Autonomic load balancing for M2M communication with long-polling
by Shinji Kitagami; Yosuke Kaneko; Ryozo Kiyohara; Takuo Suganuma
International Journal of Space-Based and Situated Computing (IJSSC), Vol. 3, No. 1, 2013

Abstract: In a machine-to-machine (M2M) service system that connects devices to the internet and which provides various remote services, long-polling communication is effective as a communication protocol that simultaneously satisfies requirements of both security and immediacy. It sustains a communication session among devices and servers for a definite period. For this reason, when a medium server for load balancing is introduced into a large-scale M2M service system, it might cause a performance bottleneck. In this paper, we propose an autonomic control method to achieve load distribution and load levelling using only devices and servers, without introducing a medium server. In the proposed method, the device selects the server to connect the subsequent time based on server load information that the server sends to the device when long polling has timed out. In addition, this method achieves levelling of the server load by exchanging load indices among servers.

Online publication date: Fri, 08-Feb-2013

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 Space-Based and Situated Computing (IJSSC):
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