基于光滑样条回归的软件可靠性模型  

Software Reliability Model Based on Smooth Splines Regression

作　　者：仇正霞 杨剑锋 胡文生 黄嘉悦 

机构地区：[1]贵州大学,数学与统计学院,贵州 贵阳 [2]贵州理工学院,大数据学院,贵州 贵阳 [3]贵州交通职业技术学院,信息工程系,贵州 贵阳

出　　处：《建模与仿真》2023年第6期5156-5164,共9页Modeling and Simulation

摘　　要：随着软件产品在各行各业的广泛使用,其高可靠、高安全成为衡量一个软件质量的重要属性。本文引入了一种基于光滑样条回归的软件可靠性模型,并将其与传统的软件可靠性模型进行比较。此外,使用了最小二乘估计方法来估计模型中的参数。最后,基于开源软件Tomcat3-11服务器的真实失效数据,利用R软件对这4类可靠性模型进行性能对比分析,结果表明光滑样条回归模型的拟合与预测效果较好。With the widespread use of software products in various industries, their high reliability and secu-rity have become important attributes for assessing software quality. This paper introduces a soft-ware reliability model based on smooth spline regression and compares it with traditional software reliability models. In addition, the least squares estimation method is used to estimate the param-eters in the model. Finally, real failure data from the open-source Tomcat 3-11 server is used to perform a performance comparison analysis of these four types of reliability models using the R software. The results show that the smooth spline regression model provides better fitting and pre-dictive performance.

关 键 词：光滑样条回归 软件可靠性模型 开源软件 失效数据 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]