An Uncertain Trust and Prediction Model in Federated Cloud using Machine Learning Approach
A. Mary Odilya Teena1, M. Aaramuthan2
1A. Mary Odilya Teena , Assistant Professor, Department of Computer Science, St. Joseph’s College of Arts &Science (Autonomous), Cuddalore, (Tamil Nadu), India. & Ph.D. (Category-B), Research Scholar, Bharathiyar University, Coimbatore, (Tamil Nadu), India.
2Dr. M. Aaramuthan , Associate Professor &Head of the Department of Information Technology, PerunthalaivarKamarajar Institute of Engineering and Technology, Nedungadu, Karaikal, India.
Manuscript received on 24 January 2019 | Revised Manuscript received on 30 March 2019 | Manuscript published on 30 January 2019 | PP: 93-97 | Volume-7 Issue-6, March 2019 | Retrieval Number: E1948017519©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Federated Cloud Model referred as the interconnection of two or more providers with some guidelines prescribed in Service Level Agreement to address the uncertainty such as SLA Violation for the specific service. Most well-known models use the concept of either probability or fuzzy set theory in managing the Quality of Service (QoS) required by the Cloud user, application and tool. In this paper, Deep Learning is applied to predict the SLA Violation and manage the uncertainty. SLA violation is defined as the failure to meet the requirement prescribed for the user and application. In addition to that, banker’s algorithm is modified and used as prediction algorithm to find the possible safe state computation of the tasks and avoid wastage of resources in federated cloud. Random forest data mining technique is applied to rank the trust based provider and top provider may be considered for the service. The simulation results reveal that the proposed model helps to avoid uncertainty to about 78% and recognized that it is one of the most appropriate model needed in federated cloud architecture.
Keywords: About Four Key Words or Phrases in Alphabetical order, Separated by Commas.
Scope of the Article: Machine Learning