Translator Disclaimer
13 February 2016 Real-time optical path control method that utilizes multiple support vector machines for traffic prediction
Author Affiliations +
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%.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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);

Back to Top