Nokia (Portugal)

We study the energy consumption of wireless sensor network links applying three widely used digital modulation schemes, i.e. MQAM, MPSK, and noncoherent MFSK. For MQAM and MPSK, pulse shaping is considered. Both transmitted signal power and circuit power are taken into account where the former is modeled using the relationship between cutoff rate and signal-to-noise ratio (SNR) and the latter is modeled considering the power consumption of typical hardware used in wireless sensor nodes. For each modulation type, the optimum parameters for minimizing the energy per information bit are derived. Moreover, a comparison among the three modulation types is presented.

The next generation of mobile networks, namely 5G, promises significant qualitative and quantitative advances for multiple vertical domains. However, most studies and investigations assess these advances under the implicit assumption of a single network service provider, with typical national coverage. In this article, we take a close look at the automotive sector and highlight a series of challenges emerging in the context of its inherent (inter)national mobility and the corresponding importance of cross-border and/or multioperator environments. Our target is to pinpoint the key influential factors affecting the transition toward seamless (cooperative) connected and automated mobility services within and across national borders. To this end, we identify and analyze a series of challenges in the areas of, networking, application, security, and regulation. We further present and discuss a series of corresponding solutions investigated in the pragmatic context of our experimental activities.

5G intends to use network slicing to support multiple vertical industries. The dynamic resource sharing and diverse customer requirements bring new challenges towards service assurance (SA), such as automation and customer-centric. As a response to these challenges, this paper proposes a hierarchical, modular, distributed, and scalable SA architecture. This paper highlights an important key feature SA coordination, which is facilitated by three new SA functions, SA interpretation, SA policy management, and data fabric. Three closed-loops are introduced to coordinate and realize automation of service management. Challenges associated with realizing SA are briefly discussed and will be addressed by leveraging the 5G infrastructure developed within the H2020-ICT-17 project 5G-VINNI.

We present a thorough machine-learning framework based on real-time state-of-polarization (SOP) monitoring for robust anomaly identification in optical fiber networks. We exploit SOP data under three different threat scenarios: (i) malicious or critical vibration events, (ii) overlapping mechanical disturbances, and (iii) malicious fiber tapping (eavesdropping). We used various supervised machine learning techniques like k-Nearest Neighbor (k-NN), random forest, extreme gradient boosting (XGBoost), and decision trees to classify different vibration events. We also assessed the framework’s resilience to background interference by superimposing sinusoidal noise at different frequencies and examining its effects on the polarization signatures. This analysis provides insight into how subsurface installations, subject to ambient vibrations, affect detection fidelity. This highlights the sensitivity to which external interference affects polarization fingerprints. Crucially, it demonstrates the system’s capacity to discern and alert on malicious vibration events even in the presence of environmental noise. However, we focus on the necessity of noise-mitigation techniques in real-world implementations while providing a potent, real-time mechanism for multi-threat recognition in the fiber networks.

This paper describes the use of Transfer Learning (TL) using experimental data and a Machine Learning (ML) model pre-trained with a Digital Twin (DT) for the prediction of amplifier failures in optical networks. Using GNPy, an open-source framework, amplifier failure conditions are simulated, creating the required training dataset for the ML model. Later, by implementing TL using optical transmission testbed network data, the model is able to capture realtime network fluctuations, thereby enabling it to distinguish network parameters variations due to any incoming failures from the regular network dynamics, thus enhancing the practical applicability of the model. The model is based on the Long Short-Term Memory (LSTM) ML Technique and is shown to achieve a TL accuracy of 99%, demonstrating the ability of the model to effectively predict failures. This method facilitates early identification and intervention, reduces service interruptions, and improves network reliability. Leveraging TL from network data provides a scalable and data-driven solution to enhance the resilience, efficiency, and ongoing operation of contemporary optical communication systems.

The coordination necessary to make a pass in CAMBADA, a robotic soccer team designed to participate in the RoboCup Middle-Size League (MSL), is presented in this paper. The approach, which relies on information sharing and integration within the team, is based on formations, flexible positionings and dynamic role and positioning assignment. Role assignment is carried out locally on each robot to increase its reactivity. Coordinated procedures for passing and setplays have also been implemented. With this design, CAMBADA reached the 3rd place in RoboCup'2010 and RoboCup'2011. Competition results and performance measures computed from logs and videos of real competition games are presented and discussed.

This study presents a digital twin-enabled framework integrated with a binary classification Machine Learning (ML) model for forecasting failures in Erbium-Doped Fiber Amplifiers (EDFAs). The framework utilizes GNPy, an opensource optical network planning tool, to construct a digital twin that serves as a virtual replica of the physical EDFA system. This digital twin facilitates the estimation of Quality of Transmission (QoT), along with the collection and analysis of key operational parameters. A binary classification model, based on Long Short-Term Memory (LSTM) networks, is trained on the data generated by the digital twin to predict potential EDFA failures, achieving a high prediction accuracy of 98 %. This predictive capability enables early fault detection and proactive maintenance, thereby minimizing unplanned downtime and service disruptions. By incorporating real-time analytics and predictive insights, the proposed approach significantly enhances the reliability, availability, and intelligence of optical network management.

The growing trend of disaggregated and cloud-native RAN architectures in 5G deployments and future 6G networks imposes stringent latency and capacity requirements on optical transport networks. This paper evaluates the feasibility of using standard single-mode fiber (SSMF) and hollow-core fiber (HCF) for supporting x-haul transport across converged metro-access networks. Using a converged metro-access network topology and experimentally modeled performance of a NOKIA ICE-X multi-carrier transceiver, we analyze end-to-end RAN connection from Radio Units (RUs) to Central Units (CUs) via Distributed Units (DUs). Results show that HCF significantly outperforms SSMF in satisfying BER and latency constraints over long distances, particularly in midhaul-dominated scenarios. Case studies with varying DU-CU link lengths further demonstrate HCF's potential to enhance service coverage for future latency-critical and high-capacity deployments. These findings position HCF as a strong candidate for enabling scalable and constraint-compliant optical transport in next-generation RAN infrastructures.

Progress in hollow-core fiber technology may lead to deployments in regional/long-haul networks. This paper proposes an optimal method to selectively upgrade spans of mesh networks with this fiber type. Simulation results show improvements in capacity/reach are achievable while minimizing the amount of hollow-core fiber used. ©2025 The Author(s)

This paper presents a real-time, artificial intelligence (AI)-powered framework for proactive fault detection and dynamic restoration in optical transport networks, leveraging continuous state-of-polarization (SOP) monitoring. By correlating live SOP telemetry from dense wavelength division multiplexing (DWDM) transceivers with machine learning-based analytics, the system accurately detects anomalous polarization patterns arising from external disturbances, commonly preceding fiber damage. Upon identifying critical events, the platform autonomously alerts the open software defined network (SDN) controller, which executes immediate traffic rerouting to ensure uninterrupted service. The solution is experimentally validated on a fournode optical ring, demonstrating precise event classification, low inference latency, and seamless network recovery. This work highlights the transformative potential of SOP-based sensing combined with intelligent control to realize self-healing, resilient optical infrastructures.

This article examines the feasibility of employing converged core-metro-access optical networks to support Radio Access Network (RAN) fronthaul and mid-haul transport under realistic performance constraints. The analysis focuses on the profile of the bit error rate (BER) and the latency evaluation in the context of 5G functional splits. We used a commercially available Nokia ICE-X 400G multi-carrier coherent transceiver, leveraging its digital subcarrier multiplexing (DSCM) capability: Supporting DP-16QAM modulation at 4 GHz channel spacing and 64 GBaud symbol rate per subcarrier. The study is carried out on a representative metro-access topology, where all Radio Unit (RU)- Distributed Unit (DU) - Central Unit (CU) paths are evaluated against BER thresholds and latency bounds for front-haul and mid-haul segments, respectively. The results reveal critical trade-offs between optical reach, modulation format robustness, and latency compliance and demonstrate how mid-haul link distances and routing diversity significantly impact overall transport feasibility for disaggregated RAN deployments. This work emphasizes the potential of transparent optical metro-access infrastructures to serve as an efficient and scalable transport layer for 5G and beyond.

In this demo, we present a real-time, machine-learning-driven framework for early fault detection in optical fiber networks, leveraging continuous State-of-Polarization (SOP) monitoring and angular speed (SOPAS) analysis. By extracting polarization fingerprints from a Polarimeter and feeding them into a trained ML classifier, our system detects and categorizes physical anomalies, such as small hits, slow shake (oscillations), and fast shake (oscillations) on the fiber, before they escalate into service disruptions. This proactive mechanism enables timely alerts and a direction towards dynamic traffic rerouting, preserving network integrity. The demonstration showcases a fully functional remote pipeline that integrates AI-based sensing, classification, and automated response, laying the foundation for self-monitoring optical infrastructures.

In light of the recent advances in hollow-core fiber (HCF) design and manufacturing, wide-scale deployments of this fiber type to realize next-generation optical transport networks may become viable in the foreseeable future, with benefits in terms of lower latency and improved capacity/reach. Nevertheless, several uncertainties remain regarding the properties of HCF that can be manufactured at scale, as well as the specifications of optical amplifiers developed to leverage the negligible low linearity of this fiber type. This work evaluates the performance of HCFs considering a wide range of potential fiber and amplifier parameters and compares them with traditional standard single-mode fiber (SSMF) and pure-silica-core fiber (PSCF). The resulting analysis allows us to determine, at a system and network level, the combination of fiber and amplifier parameters that will allow HCF to become a competitive transmission medium for next-generation optical transport networks.

The exponential rise in bandwidth demand from cloud services, real-time streaming, and emerging AI workloads is rapidly exhausting the scalability headroom of today’s optical transport networks. Conventional advances in coherent transceivers and C-band systems are nearing saturation, underscoring the need for new capacity-scaling strategies. This paper provides a comparative analysis of three orthogonal approaches: (i) transceiver evolution, (ii) spectral expansion through multi-band transmission, and (iii) spatial scaling via space-division multiplexing (SDM). Using a statistical network assessment of the German core network, we quantify their individual and combined impacts on capacity, efficiency, and long-term scalability. Results show that transceiver upgrades alone improve per-fiber throughput by up to 66% (400G to 1.2T) but yield diminishing returns under fixed spectrum. Multi-band operation increases per-fiber capacity by more than 150% when extending from C-band to full C+L+S operation, though it requires band-specific amplification and inter-band power equalization. SDM provides nearly linear scaling, delivering up to a 56-fold increase with six parallel fibers, albeit at higher infrastructure costs. A forward-looking 10-year projection under 25% annual traffic growth reveals that C-band-only systems saturate within 4–6 years, whereas hybrid strategies combining multi-band expansion with SDM sustain multi-petabit traffic, extending scalability by more than fivefold compared to single-band operation. These findings highlight that future-ready optical infrastructures must jointly exploit transceiver efficiency, ultra-wideband photonics, and spatial parallelism to ensure sustainable long-term growth.

Future 6G X-haul networks must satisfy strict latency and service reliability requirements, placing significant pressure on metro-access transport architectures. As deployments become denser, longer and more heterogeneous routes intensify physical-layer impairments, making feasibility assurance and Quality-of-Transport (QoT) evaluation increasingly complex. To address these challenges, this work proposes an AI-driven converged metro-access Optical Network-as-a-Service (ONaaS) architecture based on coherent Point-to-Multipoint (P2MP) transmission using Digital Subcarrier Multiplexing (DSCM). An experimentally characterized transceiver impairment model is embedded into a network-level simulator to perform end-to-end feasibility analysis under strict latency and BER constraints. The results show that connectivity is primarily bounded by accumulated impairments, while Distributed Unit (DU) densification improves performance mainly by shortening path lengths, with limited benefit beyond moderate routing depth. To enable scalable operation, a lightweight machine-learning-based BER estimator is developed for rapid QoT prediction. Trained on a minimal deployment scenario, the Random Forest model generalizes across DU densities and topologies with R 2 > 0 . 98 , reducing evaluation time by several orders of magnitude. A techno-economic assessment further indicates up to 75% reduction in DU-site transceivers and 27%–30% energy savings compared to Point-to-Point (P2P) provisioning, demonstrating the efficiency and scalability of AI-enabled P2MP metro-access convergence for 6G.

This research introduces a novel nonlinear aware approach to design filterless horseshoe-and-spur optical networks aiming to enhance their scalability and cost-effectiveness. By operating at higher power levels, we leverage an increased power budget which helps in reducing the required number of optical amplifiers, a primary cost factor. The network design is framed as an integer linear programming (ILP) problem, optimizing amplifier placement and coupler selection to minimize costs while maintaining a high quality of transmission (QoT). A key contribution is the introduction of a fiber nonlinearity modeling tool in this context, based on the split-step Fourier method (SSFM), which accurately predicts signal distortion and enables the relaxation of conventional power constraints. Our results demonstrate that this nonlinear-aware design can reduce the number of amplifiers by up to 20% as compared to traditional linear designs. This significant improvement in design efficiency leads to substantial capital expenditure (CapEx) savings and a reduced environmental footprint, all without compromising feasibility of the design criteria. This approach proves that allowing a manageable degree of nonlinearity can be a highly effective strategy for creating more scalable and economically viable coherent metro-scale optical networks.

Techno-economic analysis (TEA) plays a vital role in assessing the feasibility and scalability of emerging technologies, especially in the context of innovation and development. Central to any effective TEA is a reliable and detailed model of capital and operational costs. This paper reports the development of such a model for optical networks in the framework of the SEASON project, aimed at supporting a broad spectrum of techno-economic evaluations. The model is constructed using publicly available data and expert insights from project participants. Its generalizable design allows it to be used both within the SEASON project and as a reference for other studies. By harmonizing assumptions and cost parameters, the model fosters consistency across different analyses. It includes cost and power consumption data for a wide range of commercially available optical network components (including transceivers for point-to-multipoint communications), introduces a statistical framework for estimating values for emerging technologies, and provides a cost model for multiband-doped fiber amplifiers. To demonstrate its practical relevance, the paper applies the model to two case studies: an evaluation of how the cost of various multiband node architectures scales with network traffic in meshed topologies and a comparison of different transport solutions to carry fronthaul flows in the radio access network.

This paper presents a method to optimally place a limited number of hollow-core fiber (HCF) spans and high-power booster/in-line-amplifiers in optical mesh networks. Results show it effectively increases network capacity/reach while enforcing the CAPEX-related constraint.

Recent progress in hollow-core fiber (HCF) technology is raising the prospects for the deployment of this type of fiber in future infrastructure upgrades. Although earlier deployments of HCF will take advantage of its low latency property to realize point-to-point links (e.g., in the metro and aggregation network segments), HCF generations with better specifications (improving performance and deployment robustness) may become suitable for more demanding regional and long-haul network applications. In these scenarios, they may co-exist with traditional fiber types in order to ensure, at the network-level, an appropriate balance between latency reduction and the increase of capital expenses associated to both the higher cost of HCF spans and the potential reductions in reach. Therefore, fiber infrastructure owners will face a new design problem, which consists of optimizing the spans where HCF is to be used to minimize service latency while meeting optical performance degradation and cost increase bounds. This paper describes an optimal method to solve this problem, by leveraging the approximation of incoherent accumulation of noise to derive an integer linear programming (ILP) model, and two variants of a heuristic algorithm. A set of detailed simulations over a reference optical transport network highlight the optimality and scalability of the proposed method.

We applied Adjustable Robust Optimization (ARO) to P2MP filterless optical networks facing parameter uncertainty, analyzing robustness, performance, and complexity trade-offs. ARO shows significant advantages over non-adjustable methods, achieving resiliency and reducing amplifiers, particularly at higher uncertainties when non-adjustable counterparts fail.