No abstract

| Rigid fixed-grid wavelength division multiplexing (WDM) optical networks can no longer keep up with the emerging bandwidth-hungry and highly dynamic services in an efficient manner. As the available spectrum in optical fibers becomes occupied and is approaching fundamental limits, the research community has focused on seeking more advanced optical transmission and networking solutions that utilize the available bandwidth more effectively. To this end, the flexible/ elastic optical networking paradigm has emerged as a way to offer efficient use of the available optical resources. In this work, we provide a comprehensive view of the different pieces composing the ''flexible networking puzzle'' with special attention given to capturing the occurring interactions between different research fields. Only when these interrelations are clearly defined, an optimal network-wide solution can be offered. Physical layer technological aspects, network optimization for flexible networks, and control plane aspects are examined. Furthermore, future research directions and open issues are discussed.

The traffic classification problem has recently attracted the interest of both network operators and researchers. Several machine learning (ML) methods have been proposed in the literature as a promising solution to this problem. Surprisingly, very few works have studied the traffic classification problem with Sampled NetFlow data. However, Sampled NetFlow is a widely extended monitoring solution among network operators. In this paper we aim to fulfill this gap. First, we analyze the performance of current ML methods with NetFlow by adapting a popular ML-based technique. The results show that, although the adapted method is able to obtain similar accuracy than previous packet-based methods (≈90%), its accuracy degrades drastically in the presence of sampling. In order to reduce this impact, we propose a solution to network operators that is able to operate with Sampled NetFlow data and achieve good accuracy in the presence of sampling.

No abstract

Traffic classification is an important aspect in network operation and management, but challenging from a research perspective. During the last decade, several works have proposed different methods for traffic classification. Although most proposed methods achieve high accuracy, they present several practical limitations that hinder their actual deployment in production networks. For example, existing methods often require a costly training phase or expensive hardware, while their results have relatively low completeness. In this paper, we address these practical limitations by proposing an autonomic traffic classification system for large networks. Our system combines multiple classification techniques to leverage their advantages and minimize the limitations they present when used alone. Our system can operate with Sampled NetFlow data making it easier to deploy in production networks to assist network operation and management tasks. The main novelty of our system is that it can automatically retrain itself in order to sustain a high classification accuracy along time. We evaluate our solution using a 14-day trace from a large production network and show that our system can sustain an accuracy greater than 96%, even in presence of sampling, during long periods of time. The proposed system has been deployed in production in the Catalan Research and Education network and it is currently being used by network managers of more than 90 institutions connected to this network.