期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：4
页码：5288-5295
出版社：TechScience Publications
摘要：Business information is stored in the cloud environment and offers proficient software services to the clients using internet. Cloud infrastructure delivers traditional software services among different cloud users. Decentralized Self-Adaptation Mechanism has been implemented to maintain decentralization applicable to QoS exhibited cloud system. However, designing decentralized Self-Adaptation Mechanism is not trivial as it failed to port the model in CloudSim platform. Service delivery models of cloud computing understands the risks of data but fails to establish the dynamic software prediction framework on cloud infrastructure. In this paper, we design a dynamic software prediction framework on CloudSim platform called as the Software Prediction with Self-adaptive Classification (SPSC) model. SPSC model predict the software required by the user and establishes communication dynamically for providing software services to cloud users. SPSC model is split into two phases. The initial phase starts with the software prediction followed by the second phase that performs the process of classification. SPSC model performs the software prediction using autoregressive method in cloud zone for improving the software service availability rate depending on the client needs. We then present a classification model performed based on the information obtained using Principle Component Analysis (PCA). PCA based classification improves the quality of services and also used to easily identify the software peculiar features in cloud zone. The identification of peculiar features helps to improve the classification rate averagely by 12 percentages. SPSC model experiment the work in CloudSim platform with Amazon web service dataset on the factors such as execution time, classification accuracy rate and Quality of Service rate on client request
