Real-time optical path control method that utilizes multiple support vector machines for traffic prediction

Hiroshi Kawase; Yojiro Mori; Hiroshi Hasegawa; Ken-ichi Sato

doi:10.1117/12.2209463

13 February 2016 Real-time optical path control method that utilizes multiple support vector machines for traffic prediction

Hiroshi Kawase, Yojiro Mori, Hiroshi Hasegawa, Ken-ichi Sato

Author Affiliations +

Proceedings Volume 9773, Optical Metro Networks and Short-Haul Systems VIII; 97730I (2016) https://doi.org/10.1117/12.2209463
Event: SPIE OPTO, 2016, San Francisco, California, United States

Abstract

An effective solution to the continuous Internet traffic expansion is to offload traffic to lower layers such as the L2 or L1 optical layers. One possible approach is to introduce dynamic optical path operations such as adaptive establishment/tear down according to traffic variation. Path operations cannot be done instantaneously; hence, traffic prediction is essential. Conventional prediction techniques need optimal parameter values to be determined in advance by averaging long-term variations from the past. However, this does not allow adaptation to the ever-changing short-term variations expected to be common in future networks. In this paper, we propose a real-time optical path control method based on a machinelearning technique involving support vector machines (SVMs). A SVM learns the most recent traffic characteristics, and so enables better adaptation to temporal traffic variations than conventional techniques. The difficulty lies in determining how to minimize the time gap between optical path operation and buffer management at the originating points of those paths. The gap makes the required learning data set enormous and the learning process costly. To resolve the problem, we propose the adoption of multiple SVMs running in parallel, trained with non-overlapping subsets of the original data set. The maximum value of the outputs of these SVMs will be the estimated number of necessary paths. Numerical experiments prove that our proposed method outperforms a conventional prediction method, the autoregressive moving average method with optimal parameter values determined by Akaike’s information criterion, and reduces the packet-loss ratio by up to 98%.

Citation Download Citation

Hiroshi Kawase, Yojiro Mori, Hiroshi Hasegawa, and Ken-ichi Sato "Real-time optical path control method that utilizes multiple support vector machines for traffic prediction", Proc. SPIE 9773, Optical Metro Networks and Short-Haul Systems VIII, 97730I (13 February 2016); https://doi.org/10.1117/12.2209463

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Optical networks

Data processing

Statistical analysis

Artificial neural networks

Current controlled current source

Explosives

Machine learning

Show All Keywords

Keywords/Phrases

Search In:

Publication Years