This paper presents the design and implementation of an Artificial Intelligence Control Plane (AICP) for deterministic networks, emphasizing the Proof-of-Concept (PoC) demonstration. The AICP framework integrates AI, digital twin technology, and real-time telemetry to manage complex network environments, ensuring reliable and low-latency communication. The PoC showcases the practical viability of the AICP by dynamically adapting to varying network demands and maintaining stringent to the Key Performance Indicator (KPI)s of the service. Extensive testing and real-world simulations highlight the framework's potential to enhance the efficiency and resilience of industrial communication networks.

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.

This paper quantifies the potential reduction in the number of required transceivers that the use of probabilistic constellation shaping (PCS) can bring to Flex-Grid over multicore fiber (MCF) optical backbone networks, which can directly lead to a reduction in network capital expenditure (CAPEX). Results from two different backbone networks illustrate that PCS can significantly decrease the number of required transceivers compared to using traditional modulation formats, thanks to the finer granularity in spectral efficiency. The observed reduction becomes more prominent (up to 22.3%) as the traffic profile bit-rates and the network physical distances increase.

Following the Industry 4.0 vision of a full digitization of the industry, time-critical services and applications, allowing network infrastructures to deliver information with determinism and reliability, are becoming more and more relevant for a set of vertical sectors. As a consequence, deterministic network solutions are progressively emerging, albeit they are still bounded to specific technological domains. Even considering the existence of interconnected deterministic networks, the provision of an end-to-end (E2E) deterministic service over them must rely on a specific control plane architecture, capable of seamlessly integrate and control the underlying multi-technology data plane. In this work, we envision such a control plane solution, extending previous works and exploiting several innovations and novel architectural concepts. The proposed control architecture is service-centric, in order to provide the necessary flexibility, scalability, and modularity to deal with a heterogenous data plane. The architecture is hierarchical and encompasses a set of management platforms to interact with specific network technologies overarched by an E2E platform for the management, monitoring, and control of E2E deterministic services. Furthermore, Artificial Intelligence (AI) and Digital Twinning are used to enable network predictability and automation, as well as smart resource allocation, to ensure service reliability in dynamic scenarios where existing services may terminate and new ones may need to be deployed.

Service quality assurance is of capital importance in modern cloud and network infrastructures, especially in multi-domain scenarios, where multiple operators collaborate to provide end-to-end (E2E) services. However, due to the dynamics of the multiple infrastructures and deployed services, it may be difficult to identify which domains need to perform (re-)configuration operations, named actuations, to keep the quality of the E2E services. In this regard, Machine Learning (ML) techniques appear as an interesting solution for guiding the actuation systems in multi-domain scenarios. With this in mind, we present a novel approach for self-optimised multi-domain service provisioning, leveraging the capacities of Deep Reinforcement Learning (DRL), with a focus on E2E service quality assurance. Running away from traditional approaches, the presented proposal tries to minimize the number of domains that need to actuate rather than determining the exact domain-specific actuations. We compare our proposal to existing strategies in terms of performance, scalability and applicability in real scenarios.

Being able to account for the value of latency introduced by the transport infrastructure is considered a crucial feature for any 5G service provisioning strategy. This paper proposes a methodology for the automatic monitoring of the link latency in networks with a distributed SDN-based control plane architecture. The proposed link monitoring solution does not introduce any overhead in the OpenFlow channel and in the data plane. Experimental tests demonstrate the accuracy of the proposed methodology and its ability to scale to large network instances.

Future networks including the Fifth Generation (5G) and beyond mobile networks shall manage, control and orchestrate the new services for users especially vertical sectors, thereby they shall maximize the potential of 5G infrastructures and their services. Network slicing has emerged as a major new networking paradigm for meeting the diverse requirements of various vertical businesses in virtualized and softwarised 5G networks. SliceNet is a project of the EU 5G Infrastructure Public Private Partnership (5G PPP) and focuses on network slicing as a cornerstone technology in 5G networks. This article describes how the SliceNet Control Plane shall evolve to meet the end-to-end needs of many different vertical businesses. SliceNet Control Plane shall span across multiple administrative domains, by integrating different technologies in each involved segments (RAN, MEC, CN, inter-connectivity). Moreover, SliceNet Control Plane is able to allow verticals to plug their own control logic on top of provisioned slices and specialize their services characteristics while optimizing the use of shared resources, providing dynamic configuration, dynamic management, resource isolation and scalability.

Advances in optical transmission technology are driving the evolution from legacy opaque toward transparent backbone networks. Aiming at reducing the costs and energy consumption, transparent networks allow the data to be kept optical end to end and thus removing the majority of the expensive optical-electrical-optical (OEO) devices. Nonetheless, physical impairments accumulate on the signal along optical transparent paths, therefore limiting the system reach and the overall network performance. Furthermore, failures propagate in a transparent network environment and they cannot be easily localized and isolated. So then, transparent networks need to deal with a number of challenges impacting both planning and operation phases. Such challenges require the use of cross-layer approaches, which involve dynamic interactions between the physical layer and the network layer to enable the compensation for mismatching of requirements and resources. In this paper, we aim to provide an overview of such challenges, reporting comparative analysis with a selection of existing solutions and to cast a glance at the open issues for future research.

This paper introduces a Generalized Multi-Protocol Label Switching (GMPLS)-enabled Optical Burst Switched (OBS) network architecture featuring end-to-end QoS-aware burst transport services. The proposed GMPLS/OBS architecture guarantees specific burst loss probability requirements, independently of the offered network load. This is achieved through the configuration of burst Label Switched Paths (LSPs) over the network which are set-up at the GMPLS control plane level only, while it is the OBS node controller the responsible for eventually committing data plane resources upon burst arrival. In such a way, statistical multiplexing feature is preserved and, at the same time, the end-user QoS demands are met by tightly dimensioning the LSPs. A Mixed Integer Linear Programming (MILP) model is devised to provide the optimal burst LSPs dimensioning according to the offered network load and QoS requirements. Moreover, GMPLS-driven capacity reconfigurations are dynamically triggered whenever unfavorable network conditions are detected. The performance of the proposed architecture is extensively assessed on several network scenarios. Future work on the topic is finally outlined.

A novel quality-of-service (QoS) differentiation framework for optical burst switching networks is introduced. Two different methods are provided and subsequently validated. Particularly, both methods aim at using controlled loops as deflection routes, which assures an upper bounded number of hops from source to destination. This yields a 2-fold outcome. First, the insufficient offset time problematic of standard deflection routing under just-enough-time is solved. Second, excessively long delays owing to uncontrolled deflections are avoided. In both methods, the number of allowed loops is proposed as a QoS metric, giving support for class differentiation. This applies to a scenario with heterogeneous traffic demands, each one with different latency and burst loss requirements. The benefits of each proposal are quantified and further compared with existent alternatives by simulations.

This paper reports the main results achieved in the development of a prototype for demonstrating communication services, based on the principles autonomic self-organisation. In particular, the prototype has been designed and developed as a distributed adaptable complex system, realized by means of a population of lightweight autonomic components interacting with each other through self-organizing algorithms. A demonstration prototype to show the collaborative ambient of a rescue team in a critical situation with limited connectivity, such as mobility, data distribution and high probability of disconnection, has been simulated. This prototype show both how these factors represent strong challenges for current software architecture and how the distributed lightweight components can self-organize themselves in order to face these challenges.

This paper considers an optical packet-switched node with limited buffer capabilities and subject to asynchronous, variable-length packets and connection-oriented operation. In such a scenario, we address the problem of providing QoS. While existing solutions focus on applying some form of resources reservation on top of the contention resolution algorithm, here we propose a novel method: given a set of K categories of service to be provided in the network, K different contention resolution algorithms are implemented to cope with the requirements of such service categories. In this paper, we define three different OPS service categories based on three different contention resolution algorithms, we design an ad-hoc pool of fiber delay lines for such a scheme, and evaluate its performance by simulation. The obtained results indicate the merits of our method which opens up future interesting developments for a whole network scenario studies.

The data and voice integration over dense wavelength-division-multiplexing (DAVID) project proposes a metro network architecture based on several wavelength-division-multiplexing (WDM) rings interconnected via a bufferless optical switch called Hub. The Hub provides a programmable interconnection among rings on the basis of the outcome of a scheduling algorithm. Nodes connected to rings groom traffic from Internet protocol routers and Ethernet switches and share ring resources. In this paper, we address the problem of designing efficient centralized scheduling algorithms for supporting multiclass traffic services in the DAVID metro network. Two traffic classes are considered: a best-effort class, and a high-priority class with bandwidth guarantees. We define the multiclass scheduling problem at the Hub considering two different node architectures: a simpler one that relies on a complete separation between transmission and reception resources (i.e., WDM channels) and a more complex one in which nodes fully share transmission and reception channels using an erasure stage to drop received packets, thereby allowing wavelength reuse. We propose both optimum and heuristic solutions, and evaluate their performance by simulation, showing that heuristic solutions exhibit a behavior very close to the optimum solution.