A Method of Reliability Assessment Based on Neural Network and Fault Data Clustering for Cloud with Big Data
Yoshinobu Tamura, Yumi Nobukawa, Shigeru Yamada · 2015
In the mobile clouds, the data size recorded in database software becomes large. Considering the software reliability of cloud computing with big data, it is important for the software managers to assess the relationship among the database software and cloud software, because the cloud software collaborate closely with the database software by using the internet network. In this paper, we propose a method of software reliability assessment based on the fault data clustering and neural network in cloud computing environment with big data. We perform a cluster analysis for the software fault data by using k-means clustering. Also, we propose the estimation method of the cumulative numbers of detected faults based on the neural network by using the results of cluster analysis. Moreover, we show several numerical examples of software reliability assessment in the cloud computing environment with big data.