期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2021
卷号：12
期号：5
页码：856
DOI：10.14569/IJACSA.2021.01205100
出版社：Science and Information Society (SAI)
摘要：In the process of cloud service selection, it is difficult for users to choose trusted, available, and reliable cloud services. A trust model is a perfect solution for this service selection problem. In cloud computing, data availability and reliability have always been major concerns. According to research, around$285 million is lost per year due to cloud service failures, with a 99.91 percent availability rate. Replication has long been used to improve the data availability of large-scale cloud storage systems where errors are anticipated. As compared to a small-scale environment, where each data node can have different capabilities and can only accept a limited number of requests, replica place-ment in cloud storage systems becomes more complicated. As a result, deciding where to keep replicas in the system to meet the availability criteria is an issue. To address above issue this paper proposes a trust model which helps in selecting appropriate node for replica placement. This trust model generates comprehensive trust value of the data center node based on dynamic trust value combined with QoS parameters. Simulation experiments show that the model can reflect the dynamic change of data center node subject trust, enhance the predictability of node selection, and effectively decreases the failure rate of node.
