Title: Cloud resource orchestration optimisation based on ARIMA

Authors: Hua Qin; Min Yu; Yingxu Lai; Zenghui Liu; Jing Liu

Addresses: Information Technology Center, Beijing University of Technology, Beijing 100124, China ' College of Computer Sciences, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China ' College of Computer Sciences, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Science and Technology on Information Assurance Laboratory, Beijing, China ' Institute of Electromechanical Engineering, Beijing Polytechnic, Beijing 100176, China ' College of Computer Sciences, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Science and Technology on Information Assurance Laboratory, Beijing, China

Abstract: The problem of resources management in the cloud environment, focusing on the platform as a service (PaaS), satisfying the demands of users, and relieving the load on the server in high concurrency, requires attention. After analysing the resource orchestration technology on PaaS, this paper presents a dynamic orchestration optimisation framework based on autoregressive integrated moving average model (ARIMA) model. The architecture is based on an OpenStack infrastructure as a service (IaaS), and combines with Cloudify, a resource orchestration software on the PaaS. Adjustments may be made in advance by predicting the resource consumption in the next time period. Experiments showed that this architecture can effectively shorten the concurrent response time and improve the utilisation of memory.

Keywords: Cloudify; OpenStack; cloud computing; orchestration.

DOI: 10.1504/IJSPM.2019.104116

International Journal of Simulation and Process Modelling, 2019 Vol.14 No.5, pp.420 - 430

Received: 16 Aug 2018
Accepted: 12 Jan 2019

Published online: 09 Dec 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article