Integrated access and backhaul (IAB) is one of the promising techniques for 5G networks and beyond (6G), in which the same node/hardware is used to provide both backhaul and cellular services in a multi-hop architecture. Due to the sensitivity of the backhaul links with high rate/reliability demands, proper network planning is needed to ensure the IAB network performs with the desired performance levels. In this paper, we study the effect of infrastructure planning and optimization on the coverage of IAB networks. We concentrate on the cases where the fiber connectivity to the nodes is constrained due to cost. Thereby, we study the performance gains and energy efficiency in the presence of free-space optical (FSO) communication links. Our results indicate hybrid fiber/FSO deployments offer substantial cost savings compared to fully fibered networks, suggesting a beneficial trade-off for strategic link deployment while improving the service coverage probability. As we show, with proper network planning, the service coverage, energy efficiency, and cost efficiency can be improved.

Traffic in backbone networks is characterized by strong seasonality, with clear patterns visible in various services and applications based on their usage throughout the day. Data-driven networks can learn these patterns to manage resources more efficiently as they become increasingly saturated. In this paper, we explore the benefits of traffic prediction and grooming across different traffic patterns. To achieve this, we simulate network operations using uniform sets of time-varying connection requests, where all demands in a simulation share the same traffic pattern related to a specific network-based service or application. Our goal is to thoroughly evaluate the robustness of the proposed techniques across diverse scenarios. The results will facilitate the design of future application-aware algorithms for the most efficient handling of each traffic pattern.

It is essential to be able to identify hidden anomalies in order to fully automate optical networks. This requires specific features from the application programming interfaces (APIs) used by the control plane and network monitoring solution. One of the solutions, Transport API (TAPI), utilizes advanced techniques in telemetry streaming. The update policy in TAPI enables key performance indicators (KPIs) to be transmitted only when changes are detected. In this paper, we explore how the update policy configuration of TAPI and the use of unsupervised learning (UL) interact in detecting previously unseen anomalies. Results reveal various trade-offs that network operators need to consider, including compute and time overhead, as well as the overall accuracy of UL.

Relentless competition among communications ser-vice providers, increasing expectations of users, and escalating variety of new applications and services trigger the need to develop advanced solutions that can support the optimization and management of communication networks. Prediction of network traffic is one of the possible solutions providing additional data analytics information. In this paper, we consider an application-aware optical network that transmits various types of time-varying traffic. We analyze traffic prediction under two scenarios. As a reference scenario, we assume that the system is aware of multiple traffic types, and various prediction models are developed and trained for each traffic type separately. The second scenario - agnostic prediction - assumes that a single prediction model agnostic of the traffic types is created and trained. We develop several models for each of the analyzed scenarios using various regression methods. Next, we run extensive numerical experiments on real and semi-synthetic datasets to verify the performance of the proposed regression methods and compare both analyzed scenarios. The obtained results demonstrate that the proposed prediction model agnostic to the forecasted type of traffic provides excellent results; in many cases, it outperforms the reference scenario with dedicated prediction models for each traffic type. Moreover, we evaluate the proposed model's adaptability to predict unseen-before traffic types, showing that the quality loss is negligible. Finally, we test the proposed framework in a multilayer network with time-varying traffic and show how using an aggregated model does not lead to bandwidth blocking increase compared to dedicated prediction models.

With the ever-increasing traffic load, the prediction of future traffic patterns can bring significant benefits to network optimization. The appropriate choice of a forecasting model is crucial for the successful allocation of network resources, especially in application-aware networks, differentiating unique requirements of diverse traffic types. In this paper, we present a novel customizable metric called Allocation Outside Blocking Threshold (AOBT), linking the problem of network traffic prediction and bandwidth blocking probability in dynamic routing. Through extensive case studies, we show that the choice of a traffic prediction model is dependent on the metric, traffic type, and forecast horizon. We establish that the traffic prediction method should be selected individually for each unique scenario and traffic type in an application-aware network and how the AOBT metric enables it.

This work focuses on analysis of various sharing approaches in survivable spectrally-spatially flexible optical networks (SS-FONs), which use flexible optical signal regeneration based on transponders connected in back-to-back (B2B) configurations. Two sharing approaches, namely, spectrum sharing and transponder sharing are analyzed in the context of dynamic traffic. To tackle the considered optimization problem, we propose a new Adaptive Survivable Routing with B2B Regeneration with Spectrum and Transponder Sharing (ASRBR-STS) algorithm that allows to establish dynamic routing requests in translucent and survivable SS-FON with spectrum and transponder sharing. The simulations are conducted using two topologies: European and US. The obtained results show that the proposed algorithm outperforms other methods. Moreover, the results clearly demonstrate that spectrum and transponder sharing significantly improves the performance in terms of the network throughput (amount of served traffic), i.e., up to 55% more protected traffic can be served when compared to the non-sharing approach.

In this paper, we analyze the problem of transceiver sharing in survivable spectrally-spatially flexible optical networks (SS-FONs) that realize transmission of spectral super-channels and where flexible signal regeneration is provided by transceivers operating in back-to-back (B2B) configurations. Namely, to improve network throughput, we propose to use a backup transceiver sharing approach for protection of lightpaths provisioned in the network. To address the considered problem, we develop an Adaptive Survivable Routing with Back-to-Back Regeneration with Transceiver Sharing (ASRBR-TS) algorithm that serves dynamic routing requests protected by backup paths. The ASRBR-TS algorithm accounts for limited spectrum and transceiver resources and makes use of the flexibility of the B2B regeneration. With the use of ASRBR-TS, we examine potential performance gains of transceiver sharing in terms of bandwidth blocking probability (BBP) and the traffic load that can be provisioned in the network with 1% BBP threshold. The numerical experiments are run for two representative network topologies with realistic assumptions concerning applied physical model. In the experiments, we also analyze a squeezed protection approach, in which the backup path supports only a part of the bit-rate realized on the working path. The results show that the transceiver sharing approach can significantly improve the network performance, i.e., it allows to provision up to 49% more traffic when compared with a dedicated transceiver approach.