An Improved Faster Domain-Specific Predicting Energy Consumption using Neural Network
Ch. Vara Prasad1, G. Leela Krishna2, K. Nikesh3, J. Caroline4
1Ch. Vara Prasad, Department of Computer Science and Engineering, SRM Institute of Science and Technology (SRMIST), Chennai (Tamil Nadu), India.
2G. Leela Krishna, Department of Computer Science and Engineering, SRM Institute of Science and Technology (SRMIST), Chennai (Tamil Nadu), India.
3K. Nikesh, Department of Computer Science and Engineering, SRM Institute of Science and Technology (SRMIST), Chennai (Tamil Nadu), India.
4J. Caroline, Department of Computer Science and Engineering, SRM Institute of Science and Technology (SRMIST), Chennai (Tamil Nadu), India.
Manuscript received on 12 October 2021 | Revised Manuscript received on 25 October 2021 | Manuscript Accepted on 15 November 2021 | Manuscript published on 30 November 2021 | PP : 22-27 | Volume-1 Issue-1, November 2021 | Retrieval Number:100.1/ijeer.A1005121121
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Thermal administration in the large-scale cloud server farms is an essential issue. Expanded host temperature makes areas of interest which fundamentally constructs cooling cost and effects trustworthiness. Precise supposition for have temperature is imperative for dealing with the resources reasonably and furthermore cash saving. Since great numerous dollars are being squandered on coolants in cloud server farms. Temperature assessment is a non-unimportant issue by virtue of thermal varieties in the server farm. Existing answers for heat assessment are wasteful because of their computational intricacy and nonappearance of careful suspicion. We have taken apart basically the precision and time devoured by different suspicion plans utilizing some commencement limits. From our assessment, we tracked down that the Rprop-calculation utilizing strategic initiation work is appropriate as it gives practically 97.2 rate precision. Our forecasted sensor cloud model coordinates Rprop-supposition plot utilizing the strategic origin work in cloud framework which predicts future sensor information, such a lot of that customers request is answered at cloud level which reserves energy as number of transmissions are decreased in the detector organization.
Keywords: Cloud Computing, Thermal administration, Host temperature, Coolants, Rprop Algorithm.