Share Email Print
cover

Proceedings Paper

Using cloud association rule data mining approach in optical networks
Author(s): Bin Ma
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In the current DWDM network, one of the critical design issues in the utilization of networks is careful planning to minimize burst dropping resulting from resource contention. The provision of suitable planning before metadata are sent is critical to improve the rate of successful transmission. In this paper, we attempt to adopt a novel data mining approaches to determining a suitable routing path in the OBS network. Instead of using label switching techniques in DWDM, we proposed the hybrid OBS routing planning on the basics of Cloud Association Rules Algorithm, thus reduced the transmission collision rate in OBS routing. This paper searches for the optimal routing path from all the possible routing paths using cloud association rule approach with Apriori-gen algorithm based on the PACNet topology. The heuristic rules discovered by Apriori-gen algorithm are stored in the Knowledge Base (KB) as references for determining the most suitable routing path. The Knowledge Base of the routing path are set up by means of optimal path routing with the highest successful rate which is mined from the database of historical routing paths using cloud association rules. The experiment results show that the successful rates of routing paths obtained by the proposed routing planning approach can effectively improve the successful rates of transmission.

Paper Details

Date Published: 19 November 2007
PDF: 10 pages
Proc. SPIE 6783, Optical Transmission, Switching, and Subsystems V, 67833S (19 November 2007); doi: 10.1117/12.742814
Show Author Affiliations
Bin Ma, Chongqing Univ. of Posts and Telecommunications (China)


Published in SPIE Proceedings Vol. 6783:
Optical Transmission, Switching, and Subsystems V
Dominique Chiaroni; Wanyi Gu; Ken-ichi Kitayama; Chang-Soo Park, Editor(s)

© SPIE. Terms of Use
Back to Top