Amazing technological breakthrough possible @S-Logix pro@slogix.in

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • pro@slogix.in
  • +91- 81240 01111

Social List

An intelligent swarm based prediction approach for predicting cloud computing user resource needs - 2020

An intelligent swarm based prediction approach for predicting cloud computing user resource needs

Research Area:  Cloud Computing

Abstract:

Cloud computing aimed at offering elastic resource allocation on demand to cloud consumers. Building a cloud resource demand prediction model is a challenging task because cloud consumers demand changes over time. Most of the current works in cloud resource demand prediction study the problem from the cloud provider perspective. In this paper, we study the problem from the cloud consumer perspective with the aim to help the consumers to meet their resource needs, derive estimates for the required IT budget, select the best cloud providers, and get better pricing through the advanced reservation of required cloud resources. We develop a new Swarm Intelligence Based Prediction Approach (SIBPA) to predict with higher accuracy the resource needs of a cloud consumer in terms of CPU, memory, and disk storage utilization. The SIBPA is also able to predict the response time and throughput which in turn enables the cloud consumers to make a better scaling decision. It also takes into account the dynamic behavior of consumer requests in a long term period and the seasonal or/and trend patterns in time series. The SIBPA uses the Particle Swarm Optimization (PSO) approach for selecting the best features from the dataset and for estimating the parameters of the prediction algorithms. The experimental results reveal that the prediction accuracy of the SIBPA outperforms the current prediction models. In terms of CPU utilization prediction, the accuracy of SIBPA outperforms the accuracy of the existing cloud consumer prediction frameworks that use Linear Regression, Neural Network, and Support Vector Machines approaches by 56.95%, 80.42%, and 63.86% respectively according to RMSE, and by 72.66%, 44.24%, and 56.78% according to MAPE. The accuracy of SIBPA also outperforms the accuracy of the existing cloud consumer prediction frameworks in terms of response time, throughput, and memory utilization predictions. The analysis and experiment results of SIBPA are discussed in detail in this paper.

Keywords:  

Author(s) Name:  Hisham A.Kholidy

Journal name:  Computer Communications

Conferrence name:  

Publisher name:  Elsevier

DOI:  10.1016/j.comcom.2019.12.028

Volume Information:  Volume 151, 1 February 2020, Pages 133-144