Using Machine Learning Algorithms for Cloud Client Prediction Models in a Web VM Resource Provisioning Environment
Journal Title: Transactions on Machine Learning and Artificial Intelligence - Year 2016, Vol 4, Issue 1
Abstract
In order to meet Service Level Agreement (SLA) requirements, efficient scaling of Virtual Machine (VM) resources in cloud computing needs to be provisioned ahead due to the instantiation time required by the VM. One way to do this is by predicting future resource demands. The existing research on VM resource provisioning are either reactive in their approach or use only non-business level metrics. In this research, a Cloud client prediction model for TPC-W benchmark web application is developed and evaluated using three machine learning techniques: Support Vector Regression (SVR), Neural Networks (NN) and Linear Regression (LR). Business level metrics for Response Time and Throughput are included in the prediction model with the aim of providing cloud clients with a more robust scaling decision choice. Results and analysis from the experiments carried out on Amazon Elastic Compute Cloud (EC2) show that Support Vector Regression provides the best prediction model for random-like workload traffic pattern.
Authors and Affiliations
Samuel A. Ajila, Akindele A. Bankole
Keywords
Related Articles
- EP ID EP278157
- DOI 10.14738/tmlai.41.1690
- Views 98
- Downloads 0
Simulation of the Charge Motion near the Velocity of Light in Electric and Magnetic Fields
A numerical simulation method for the charge motion near the velocity of light in electric and magnetic fields has been investigated using the relativistic mass by Einstein’s special theory of relativity, and an electron...
Vibration Level Improvement of Id Fan in a Cement Plant Based On CFD Study of Incoming Dust Particles Streamline
This paper presents numerical study of aerosol flow inside of the induce draft (ID) fan inlet duct of a cement plant and the field observation of the proposed guide plate implementation as vibration reducer. Since ID fan...
The GeoRSS Model and the Design of a Ranking Algorithm in Semantic Web
Ecommerce has become nowadays an influential actor in the international trade industry and has greatly contributed in the economic development of nations. The fact of dealing with this field along with the evolution of t...
Generic Platform to Generate Educational Components
In this research, we will present all the concepts necessary for the implementation of a warehouse of educational components. We define three classes of educational components: Learning components, services components an...
Brain Tumor Segmentation using Multiobjective Fuzzy Clustering
The segmentation of magnetic resonance images plays a crucial role in medical image analysis because it extracts the required area from the image. Despite intensive research, it still remains a challenging problem and th...