XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Jeddi S, sharifian S. A multiband GMDH ensemble algorithm for NFV traffic prediction in cloud computing infrastructure. Journal of Iranian Association of Electrical and Electronics Engineers 2021; 18 (4) :175-184
URL: http://jiaeee.com/article-1-662-en.html
Amirkabir University of Technology
Abstract:   (1280 Views)
Network function virtualization (NFV) is an emerging technology. NFV enables networks to use software defined virtual functions such as firewalls, load balancers, and WAN accelerators, conventionally running on dedicated hardware. In order to provide NFV resources and meet SLA (Service Level Agreement) conditions, minimize energy consumption and utilize physical resources efficiently, dynamic resource allocation in cloud is an essential task. Since network traffic is changing rapidly, an optimized resource allocation strategy should consider resource auto-scaling property for NFV services.in order to scale cloud resources, we should predict NFV workload. Existing prediction methods are providing poor results for highly volatile and fluctuating time series such as cloud workloads. So, we propose a multiband decomposed wavelet prediction by GMDH ensemble algorithm for NFV traffic preciction. We evaluate the proposed model with two cloud workload traces. The results show the MAPE of prediction by the wavelet -GMDH method improved by 7.2% in compare to best perevious work in recent papers.

 
Full-Text [PDF 1127 kb]   (503 Downloads)    
Type of Article: Research | Subject: Electronic
Received: 2018/09/7 | Accepted: 2019/09/23 | Published: 2021/10/14

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0)

© 2024 CC BY-NC 4.0 | Journal of Iranian Association of Electrical and Electronics Engineers

Designed & Developed by : Yektaweb