Daily user-online load forecasting for social network site based on the DFT resampling interpolation with periodic extension
by Zong-chang Yang
International Journal of Information and Communication Technology (IJICT), Vol. 10, No. 2, 2017

Abstract: Along with rapid development of the internet, a new type of information networks called 'online social networks' are emerging in popularity, which have been one global phenomenon. Then analysis and forecasting of user-online load movement for one social network site is increasingly important because of its significant effect on web traffic, information propagation, resource allocation, maintenance management and commercial operation. In this study, it is found that the daily online load movement roughly exhibits daily cyclical variations. Then with periodic extension for the daily user-online load movement, a forecast approach based on the called discrete Fourier transform (DFT) resampling interpolation is proposed, in which two-factor up-sampling is performed on the periodically adjusted user-online load observed sequence to predict (estimate) its future movement. Experiments and result analysis indicate potentiality of the proposed method that it yields satisfying results in forecasting daily user-online load movements at the Chinese social network websites.

Online publication date: Tue, 07-Feb-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Information and Communication Technology (IJICT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com