Cloud resource orchestration optimisation based on ARIMA. (9th December 2019)

• Record Type: Journal Article
• Authors: Qin, Hua; Yu, Min; Lai, Yingxu; Liu, Zenghui; Liu, Jing
• Is Part Of: International journal of simulation and process modelling. Volume 14:Number 5(2019)
• Page Start: 420
• Page End: 430
• Publication Date: 2019-12-09
• Subjects: Cloudify -- OpenStack -- cloud computing -- orchestration; Management -- Computer simulation -- Periodicals; Mathematical models -- Periodicals; Operations research -- Periodicals; Simulation methods -- Periodicals; 003.05
• Languages: English
• ISSNs: 1740-2123

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.