Network behavior modelling is a central issue for model-based approaches of self-diagnosis of telecommunication networks. There are two methods to build such models. The model can be built from expert knowledge acquired from network standards and/or the model can be learnt from data generated by network components by data mining algorithms. In a recent work, we proposed a model of architecture and fault propagation for the GPON-FTTH (Gigabit Passive Optical Network-Fiber To The Home) access network. This model is based on a Bayesian network which encodes expert knowledge. This includes dependencies that encode fault propagation and conditional probability distributions that encode the strength of those dependencies. In this paper we consider the problem of automatically tuning the above mentioned probability distributions. This is a parameter estimation problem under missing data conditions that we solve with the Expectation Maximization (EM) algorithm. Conditional probability distributions are learnt from the tremendous amount of alarms generated by an operating GPON-FTTH network during two months in 2015. Self-diagnosis is carried out to analyze the root cause of alarms. The performance of the diagnosis is evaluated with respect to an expert system based on deterministic decision rules currently used by the Internet Access Provider to diagnose network problems.

Fixed-mobile convergence initially focused on optimizing fixed and mobile telephone infrastructure for voice services. The appearance of VoIP and smartphones, the growing popularity of social networks and video hosting services, the emerging of 5G, Internet of Things, machine-to-machine communication and ever newer over-the-top services motivated manufacturers, network operators and service providers to refocus and data delivery. The tutorial highlights the structural and functional aspects for efficiently instrumenting this convergence process, including infrastructure considerations, network function virtualization, software defined networking, unified functionality. The presentations are embedded into an overview of the past efforts, a summary of the state of the art, and a look-ahead for future communications networks. The authors are members of the Combo European consortium working on fixed-mobile convergence.

In this paper we study different options for the survivability implementation in MPLS over optical transport networks (OTN) in terms of network resource usage and configuration cost. We investigate two approaches to the survivability deployment: single layer and multilayer survivability and present various methods for spare capacity allocation (SCA) to reroute disrupted traffic. The comparative analysis shows the influence of the offered traffic granularity and the physical network structure on the survivability cost: for high bandwidth LSPs, close to the optical channel capacity, the multilayer survivability outperforms the single layer one, whereas for low bandwidth LSPs the single layer survivability is more cost-efficient. On the other hand, sparse networks of low connectivity parameter use more wavelengths for optical path routing and increase the configuration cost, as compared with dense networks. We demonstrate that by mapping efficiently the spare capacity of the MPLS layer onto the resources of the optical layer one can achieve up to 22% savings in the total configuration cost and up to 37% in the optical layer cost. Further savings (up to 9 %) in the wavelength use can be obtained with the integrated approach to network configuration over the sequential one, however, at the increase in the optimization problem complexity. These results are based on a cost model with different cost variations, and were obtained for networks targeted to a nationwide coverage