Decision Support Based Resource Allocation for Cost Reduction in Cloud Storage using Big Data Analytics
Krishnakumar L1, Nithya A2
1Mr. Krishnakumar L1, Research Scholar, School of Computer Studies, Rathnavel Subramaniam College of Arts and Science, Coimbatore, India.
2Dr. Nithya A, Research Supervisor, School of Computer Studies, Rathnavel Subramaniam College of Arts and Science, Coimbatore, India.
Manuscript received on 11 August 2019. | Revised Manuscript received on 17 August 2019. | Manuscript published on 30 September 2019. | PP: 8124-8126 | Volume-8 Issue-3 September 2019 | Retrieval Number: C5828098319/2019©BEIESP | DOI: 10.35940/ijrte.C5828.098319
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: Provision of highly efficient storage for dynamically growing data is considered problem to be solved in data mining. Few research works have been designed for big data storage analytics. However, the storage efficiency using conventional techniques was not sufficient as where data duplication and storage overhead problem was not addressed. In order to overcome such limitations, Tanimoto Regressive Decision Support Based Blake2 Hashing Space Efficient Quotient Data Structure (TRDS-BHSEQDS) Model is proposed. Initially, TRDS-BHSEQDS technique gets larger number of input data as input. Then, TRDS-BHSEQDS technique computes 512 bits Blake2 hash value for each data to be stored. Consequently, TRDS-BHSEQDS technique applies Tanimoto Regressive Decision Support Model (TRDSM) where it carried outs regression analysis with application of Tanimoto similarity coefficient. During this process, proposed TRDS-BHSEQDS technique finds relationship between hash values of data by determining Tanimoto similarity coefficient value. If similarity value is ‘+1’, then TRDS-BHSEQDS technique considered that input data is already stored in BHSEQF memory. TRDS-BHSEQDS technique enhances the storage efficiency of big data when compared to state-of-the-art works. The performance of TRDS-BHSEQDS technique is measured in terms of storage efficiency, time complexity and space complexity and storage overhead with respect to different numbers of input big data.
Keywords: Big Data, Blake2 Hashed Space Efficient Quotient Filter, Hash Value, Regression Analysis, Storage Overhead, Tanimoto Regressive Decision Support Model.
Scope of the Article: Big Data Security