Framework for Application Service Behavior Prognostication with Cost-Effective Provisioning In a Utility Cloud
Journal Title: International Journal of engineering Research and Applications - Year 2018, Vol 8, Issue 3
Abstract
In A Utility Cloud Resources Are Operating On A Utility Basis That Allows Customers To Pay As They Go And Only For The Resources They Will Use At Multiple Granularities For A Specified Level Of Quality Of Service. Cloud Infrastructure Services Or Iaas (Infrastructure–As-A-Service) Delivers The Computer Infrastructure Or We Can Say A Platform Virtualization Environment, As A Service And The Service Is Typically Billed On A Utility Computing Basis And Amount Of Resources Consumed. Generally, This Infrastructure Allocation Is Static And Resources Are Allocated During VM Instantiation. Any Change In Workload Leading To Significant Increase Or Decrease In Resources Is Handled By VM Migration. Hence, Cloud Users Tend To Characterize Their Workloads At A Coarse Grained Level Which Potentially Leads To Over-Allocated VM Resources Or Under-Performing Application. That Means Either User Is Paying More In Case Of Over-Allocation Of Resources Or The Application Is Under-Performed In Case Of Under-Allocation Of Resources. In This Paper, We Present A Framework For Iaas Utility Cloud Where A Prognostication Component Predicts At Run-Time The Expected Demand By Application Which Is Then Used To Modulate Resource Allocation Based On The Predicted Demand. We Derive This Component Based On A Cost Model To Make It More Cost-Effective For Both The Service User And The Service Provider. Confidence Interval For Predicted Workload Is Used To Minimize This Effective Cost.
Authors and Affiliations
Monika Sainger, Dr. K. P. Yadav, Dr. H. S. Sharma
Keywords
Related Articles
- EP ID EP393879
- DOI 10.9790/9622-0803031522.
- Views 92
- Downloads 0
A Novel Control Strategy For Shunt Active Power Filter Using NARX Neural Network
This paper presents a novel control strategy for shunt active power filter (APF) based on Nonlinear AutoRegressive with eXogenous neural network (NARX). The proposed series parallel NARX neural network is trained by usin...
Analysis of Self-Supported Steel Chimney with the Effects of Geometrical Parameters
Steel stacks are smoke releasing slender and tall structures constructed for various power plant or oil and gas industries. Steel chimney are subjected to static and dynamic loadings. Static analysis is carried out by st...
A survey conducted on cotton and Bt cotton farming practices, with pesticide application: a case study
Agricultural produce has to increase to fulfill the necessity of the farmer and population demand due to this reason pesticide and fertilizers cane be used to increase the crop yield and agricultural produce. The excessi...
Chemical Reaction And Heat Generation Effects On Mhd Free Convective Flow Over A Porous Plate With Varaible Tempareture And Variable Concentration
This Work Is Aimed At Describing The Chemical Reaction And Heat Generation Effects On MHD Free Convective Flow Over A Porous Plate With Varaible Tempareture And Variable Concentration.Analytic Solution Is Carried Out Und...
Does a Hybrid Approach of Agile and Plan-Driven Methods Work Better for IT System Development Projects?
With a focus on large-scale IT system development projects in diverse enterprises, this research suggests that a hybrid approach combining agile and plan-driven management methods should fit in a wider context of specifi...