Neural network based optical network restoration with multiple classes of traffic

Gokisik, D
Bilgen, Semih
Neural-network-based optical network restoration is illustrated over an example in which multiple classes of traffic are considered. Over the pre-planned primary and backup capacity, optimal routing and wavelength assignment is carried out. In case of a network failure, protection routes and optimum flow values on these protection routes are extracted from a previously trained feed-forward neural network which is distributed over the optical data communications network.


Linear mixed model with Laplace distribution (LLMM)
Gökalp Yavuz, Fulya (2018-03-01)
Linear mixed modeling (LMM) is a comprehensive technique used for clustered, panel and longitudinal data. The main assumption of classical LMM is having normally distributed random effects and error terms. However, there are several situations for that we need to use heavier tails distributions than the (multivariate) normal to handle outliers and/or heavy tailness in data. In this study, we focus on LMM using the multivariate Laplace distribution which is known as the heavy tailed alternative to the normal...
Blocking performance of class of service differentiation in survivable all-optical networks
Turan, Bilgehan; Koçyiğit, Altan; Department of Information Systems (2005)
This thesis evaluates the performance of service differentiation with different class of services namely protection, reservation and the best effort services on the NxN meshed torus and the ring topology, which are established as survivable all-optical WDM networks. Blocking probabilities are measured as performance criteria and the effects of different number of wavelengths, different type of services and different topology size with wavelength selective lightpath allocation schemes are investigated by sim...
An SRWNN-based approach on developing a self-learning and self-evolving adaptive control system for motion platforms
Ari, Evrim Onur; Kocaoglan, Erol (2016-02-01)
In this paper, a self-recurrent wavelet neural network (SRWNN)-based indirect adaptive control architecture is modified for performing speed control of a motion platform. The transient behaviour of the original learning algorithm has been improved by modifying the learning rate updates. The contribution of the proposed modification has been verified via both simulations and experiments. Moreover, the performance of the proposed architecture is compared with robust RST designs performed on a similar benchmar...
Evaluation of Ground motion Record Scaling and Selection Methods for Seismic Design and Assessment of Structures
Ay, Bekir Özer; Crowley, Helen (null; 2015-10-16)
Amplitude scaling and selection of ground-motion records are frequently used tools to obtain a group of accelerograms suitable for structural performance assessment for a given hazard level. To provide a suitable set of records to be used in nonlinear dynamic analysis either to estimate median structural response or to predict its full probability distribution, “n” scaled ground motions that best match with target spectrum are selected. Common concerns related with this approach are the use of appropriate d...
SUBASI, A; GURAN, H (1994-04-14)
The presented work is a study of performance of delta switching interconnection networks (INS). Delta networks are used for interconnecting processors to memory modules in multiprocessor systems. Buffered delta networks have buffers to store the incoming packets. In this work, a new model for the multibuffered delta networks, Which may be called as dynamic buffered delta networks, are proposed and esamined. The buffered delta networks were proposed before may be called as static buffered delta networks. A s...
Citation Formats
D. Gokisik and S. Bilgen, “Neural network based optical network restoration with multiple classes of traffic,” COMPUTER AND INFORMATION SCIENCES - ISCIS 2003, pp. 771–778, 2003, Accessed: 00, 2020. [Online]. Available: