The introduction of flexible frequency grids and advanced modulation techniques to optical transmission, namely an elastic optical network, requires new routing and spectrum allocation techniques. In this paper, we investigate dynamic two-step routing and spectrum allocation (RSA) methods for elastic optical networks. K-shortest path-based methods as well as spectrum allocation methods are analysed and discussed. Experimental verification of the investigated techniques is provided using simulation software. Simulation results present effectiveness of routing and spectrum allocation methods for analyzed networks using requested bandwidth of connections. Moreover, performance of shortest path first methods improves considerably when a number of candidate paths increases in the UBN24 topology.

As a consequence of increased complexity, technical requirements of services and expectations of end-users, telecommunication networks and systems must still increase their efficiency. Research currently focuses on introducing automation and intelligence into network control and management. Neural Networks form a class of Machine Learning techniques utilizing the supervised learning paradigm. The class is mature and comprises a significant number of algorithms. As a result, Neural Networks-based solutions are widely applicable, also in the context of communications and networking. The aim of this tutorial is twofold. Firstly, to provide fundamentals regarding the Neural Network (NN) method. Secondly, to comprehensively study the examples of applying NN-based solutions to solve problems in different aspects of communications and networking. Studies are supplemented with additional explanations, figures and critical considerations, including pros and cons of using selected methods for particular purposes. This part uniquely complements the tutorial one and facilitates in-depth understanding of NN. Based on the conducted studies, we draw a comparative analysis, summaries and expected future research topics and challenges of using NN in communications and networking.

As global internet traffic continues to increase, network operators face challenges on how to efficiently manage transmission in their networks. Even though attempts are underway to make optical networks automatic, the majority of actions related to traffic engineering are still performed manually by the administrators. In this paper we propose an Automatic Hidden Bypasses approach to enhance resource utilization in optical networks. Our solution uses the software-defined networking concept to automatically create or remove hidden bypasses which are not visible at the network layer. The mechanism increases throughput and reduces transmission delays.

In this paper, we propose a novel priority-aware solution named bypass to handle high- and low-priority traffic in multi-layer networks. Our approach assumes diversification of elastic optical spectrum to ensure additional resources reserved for emergency situations. When congestion occurs, the solution dynamically provides new paths, allocating a hidden spectrum to offload traffic from the congested links in the IP layer. Resources for a bypass are selected based on traffic priority. High-priority traffic always gets the shortest bypasses in terms of physical distance, which minimizes delay. Bypasses for low-priority traffic can be established if the utilization of the spectrum along the path is below the assumed threshold. The software-defined networking controller ensures the global view of the network and cooperation between IP and elastic optical layers. Simulation results show that the solution successfully reduces the amount of rejected high-priority traffic when compared to regular bypasses and when no bypasses are used. Also, overall bandwidth blocking probability is lower when our priority-aware bypasses are used.