Fernando Morales

Designing, Operating, and Reoptimizing Elastic Optical Networks

Emerging services and applications demanding high bitrate and stringent quality of service requirements are pushing telecom operators to upgrade their core networks based on wavelength-division multiplexing (WDM) to a more flexible technology for the more dynamic and variable traffic that is expected to be conveyed. Finally, academy- and industry-driven research on elastic optical networks (EON) has turned out into a mature enough technology ready to gradually upgrade WDM-based networks. Among others, key EON features include flexible spectrum allocation, connections beyond 100 Gb/s, advanced modulation formats, and elasticity against time-varying traffic. As a consequence of the variety of features involved, network design and algorithms for EONs are remarkably more complex than those for WDM networks. However, new opportunities for network operators to reduce costs arise by exploiting those features; in fact, the classical network life cycle based on fixed periodical planning cycles needs to be adapted to greatly reduce overprovisioning by applying reoptimization techniques to reconfigure the network while it is in operation and to efficiently manage new services, such as datacenter interconnection that will require provisioning multicast connections and elastic spectrum allocation for time-varying traffic. This paper reviews and extends mathematical models and algorithms to solve optimization problems related to the design, operation, and reoptimization of EONs. In addition, two use cases are presented as illustrative examples on how the network life cycle needs to be extended with in-operation planning and data analytics thus adding cognition to the network.

Virtual Network Topology Adaptability Based on Data Analytics for Traffic Prediction

The introduction of new services requiring large and dynamic bitrate connectivity can cause changes in the direction of the traffic in metro and even core network segments throughout the day. This leads to large overprovisioning in statically managed virtual network topologies (VNTs), which are designed to cope with the traffic forecast. To reduce expenses while ensuring the required grade of service, in this paper we propose a VNT reconfiguration approach based on data analytics for traffic prediction (VENTURE). It regularly reconfigures the VNT based on the predicted traffic, thus adapting the topology to both the current and the predicted traffic volume and direction. A machine learning algorithm based on an artificial neural network is used to provide robust and adaptive traffic models. The reconfiguration problem that takes as its input the traffic prediction is modeled mathematically, and a heuristic is proposed to solve it in practical times. To support VENTURE, we propose an architecture that allows collecting and storing data from monitoring at the routers and that is used to train predictive models for every origin-destination pair. Exhaustive simulation results of the algorithm, together with the experimental assessment of the proposed architecture, are finally presented.

On-demand incremental capacity planning in optical transport networks

Incremental planning is performed periodically to decide how a backbone optical network has to be updated to serve the forecast traffic during the next planning period. Based on reliable traffic prediction, new equipment is installed and its capacity is ready to be used. Nonetheless, due to the introduction of new services among other reasons, exact prediction is not usually available. This leads to the installation of more capacity than required, thus increasing network expenditures. In this paper, we propose to reduce expenses by incrementing the capacity of the network as soon as it is required to meet the target performance. Hence, performance metrics are monitored and the incremental capacity (INCA) planning problem is solved on-demand when some metrics drop under a threshold. The INCA problem is mathematically modeled and a heuristic algorithm is proposed to solve the problem in practical computation times. Since solving the INCA problem requires access to both operation and inventory databases, an architecture to support on-demand network planning as well as a model for the inventory is proposed. Exhaustive simulation results, together with its experimental assessment, validate the proposed on-demand INCA planning.

Traffic generation for telecom cloud-based simulation

With the incremental amount of applications running over the telecom cloud architecture it is becoming of paramount importance being able to run simulations aiming at evaluating the performance of such applications. To that end, one of the key elements in the simulation is how to generate network traffic. In this paper we propose realistic traffic functions that can be used for such purposes and present how those functions have been integrated in our OMNET++-based simulator.

Data analytics based origin-destination core traffic modelling

Traffic monitoring is an essential task for network operators since it allows evaluating network performance. Monitoring data from origin-destination (OD) traffic in core virtual network topologies can be collected from packet nodes and stored in a repository for further analysis, e.g., to detect anomalies or to create predicted traffic matrices for the near future. In this paper we propose a set of modules to support data analytics-based algorithms along with a machine learning procedure based on artificial neural networks (ANN) that provides robust and adaptive traffic models.

Dynamic core VNT adaptability based on predictive metro-flow traffic models

MPLS-over-optical virtual network topologies (VNTs) can be adapted to near-future traffic matrices based on predictive models that are estimated by applying data analytics on monitored origin-destination (OD) traffic. However, the deployment of independent SDN controllers for core and metro segments can bring large inefficiencies to this core network reconfiguration based on traffic prediction when traffic flows from metro areas are rerouted to different ingress nodes in the core. In such cases, OD traffic patterns in the core might severely change, thus affecting the quality of the predictive OD models. New traffic model re-estimation usually takes a long time, during which no predictive capabilities are available for the network operator. To alleviate this problem, we propose to extend data analytics to metro networks to obtain predictive models for the metro flows; by knowing how these flows are aggregated into OD pairs in the core, we can also aggregate their predictive models, thus accurately predicting OD traffic and therefore enabling core VNT reconfiguration. To obtain quality metro-flow models, we propose an estimation algorithmthat processes monitored data and returns a predictive model. In addition, a flow controller is proposed for the control architecture to allow metro and core controllers to exchange metro-flow model information. The proposed model aggregation is evaluated through exhaustive simulation, and eventually experimentally assessed together with the flow controller in a testbed connecting premises in CNIT (Pisa, Italy) and UPC (Barcelona, Spain).

Big data analytics for the virtual network topology reconfiguration use case

ABNOs OAM Handler is extended with big data analytics capabilities to anticipate traffic changes in volume and direction. Predicted traffic is used to trigger virtual network topology re-optimization. When the virtual topology needs to be reconfigured, predicted and current traffic matrices are used to find the optimal topology. A heuristic algorithm to adapt current virtual topology to meet both actual demands and expected traffic matrix is proposed. Experimental assessment is carried out on UPCs SYNERGY testbed.

Adapting the virtual network topology to near future traffic

The introduction of new services requiring large and dynamic bitrate connectivity can cause changes in the direction of the traffic in metro and even core network segments along the day. This leads to large overprovisioning in statically managed virtual network topologies (VNT), designed to cope with the traffic forecast. To reduce expenses while ensuring the required grade of service, in this paper we propose the VNT reconfiguration approach based on current and near-future traffic matrices (VENTURE) to regularly adapt the topology to both, the current and future traffic volume and direction. The problem is formally stated and a heuristic algorithm is proposed to solve it.

Incremental capacity planning in optical transport networks based on periodic performance metrics

Incremental planning is performed periodically to decide how a backbone optical network has to be updated to serve the forecast traffic during the next planning period. Based on reliable traffic prediction, new equipment is installed and its capacity is ready to be used. Nonetheless, due among others to the introduction of new services, exact prediction is not usually available, which leads to install more capacity than that required thus, increasing network expenditures. To reduce expenses, we propose to monitor some performance metrics and launch the incremental capacity planning problem (INCA) to meet the target performance when some performance metric drops under a threshold. A heuristic algorithm is proposed to solve INCA in practical times. We show that INCA produces savings in terms of used cards with respect to periodical planning thus, demonstrating the utility of our proposal.