Traditional rule-based or static management approaches struggle to cope with the dynamic, multi-layered nature of 5G/6G networks, creating a strong motivation for AI-native solutions – management systems built from the ground up with artificial intelligence – to enable autonomous, real-time network control. In this work, we introduce GNN-ATIVE, an AI-native orchestration framework that leverages Graph Neural Networks (GNNs) and knowledge graphs (KGs) in a unified graph-based paradigm for network management. GNN-ATIVE uses a semantic knowledge graph to represent the network’s state and context, employing standard ontologies to ensure consistency and interoperability. Building on this foundation, we design Knowledge Graph enabled Generative Pretrained Transformer (KG-GPT), a novel graph-to-graph Transformer model that performs knowledge-driven reasoning on the KG. KG ingests the structured network state (nodes, links, and attributes) and infers optimal configurations or management actions, serving as a high-level decision engine for the orchestrator. We implement and evaluate GNN-ATIVE on an Optical Transport Network (OTN) testbed using real network components. The results demonstrate that GNN-ATIVE can effectively manage OTN resources and adapt to network changes while achieving low-latency inference for decision making.

The growth of telecommunication networks towards 6 G, owing to the complexity and heterogeneity, mandates a paradigm shift in network management. Due to the nature of the traditional Policy-based Management and Control (PBMC), aspects of network management have to be well thought out during the design phase making the system inflexible. Artificial Intelligence (AI) is expected to augment PBMC by introducing run-time flexibility and adaptability. The use of AI becomes more pressing, when 6 G systems are considered to host more diverse technologies catering to specific use cases thus increasing the burden on operators. This article presents “GraphGPT”, a transformer-based Knowledge Graph (KG) reasoning model prepared using light-weight and tailored datasets for 6 G. The implementation and evaluation details present the first look of the model.

Network management systems for beyond 5G (B5G) and 6G networks today require efficient approaches for handling increased heterogeneity, network-function dis-aggregation, performance requirements, and optimizing networks to support highly diverse use cases. While the Open-Radio Access Network (O-RAN) Service Management and Orchestration (SMO) frameworks efficiently manage RAN and cloud infrastructure, the fragmentation of management platforms across RAN, Core Network (CN), and Transport Network (TN) introduces operational inefficiencies, particularly in Non-Public Networks (NPNs) deployments. This paper proposes a novel extension to the O-RAN SMO architecture, integrating CN and TN management functionalities into a unified control framework. By exploiting AI/ML-driven$\mathrm{x} / \text{rApps}$and a converged data analytics pipeline, the proposed architecture enhances SMO's fault management, resource optimization, and service continuity capabilities. Our implementation validates the feasibility of the proposed SMO extension, demonstrating subscriber-specific QoS assurance through O-RAN-based mobility management mechanisms. The proposed approach successfully shows how RAN-/Core-converged SMOs enable significant enhancements to O-RAN's x/rApps, allowing for subscriber-specific as well as application-specific differentiated QoS assurance.

The continuously increasing amount of sensors in cyber-physical systems requires efficient edge computing architectures which follow the paradigm to process data where it emerges. Encapsulated software functions enable the unrestricted allocation of software functions to the edge, but lack real-time execution semantics and a real-time scheduling algorithm. In general, the allocation and scheduling of multiple constraint tasks in a distributed execution environment is classified as NP-complete. Nevertheless, by using prior knowledge, we are able to set up an optimal scheduling algorithm which leads to a highly reduced time complexity. Thus, our efficient approach enables modularity even for safety-critical real-time systems.

With the increase of the volume of data produced by IoT devices, there is a growing demand of applications capable of elaborating data anywhere along the IoT-to-Cloud path (Edge/Fog). In industrial environments, strict real-time constraints require computation to run as close to the data origin as possible (e.g., IoT Gateway or Edge nodes), whilst batch-wise tasks such as Big Data analytics and Machine Learning model training are advised to run on the Cloud, where computing resources are abundant. The H2020 IoTwins project leverages the digital twin concept to implement virtual representation of physical assets (e.g., machine parts, machines, production/control processes) and deliver a software platform that will help enterprises, and in particular SMEs, to build highly innovative, AI-based services that exploit the potential of IoT/Edge/Cloud computing paradigms. In this paper, we discuss the design principles of the IoTwins reference architecture, delving into technical details of its components and offered functionalities, and propose an exemplary software implementation.

The distributed Cloud Computing paradigm is continuously being adopted within the industrial automation domain. The most distinguishing feature of these Edge Clouds relates to their ability to provide low-latency and even hard realtime services. As infrastructure deployments can be rather heterogeneous in their nature, service providers require precise means for estimating end-to-end application latency behavior, in order to know performance boundaries that can be met for defining certain Service Level Agreements (SLAs). Although network performance tools exist for many years, mechanisms for assessing hard real-time performance of applications in distributed Edge Cloud environments have not been considered extensively yet. Therefore, we use a built-in feature of the Linux Kernel, the extended Berkeley Packet Filter (eBPF), to measure delays between targeted endpoints in the kernel stack, that enable the user to gain deeper and more accurate measurements of events as compared to generalized approaches (as accurate as eBPF / the time-stamping facility from the kernel). As a result, the real-time behavior of particular Edge Cloud deployments, including its hosted applications, can be profiled in detail by end-users as well as service-providers. Within our evaluation we have monitored a cyclic transmission of packets with a scheduled delay of under 190 μs and measured a round trip time under 2 ms. Future work include profiling the real-time behavior of potentially hosted time-critical applications, such as virtual Programmable Logic Controllers (vPLCs), over real-time networks, such Time Sensitive Networking (TSN); the extension towards dynamically configured real-time networks; and finally its application to future organic, self-optimizing Ultra-Reliable Low-Latency Communication 6G core networks.

While great emphasis is given in the current literature about the potential of leveraging the cloud for testing purposes, the authors have scarce factual evidence from real‐world industrial contexts about the motivations, drawbacks and benefits related to the adoption of automated cloud testing technology. In this study, the authors present an empirical study undertaken within the ongoing European Project ElasTest, which has developed an open source platform for end‐to‐end testing of large distributed systems. This study aims at validating the ElasTest solution, and consists of the assessment of four demonstrators belonging to different application domains, namely e‐commerce, 5G networking, WebRTC and Internet of Things. For each demonstrator, they collected differing requirements, and achieved varying results, both positive and negative, showing that cloud testing needs careful assessment before adoption.