The use cases associated to the emerging 6G technology demand a dynamic and adaptive network operation capable of addressing the specific requirements of heterogeneous data plane technologies. This demonstration presents the operation of a multi-domain multi-technology control plane architecture designed to provision end-to-end (E2E) connectivity with deterministic performance guarantees. Key innovations highlighted in the demonstration include homogenized configuration of diverse data plane technologies, advanced topology abstraction enabling Key Performance Indicator (KPI)-aware path computation, and the use of digital twin (DT)-based KPI estimation to support deterministic connectivity configuration. These capabilities collectively showcase a promising approach for managing the complexity and performance demands of future 6G networks.

Disaggregated datacenters are promising solutions for executing ML applications. One crucial aspect is the application resilience against infrastructure failures. We analyze application affectation and disruption rates in front of various failure patterns.

The advent of B5G/6G communication infrastructures answers to the requirements posed by emerging use cases and business models, such as Industry 4.0 and autonomous guided vehicles, which impose a set of highly demanding Key Performance Indicators (KPIs). In this regard, time-engineered applications are of particular importance. Said applications, while do not may impose very demanding latencies, they impose a strict control over them to ensure a deterministic service performance. This has given rise to the concept of Deterministic Networking that relies on adding deterministic capabilities to all involved network infrastructures. In general, optical networks are seen as one of the main enablers of latency and jitter-bounded communications, due to their intrinsic deterministic nature. In the framework of Industry 4.0 use cases, such capability can be exploited to enable remote control of optically interconnected smart factories, contributing this way to reduce both CAPEX and OPEX. However, the estimation of KPIs across optically interconnected smart factories/client domains and the provisioning of end-to-end (E2E) services arises several challenges. In this work, we present firstly multiple service provisioning schemas (single-vs multi-path) leveraging the capabilities of the Software Defined Networking (SDN) paradigm. Then, we provide tools and algorithms for best-case KPI estimation and resource allocation decision and analyze the impact of supporting heterogeneous KPIs into the obtained overall network performance.

In the 6G ecosystem, the provisioning of deterministic services with KPI guarantees over multitechnological network domains requires the proper selection of the end-to -end (E2E) paths. Since each technological domain has its own capabilities and resources, in an E2E perspective, the proper selection of the domains to achieve the service KPIs is fundamental. The paper discusses the challenges of the E2E path/domain selection, provides an overall supporting control plane architecture and presents a proof of concept.

Several industrial use cases require the deployment of computing resources over distributed computational facilities. However, quasi-deterministic communications are a must in this scenario, arising the need for performance assurance.

The provisioning of deterministic services over E2E multi-technological infrastructures requires the proper configuration of the resources to match the required Key Performance Indicators (KPI), such as latency and jitter. From an architectural point of view, such configuration is carried out by an SDN-based TSN Controller that has the responsibility to control multiple technologies. In this paper, the main challenges of the TSN controller in such scenario are deeply discussed and its role and implementation in the TIMING architecture is also discussed.

The rising of applications with intense requirements in data volumes, storage space and CPU/GPU utilization, such as Machine Learning/Artificial Intelligence (ML/AI) applications, imposes different challenges on the Data Center Network design and operation. When compared to traditional data centers infrastructures, the recent explored disaggregated optical data center concept may bring multiple benefits in terms of optimized usage of the IT and network resources. Nevertheless, at the same time, it also brings some technical challenges. In such context, the paper discusses both data and control architectural solutions for optical disaggregated data centers for ML/AI applications, focusing on their benefits but also on the associated complexities.

One of the most challenging tasks that autonomous network control systems need to face is to provision end-to-end packet flows spanning several domains. With the advent of time sensitive networking, the co-existence of services and infrastructure with and without time sensitive capabilities adds more complexity to the end-to-end flow management. In particular, avoiding unproper provisioning decisions is key to guarantee stringent quality of service requirements. In this demo, we will showcase an integrated control plane for provisioning flows spanning through domains with and without TSN capabilities. The decision making process will be supported by a digital twin in charge of estimating expected performance indicators before path provisioning acceptance.

Future 6G systems and networks will need to provide support to a wide set of highly demanding use cases. Among others, service provisioning with deterministic guarantees, such as latency and jitter must be supported in SDN-controlled networks. In an E2E scenario, the selection of the paths over the different involved technological domains must be done properly to assure the service guarantees. In this paper, the role of the Path Computation (PC) in an SDN-based control architecture for deterministic services is firstly discussed. E2E Paths selection strategies are then benchmarked.

Many service flows between client and server end-points traverse multiple computer networks even for a private network deployment. The challenge of reducing the complexity of such services is researched on by the European Commission-funded project PREDICT-6G, with special focus on deterministic communications. The provisioning of service flows over a multi-domain multi-technology group of computer networks is a particular challenge if each domain comes with its own set of deterministic communication support. To address that, an overarching End-to-End control plane is being developed in the project and is described herein. As the proposed innovations require a mix of technologies from Standardisation Development Organisations, this paper assesses the proposition of PREDICT-6G against the ongoing work in 3GPP, IETF, ETSI and IEEE.

ML applications present time varying requirements that should be accounted for an optimized deployment. We evaluate the benefits of disaggregated DC infrastructures for supporting them and propose a dynamic re-orchestration strategy for improved resource usage.

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.

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.

We demonstrate that joint orchestration of TSN and optical network domains in support of IIoT applications reduces the TSN blocking by four orders of magnitude and the usage of high priority queues by a 28-100%.

The provisioning of time sensitive end-to-end services in future 6G networks imposes multiple technical challenges, spanning from the data plane to the control and orchestration planes. In particular, the automation of the provisioning and maintenance of connectivity services with deterministic constraints over multiple technology/administrative domains requires control and orchestration solutions able to assure the strict time service requirements. In line with that, the paper investigates some requirements imposed to the control and orchestration planes and it also shows potential enabling architectures for end-to-end service guarantees.

The rise of traffic intensive services and applications is pushing the limits of conventional single band Wavelength Division Multiplexing (WDM) optical networks. As an answer to this challenge, new data plane technologies are being investigated. Multi-band optical networks have raised as a very interesting candidate due to the potential increased capacity they offer thanks to the exploitation of multiple bands of the optical spectrum. Considering the whole telecom ecosystem, multi-band optical networks will coexist with other technological segments (e.g., Radio Access Network (RAN)) with the aim of provisioning services across the end-to-end infrastructure. With the advent of 5G and beyond 5G (B5G) architectures, novel provisioning paradigms are taking preponderance, such as the case of network slicing, which represents a radical paradigm change with respect to legacy business and provisioning models. As such, proper solutions for supporting network slice provisioning and runtime maintenance at the data plane are required. With this in mind, in this paper we present a control and orchestration architecture for the configuration and maintenance of network slices in multi-band optical networks, in support of B5G end-to-end services. Indeed, quality assurance and maintenance at all levels is seen as a cornerstone in B5G architectures. Thus, proper mechanisms adapted to the nature of the underlying sliceable multi-band data plane are required to ensure the quality of deployed slices. In this regard, we also present a novel band-adaptive protection scheme which takes advantage of the properties of the multi-band data plane so as to enhance the robustness of slices against quality degradations. We showcase the provisioning and maintenance of multi-band optical network slices by means of an experimental demonstration in a real testbed deployed at our premises. In addition, we evaluate the performance of the proposed band-adaptive protection scheme for slice quality assurance in front of other strategies by means of extensive simulation analysis in larger network scenarios.

Datacenter (DC) infrastructures are essential to support the requirements posed by nowadays digital society and emerging industrial trends. In such context, a proper actuation management has become especially relevant for service quality assurance operations. In situations where it may be difficult to determine which is the sub-system that needs to apply an actuation, machine learning (ML)-based strategies become valuable assets to orchestrate the actuations to be applied. In this paper, we discuss three strategies for actuation orchestration in inter-/intra-DC scenarios interconnected through optical network systems and benchmark them in terms of requirements that they impose and the achieved performance.

We propose a novel SDN control and orchestration architecture to provide composed IaaS over optical disaggregated data centers. We experimentally validate intent-based mechanisms that make the architecture independent from the underlying physical infrastructure technology. © 2022 The Authors

Due to the limitations of traditional data center (DC) architectures, the concept of infrastructure disaggregation has been proposed. DC resources are separated into multiple blades to be exploited independently. As a result, composable DC (CDC) infrastructures are achieved, enhancing the modularity of resource provisioning. However, disaggregation introduces additional challenges that need to be carefully analyzed. One relates to the potential complexity increase on the orchestration and infrastructure configuration that need to be performed when provisioning resources to support services. This aspect is highly influenced by the distribution of resources at the physical infrastructure. As such, when analyzing the performance of a CDC, it becomes essential to also study the related operational complexity of the resource orchestration and configuration phases. Furthermore, the requirements of several tenant services may impose heterogeneous deployments over the shared physical infrastructure in the form of either disaggregated single-server or multi-server distributions. The associated orchestration/configuration cost is again highly influenced by the data plane architecture of the CDC. With these aspects in mind, in this paper, we provide a methodology for analysis of the complexity of resource orchestration for a service deployment and the associated configuration cost in optical CDCs, considering various service deployment setups. A selected set of CDC architectures found in the literature is employed to quantitatively illustrate how the data plane design and service deployment strategies affect the complexity of infrastructure configuration and resource orchestration.