Open AccessCloud Qos Ranking Prediction using Tanimoto Coefficient Similarity Based Deep Learning Method
Author(s) -
S. Sujatha,
Subrata Bose
Publication year - 2020
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.b4427.029320
Subject(s) - cloud computing , computer science , quality of service , ranking (information retrieval) , reliability (semiconductor) , similarity (geometry) , service provider , data mining , service (business) , machine learning , artificial intelligence , computer network , power (physics) , physics , economy , quantum mechanics , economics , image (mathematics) , operating system
Cloud computing is a service which provides virtualized resources conforming to the end-user needs. Infrastructure, platform and software included in it. For the last two decades, it has achieved very gigantic growth. Currently, there are several cloud service providers in the market. The primary aim of this research is to minimize cloud service violation. It helps the service providers in exempting the penalty enhancing their reliability. So, cloud service QOS prediction is a research problem that must be solved. It is a very necessary thing for cloud service providers and cloud users. We have discussed several QoS prediction related to researches in the literature survey. But none of them has given a satisfactory QoS prediction. In this paper, we proposed a Tanimoto Coefficient Similarity-Based Deep Learning Method for QoS ranking prediction. The analysis helps service providers choose a suitable prediction method with optimal control parameters so that they can obtain accurate prediction results and avoid violation penalties. In comparison with the prior method in practice, the proposed method is more significant in terms of prediction accuracy, prediction time and error rate.