性能的研究与设计  

The research and design on software performance prediction with PCM

作　　者：冯富霞[1] 李森贵 

机构地区：[1]安徽工程大学计算机与信息学院,安徽芜湖241000 [2]芜湖莫森泰克汽车科技有限公司,安徽芜湖241000

出　　处：《安徽工程大学学报》2013年第4期70-73,共4页Journal of Anhui Polytechnic University

基　　金：安徽工程大学青年基金资助项目(2009YQ038)

摘　　要：为了减少基于组件的软件性能预测技术复杂度,研究了软件性能预测的方法.基于PCM(Palladio Component Model)性能预测方法,分析了PCM与UML的建模关系与PCM建模过程,指出架构级和组件级参数之间的关联.此两类不确定性参数的设置与取值是PCM建模的关键,同时,性能预测的成功需要预测工具的有利支持.最后提出了一种PCM性能预测工具的设计方法.To reduce the technique complex about component-based software performance prediction, soft- ware performance prediction methods are researched. Based on the PCM method, the modeling relation and progress between PCM and UML are analyzed, the contact between framework and component pa- rameters is presented,the two kinds of imperfect parameters are the key on PCM modeling. The per- formance prediction tool is needed to support the successful prediction. Finally,one design method on the PCM performance prediction tool is provided.

关 键 词：Palladio组件模型 性能预测 统一建模语言 Eclipse模型框架 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]