基于灰色随机Petri网的构件化软件可靠性早期评估方法  

Early evaluation of component software reliability based on grey stochastic Petri net

作　　者：刘玲艳[1] 吴晓平[1] 

机构地区：[1]海军工程大学电子工程学院,武汉430033

出　　处：《海军工程大学学报》2011年第1期16-22,共7页Journal of Naval University of Engineering

基　　金：国家自然科学基金资助项目(60774029)

摘　　要：针对构件化软件系统本身的复杂性和早期可靠性评估存在的"贫信息、少数据"的问题,提出了一种灰色随机Petri网(GrSPN)模型。该模型在随机Petri网的变迁速率中引入灰数,首先结合系统GrSPN模型的可达树确定系统的状态标识集及其子集,然后将得到的GrSPN转化为与其同构的连续时间马尔可夫链(MC)。通过对MC的平稳状态分布对软件系统可靠性进行分析,得到用灰数表示的稳态概率,然后根据白化权函数对结果进行白化,得到软件系统每个可达状态标识下的稳态概率,进而求得系统可靠度。最后,结合某构件化软件可靠性早期评估实例验证了该模型的有效性。Aiming at the complexity of software systems and the problem of pure information and few data in early reliability evaluations,a model based on grey stochastic Petri net（GrSPN） was proposed.In the model,interval gray numbers was introduced into the transition rates.Combining with the reachable tree of GrSPN,the state marks of the system and its subset were gained.Then the GrSPN model was translated into Markov chain（MC） being isomorphic with it.The analysis of reliability of the software system by means of the stable state distribution of MC leaded to obtaining the steady probability of each reachable state,which was expressed by interzone gray numbers.And the whiten values of the steady probability was gained based on whitening transforming functions.Finally the model proposed was applied to the evaluation of some software system,and the result proves that this model is effective.

关 键 词：构件化软件 可靠性 灰色随机Petri网 早期评估 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]