The evolution towards 6G edge-cloud ecosystems demands autonomous, intent-based network management to handle unprecedented infrastructure complexity. While Large Language Models offer promising capabilities for translating high-level user intents into network configurations, current monolithic approaches suffer from cognitive overload, hallucinations, and a profound inability to safely execute low-level data plane mutations. To bridge this gap, we introduce Edgent, a novel framework that integrates hierarchical Agentic AI with Extended Berkeley Packet Filter technologies via the Model Context Protocol. Edgent utilizes a state-driven Supervisor, enhanced by Retrieval-Augmented Generation, to decompose abstract human intents into deterministic execution graphs and dynamically delegate tasks to domain-specific worker agents. We empirically validate the framework by autonomously deploying a distributed, in-kernel DDoS mitigation pipeline across scaled containerized topologies containing up to 85 nodes. Extensive evaluations demonstrate high orchestration reliability; notably, even heavily quantized Small Language Models (e.g., 4B parameters) achieve near-perfect zero-shot execution and 100% overall task completion through autonomous error recovery. Finally, latency and resource profiling confirm that the multi-agent framework can be efficiently driven by fully localized models compatible with orchestration tasks directly within resource-constrained edge environments, therefore this work positions Edgent as a pragmatic step toward the realization of zero-touch nextgeneration networks.

Traditional SDN controllers are usually deployed as monolithic systems or tightly coupled service chains, limiting their adaptability in distributed or federated network domains. This paper presents eMSN, a microservice-based SDN framework that enables controller decomposition and decentralized multidomain orchestration, providing a foundation for scalable, and domain-aware SDN experimentation. The framework introduces lightweight, containerized microservices that interact via REST APIs and coordinate through a shared ETCD cluster. The main one, called FlowBlocker, collects topology and host information from the emitter, builds a policy-aware decision table, and shares domain-scoped state in ETCD. The latter stores only host/topology data and never flow rules; enforcement decisions remain within FlowBlocker, which installs rules locally via Ryu Core or coordinates with peer FlowBlockers across domains. The architecture supports centralized, partially decentralized, and fully decentralized deployment models. The proof-of-concept implementation uses Docker and Mininet for reproducibility. Functional evaluation demonstrates sub-millisecond Packet-In responsiveness, tens-of-milliseconds policy enforcement latency, and correct blocking of unauthorized traffic.

Software-Defined Networking traditionally relies on the separation of the control and data planes, centralizing network intelligence within a logically unified controller. However, centralizing control functionalities often introduces limitations that negatively impact the overall Quality of Service, particularly in distributed and heterogeneous network scenarios. In this paper, we explore an adaptive approach to orchestrate a microservice-based SDN controller dynamically at the Edge. Building upon our previously introduced frameworks for Microservice-based SDN Controller and for flexible service-model-aware orchestration, we investigate the benefits of adaptively deploying our microservice-based SDN controller’s functionalities at the Edge to enhance QoS. We leverage our orchestration framework to dynamically decide and execute the optimal placement of latency-critical microservices according to real-time monitoring data and evolving user demands. We evaluate the performance by comparing various deployment strategies, focusing on the tradeoff between control plane latency and placement of controller functionalities. Results demonstrate that our adaptive Edge deployment approach has the potential to reduces control plane latency, demonstrating the practical benefits of integrating SDN controller modularity with intelligent service orchestration in dynamic and heterogeneous network environments.

In SDN-enabled disaggregated optical networks, switches and wavelength converters are managed through software abstractions that model their capabilities, enabling greater flexibility and improved performance. While traditional approaches statically assign converters to specific nodes, such abstractions allow wavelength conversion to be considered as a distributed processing function, dynamically migrating across the network like a Cloud-based service. This enhances the ability of the control layer to flexibly allocate conversion resources to reduce blocking occurrences. Additionally, the orchestration layer dynamically selects wavelength allocation policies based on these abstractions, ensuring an optimal balance between performance and resource efficiency. This paper proposes a novel Cloud-native approach to wavelength conversion in disaggregated optical networks. We present a framework for orchestrating and controlling end-to-end services with a focus on lightpath provisioning, supported by a resource availability model that facilitates efficient wavelength selection. Our evaluation compares multiple wavelength assignment algorithms through both static and dynamic simulations. The results highlight key trade-offs among these algorithms in terms of blocking probability, resource utilization, and overall cost efficiency, providing valuable insights for improving the overall network performance.

The growing reliance on digital connectivity has made Internet Service Provider (ISP) networks a critical component of modern society, yet they remain a prime target for cyber threats. In recent years, cyberattacks against ISPs have increased in scale and sophistication, posing severe risks to national security, economic stability, and user privacy. The advent of in-network computing and programmable data plane presents a paradigm shift in network security, offering the flexibility to define, modify, and optimize packet processing logic dynamically. Among these advancements, the P4 programming language plays a crucial role, allowing network operators to implement fine-grained traffic monitoring directly within network devices. By leveraging in-network computation, P4 facilitates real-time anomaly detection, making it a powerful tool for mitigating Distributed Denial of Service (DDoS) attacks. However, orchestrating security functions across a distributed network of P4 switches remains a challenge, requiring an efficient and scalable deployment framework.In this paper, we present an open-source orchestration platform for managing and deploying P4-based security programs to enable real-time DDoS detection. Our solution leverages dynamic programmability to enhance network security. By integrating a novel queue monitoring mechanism directly into the data plane, our approach enables the collection of fine-grained network performance metrics in real-time, facilitating faster and more precise attack detection and mitigation. The proposed framework is highly scalable and adaptable, strengthening ISP networks against evolving cyber threats.

Traditional Cloud-based multimedia transcoding approaches struggle with issues like latency and bandwidth limitations. In this work, we experiment with strategies that exploit Edge computing capabilities to get around such constraints. We focus on an on-demand multimedia transcoding service for real-time video streaming on the uplink, leveraging a state-of-the-art Edge Computing service orchestrator to handle its provisioning. We regard this as a use case for the orchestration platform, with the objective of enhancing the experience of the user as well as keeping important metrics in check, including resource utilization and load distribution over the Edge compute nodes. We perform evaluations on a physical testbed to assess the performance of the Edge-based system using real-world video transcoding workloads.

The Edge-Cloud Continuum represents a paradigm shift in distributed computing, seamlessly integrating resources from cloud data centers to edge devices. However, orchestrating services across this heterogeneous landscape poses significant challenges, as it requires finding a delicate balance between different (and competing) objectives, including service acceptance probability, offered Quality-of-Service, and network energy consumption. To address this challenge, we propose leveraging Multi-Objective Reinforcement Learning (MORL) to approximate the full Pareto Front of service orchestration policies. In contrast to conventional solutions based on single-objective RL, a MORL approach allows a network operator to inspect all possible “optimal” trade-offs, and then decide a posteriori on the orchestration policy that best satisfies the system’s operational requirements. Specifically, we first conduct an extensive measurement study to accurately model the energy consumption of heterogeneous edge devices and servers under various workloads, alongside the resource consumption of popular cloud services. Then, we develop a set-based MORL policy for service orchestration that can adapt to arbitrary network topologies without the need for retraining. Illustrative numerical results against selected heuristics show that our MORL policy outperforms baselines by 30% on average over a broad set of objective preferences, and generalizes to network topologies up to 5x larger than training.

Efficient service provisioning in the Edge-to-Cloud Continuum is of utmost importance for modern applications. While sensible decisions can be taken if enough monitoring data is collected, maintaining continuous telemetry data streams amidst the continuum’s complexity is challenging. This paper introduces CRISP (reConstructing Resource Information for Service Placement), a solution combining data reconstruction and service placement strategies to optimize decisions despite incomplete monitoring data. CRISP utilizes Convolutional Neural Networks and Long Short-Term Memory models for data reconstruction, integrating them with a heuristic algorithm that selects nodes for service component placement. Numerical results demonstrate CRISP’s efficacy in optimizing service provisioning despite missing data, contributing to enhanced resource utilization and service performance in the considered context.

The Edge Computing paradigm is increasingly gaining traction in modern telecommunication scenarios, as it enables the offloading of computational tasks from end devices to a variety of nodes located in close proximity to them. This approach is essential for meeting the ever-stricter Quality of Service requirements imposed by modern applications. Concurrently, the advent of Data Plane Programmability allows for unmatched flexibility on the networking plane, supporting processing of multiple protocols in a logically centralized fashion with simple in-line computation, and offering the possibility to offload additional services to networking equipment. Reaping those benefits necessitates heedful management of resources and infrastructure. This, in turn, calls for the introduction of a service orchestration entity, capable of taking advantage of device heterogeneity to enable efficient and swift service provisioning. This work delves into the potential of introducing an orchestration system able to cope with the challenges of offloading security tasks at the Edge. This effort involves developing and implementing novel architectural components that capitalize on the heterogeneous nature of the Edge infrastructure as well as of the Programmable Data Plane as a potential tool for service offloading. To establish the feasibility and performance of this approach, an industrial scenario is considered, where the integrity of data from legacy devices must be ensured. Following an evaluation of the hashing performance of the Programmable Data Plane in comparison to general-purpose devices, a simulation study is conducted on the overall orchestration system, demonstrating the viability of the proposed approach.

The use of microservice-based applications is becoming more prominent also in the telecommunication field. The current 5G core network, for instance, is already built around the concept of a “Service Based Architecture”, and it is foreseeable that 6G will push even further this concept to enable more flexible and pervasive deployments. However, the increasing complexity of future networks calls for sophisticated platforms that could help network providers with their deployments design. In this framework, a central research trend is the development of digital twins of the physical infrastructures. These digital representations should closely mimic the behavior of the managed system, allowing the operators to test new configurations, analyze what-if scenarios, or train their reinforcement learning algorithms in safe environments. Considering that Kubernetes is becoming the de-facto standard platform for container orchestration and microservice-based application lifecycle management, the implementation of a Kubernetes digital twin requires an accurate characterization of the microservice response time, possibly leveraging suitable Machine Learning techniques trained with measurement data collected in the field. In this paper we introduce a new methodology, based on Mixture Density Networks, to accurately estimate the statistical distribution of the response time of microservice-based applications. We show the improvement in performance with respect to simulation-based inference procedures proposed in literature.

We consider the problem of designing and training a neural network-based orchestrator for fog computing service deployment. Our goal is to train an orchestrator able to optimize diversified and competing QoS requirements, such as blocking probability and service delay, while potentially supporting thousands of fog nodes. To cope with said challenges, we implement our neural orchestrator as a Deep Set (DS) network operating on sets of fog nodes, and we leverage Deep Reinforcement Learning (DRL) with invalid action masking to find an optimal trade-off between competing objectives. Illustrative numerical results show that our Deep Set-based policy generalizes well to problem sizes (i.e., in terms of numbers of fog nodes) up to two orders of magnitude larger than the ones seen during the training phase, outperforming both greedy heuristics and traditional Multi-Layer Perceptron (MLP)-based DRL. In addition, inference times of our DS-based policy are up to an order of magnitude faster than an MLP, allowing for excellent scalability and near real-time online decision-making.

With the establishment of the Everything-as-a-Service (XaaS) paradigm for service provisioning, coupled with the increasingly-demanding requirements imposed by modern network services, the need for a XaaS-aware orchestration system able to cope with a heterogeneous infrastructure, such as the one of Fog Computing environments, is evident. In this work, we describe the working principles and implementation aspects that allow the orchestration of services offered according to the Function-as-a-Service (FaaS) model. The live demonstration will showcase the ability of the system to deploy this kind of services on a suitable test bed, with comments on the procedure and the performance.

Fog Computing can facilitate the adoption of the Everything-as-a-Service paradigm in infrastructure segments that are located closer to the end user, or to the data source, compared to typical Cloud solutions. This enables combining the advantages of flexible service deployment models with the need to cope with the strict requirements–especially in terms of latency–of emerging applications in softwarized networks. Along comes the need to consider aspects of service orchestration specific to the Fog environment and its intrinsically dynamic nature. In this paper we propose an architecture for flexible Fog Computing service orchestration, with a particular focus on the awareness of service deployment models. We discuss the design choices and describe the components and operations of the proposed orchestration system. We then present a complete working implementation of such architecture, including insights on its ability to handle critical orchestration functions such as service discovery and resource monitoring. We also report on the experimental validation of the system and the performance evaluation on real-world equipment, proving the feasibility and the effectiveness of the approach on a dynamic Fog infrastructure. We complement the work by presenting the results of a combinatorial analysis, validated by simulation, of the service model-aware resource selection process. As a result of our investigation, we show that Fog services can be effectively deployed in a matter of a few seconds, or even in less than one second when suitable Fog nodes are available, taking advantage of the awareness of the available service models.

The service function chaining paradigm links ordered service functions via network virtualization, in support of applications with severe network constraints. To provide wide-area (federated) virtual network services, a distributed architecture should orchestrate cooperating or competing processes to generate and maintain virtual paths hosting service function chains while, guaranteeing performance and fast asynchronous consensus even in the presence of failures. To this end, we propose a prototype of an architecture for robust service function chain instantiation with convergence and performance guarantees. To instantiate a service chain, our system uses a fully distributed asynchronous consensus mechanism that has bounds on convergence time and leads to a (1 - 1/e)-approximation ratio with respect to the Pareto optimal chain instantiation, even in the presence of (non-byzantine) failures. Moreover, we show that a better optimal chain approximation cannot exist. To establish the practicality of our approach, we evaluate the system performance, policy tradeoffs, and overhead via simulations and through a prototype implementation. We then describe our extensible management object model and compare our asynchronous consensus's overhead against Raft, a recent decentralized consensus protocol, showing superior performance. We furthermore discuss a new management object model for distributed service function chain instantiation.

The network management community has explored and exploited light, copper, and several wireless spectra (including acoustics) as a media to transfer control or data traffic. Meanwhile, haptic technologies are being explored in end-user (wearable) devices, and Tactile Internet is being used merely as a metaphor. However, with rare exceptions and for smaller scoped projects, to our knowledge, vibration has been largely untouched as networking communication media.In this paper, we share the lessons learned while creating and optimizing a pilot testbed that serves as an inexpensive starting point for the exploration of vibration-defined networking. We demonstrate the feasibility of vibrations as a tool for resiliency, physical layer security, and an innovative method of teaching networking concepts to the Visually Impaired (VI) community.

In this manuscript we describe an experimental work that integrates the NFV-MANO framework with segment routing to support 5G network slicing. The aim is to implement Service Function Chains spanning several cloud domains and the related interconnection transport network in a coordinated way. The manuscript shows the feasibility and the performance effectiveness of this approach, reporting numerical results from practical experiments.

A key aspect that Telco operators must carefully consider when deploying Network Function Virtualization (NFV) solutions is the level of performance that cloud computing software platforms can guarantee in support of the offered network services. OpenStack is widely considered as one of the most relevant open-source frameworks that could accelerate the NFV adoption, also because the evolution of its networking components sees a progressive integration of SDN-based solutions that could significantly improve the performance of cloud-based connectivity services. In this paper, we discuss some of the most recent OpenStack innovations that enable a native SDN-like approach to firewalling functions in the data plane, as well as a native SDN-oriented control of the virtual network infrastructure. Then we present a detailed performance analysis of the aforementioned innovations at both the data and control/management plane, showing the potentials of native SDN adoption within OpenStack toward an integrated solution for production-level NFV deployments.