Multi-access edge computing provides localized resources within mobile networks to address the requirements of emerging latency-sensitive and computing-intensive applications. At the edge, dynamic requests necessitate sophisticated resource management for adaptive network slicing. This involves optimizing resource allocations, scaling functions, and load balancing to utilize only essential resources under constrained network scenarios. However, existing solutions largely assume static slice counts, ignoring the re-optimization overhead associated with management algorithms when slices fluctuate. Moreover, many approaches rely on simplified energy models that overlook intertemporal resource scheduling and are predominantly evaluated through simulations, neglecting critical practical considerations. This paper presents an incremental cooperative Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for resource management in dynamic edge slicing. The proposed approach optimizes long-term slicing benefits by reducing delay and energy consumption while minimizing retraining overhead in response to slice variations. Furthermore, we implement an urban-wide edge computing testbed based on OpenStack and Kubernetes to validate the algorithm’s performance. Experimental results demonstrate that our incremental MADDPG method outperforms benchmark strategies in aggregated slicing utility and reduces training energy consumption by up to 50% compared to the re-optimization approach.

The emergence of beyond 5G and 6G networks is set to revolutionise telecommunications, addressing the demands of emerging applications through advanced capabilities. At the core of this transformation lies next-generation intelligent service orchestration, which is essential for meeting future Key Performance Indicators (KPIs) and Key Value Indicators (KVIs) such as ultra-low latency, efficient power consumption and resource utilisation. These capabilities require multi-objective, seamless end-to-end service delivery across complex, distributed environments. Achieving such delivery requires scalable and modular system design approaches that support dynamic service composition and adaptability. Cloud-native technologies, underpinned by microservices architectures, plays a pivotal role, but also will introduce challenges in orchestrating resources efficiently across heterogeneous domains. To address these challenges, this paper proposes a solution, Federated Intelligent multi-objective Service function chain Orchestration (FISO) that integrates multi-objective federated profiling to preserve privacy while ensuring efficient end-to-end service delivery. FISO integrates Federated Learning (FL) and Reinforcement Learning (RL). FL is used to collaboratively learn from distributed edge profiling clients without sharing raw data, while RL dynamically guides optimal decision making for resource allocation and Service Function Chain (SFC) placement based on feedback from the federated models. FISO predicts optimal computing and network resources for SFCs, enabling the selection of appropriate edge locations, efficient resource allocation, placement of SFCs, and lifecycle management. Experimental results demonstrated on a pragmatic testbed validate the effectiveness of FISO in efficiently placing requested SFCs within an administrative domain with multiple edge/cloud nodes, predicting optimal CPU, memory, and link capacity resources, and minimising end-to-end latency and energy consumption.

Federated Learning (FL) enables collaborative model training across edge devices while preserving data locally. Deploying FL faces challenges due to device heterogeneity. Using cloud technologies like Kubernetes (K8s) can offer computational elasticity, yet may compromise FL privacy principles. K8s can jeopardise FL privacy by potentially allowing malicious FL clients to access other resources given its flat networking approach. This paper introduces the privacy-preserving K8s operator kubeFlower. It addresses privacy risks via isolation-by-design and differential privacy for data management. Isolation ensures secure resource sharing, while differential privacy safeguards individual data privacy. We introduce the Privacy Preserving Persistent Volume Claimer (P3-VC), which adds noise to data while managing a privacy budget. kubeFlower simplifies FL system management in K8s while ensuring privacy. We tested our approach on a network testbed composed of different geo-located cloud and edge nodes where FL clients are deployed. Our results demonstrate the approach’s efficacy in preserving privacy in K8s-based FL for cloud–edge environments.

Leveraging the potential of Virtualised Network Functions (VNFs) requires a clear understanding of the link between resource consumption and performance. The current state of the art tries to do that by utilising machine learning and specifically Supervised Learning (SL) models for given network environments and VNF types assuming single-objective optimisation targets. Taking a different approach, iOn-Profiler poses a novel VNF profiler optimising multi-resource type allocation and performance objectives using adapted Reinforcement Learning (RL). Our approach can meet key performance indicator targets while minimising multi-resource type consumption and optimising the VNF output rate compared to existing single-objective solutions. Our experimental evaluation with three real-world VNF types over a total of 39 study scenarios (13 per VNF), for three resource types (virtual CPU, memory, and network link capacity), verifies the accuracy of resource allocation predictions and corresponding successful profiling decisions via a benchmark comparison between our RL model and SL models. We also conduct a complementary exhaustive search-space study revealing that different resources impact performance in varying ways per VNF type, implying the necessity of multi-objective optimisation, individualised examination per VNF type, and adaptable online profile learning, such as with the autonomous online learning approach of iOn-Profiler.

HELICON is a novel hierarchical Reinforcement Learning (RL) approach for orchestrating the dynamic placement of Virtual Network Functions (VNFs) in Cloud and Edge 5G environments. It proves capable of addressing an NP-Hard decision-making problem with adopted RL while augmenting the current state of the art in orchestrators with a previously unexplored lightweight distributed and hierarchical RL approach. HELICON can run as a fully autonomous solution or complement orchestrators, thus bridging a significant gap in existing orchestrators, which generally lack intelligent and dynamic adaptation capabilities. Finally, our performance evaluation results over an actual 5G city testbed and use case validate that HELICON outperforms traditional policy-based Open Source MANO and other heuristic policies concerning single or multi-objective optimisation goals. What is more, HELICON’s performance meets with that of node-specific custom supervised learning models, whereas it clearly outperforms supervised learning under dynamic conditions.

Ultra-reliable low-latency communication (URLLC) services are intrinsically challenging to deliver, with many 5G and future services, including mobile game streaming, adding further complexity by demanding zero service downtime in high-mobility scenarios. Solving these challenges is essential and must be addressed beyond mobile gaming to realise a multitude of current and future services like eX-tended/Virtual Reality(XR/VR) or holoportation in mobile scenarios. Multi-access Edge Computing (MEC) brings services “closer” to user consumption with evident advantages yet at the cost of maintaining a zero downtime guarantee when user handovers (HOs) are prevalent due to the decentralisation of services towards the network edge. In this work, we design and evaluate intelligent HO prediction models between radio 5G Base Stations. The motivation for timely user HO prediction lies in being a vital presupposition for path steering and other MANO control actions in contemporary programmable 5G networks to deliver a zero downtime perception during HO events. Our detailed simulation and actual testbed evaluation results show that effective HO prediction can be achieved using a combination of Long Short-Term Memory (LSTM) or gradient boost regression with classification models, with the latter filtering out any Reference Signal Received Power (RSRP) prediction input outliers for predicting the serving cell.

The study of Service Function Chains (SFCs) placement problem is crucial to support services flexibly and use resources efficiently. Solutions should satisfy various Quality of Service requirements, avoid edge resource congestion, and improve service acceptance ratio (SAR). This work presents a novel approach to address these challenges by solving amulti-objective SFCs placementproblem based on the Pointer Network in multi-layer edge and cloud networks. We design a Deep Reinforcement Learning algorithm, calledChebyshev-assisted Actor-Critic SFCs Placement Algorithm, to overcome the limitations of traditional heuristic and evolutionary algorithms. Then, we run this algorithm iteratively with a set of weights to obtain non-dominated fronts, which have much higher hypervolume values than those obtained from other state-of-the-art algorithms. Moreover, running our algorithm individually with selected weights from non-dominated fronts can avoid edge resource congestion and achieve 98% SARs of low-latency services during high-workload periods. Finally, based on both simulation and real testbed experimental results, it is validated that the proposed algorithm fits for pragmatic service deployment while achieving 100% of SARs in the use cases deployed on the testbed.

Currently, telecommunication research communities are striving towards the adoption of Zero-touch network and Service Management (ZSM) in Network Function Virtualisation (NFV) orchestration. Contemporary efforts on adopting Machine Learning (ML) and Artificial Intelligence (AI) have caused an upsurge of ZSM application in the VNF space. While ML and AI complement the ZSM goals for building the intelligent NFV orchestration, a deep knowledge about the resource consumption by Network Services (NSs) and its constituent Virtual Network Functions (VNFs) is required, which would enable AI and ML models to manage the available resources better and enhance user experience. In this article, we propose a Novel Autonomous Profiling (NAP) method that not only predicts the optimum network load a VNF can support but also estimates the required resources in terms of CPU, Memory, and Network, to meet the performance targets and workload by utilising ML techniques. Our performance evaluation results on real datasets show that the output of NAP can be used in the next generation of NFV orchestration.

5G networks generate massive (quasi-) real-time data streams that different network apps can exploit to implement sophisticated single- or cross-domain control and management logic. This paper presents ElasticSDK, a Software Development Kit specially designed to abstract the development and chaining of such agile 5G monitoring apps for the control, management, and coordination of the underlying 5G network heterogeneous modules. Custom apps can collect, incrementally process and further expose flows in a flexible Pub/Sub fashion via appropriate SDK API calls, thus sharing both raw and complex data flows among themselves. Furthermore, the design of ElasticSDK allows respecting typical 5G data ownership and privacy models, as desired by the different 5G stakeholders ranging from physical infrastructure providers up to service providers over slicing. Finally, we provide two important contributions to the 5G open-source research community: (i) a RAN monitoring prototype implementation over the ElasticSearch and FlexRAN platforms that allows to demonstrate ElasticSDK app development and capturing hierarchical control features of typical SDN-enabled 5G architectures, and (ii) a first-ever publicly available dataset of realistic 5G RAN monitoring traces.

In this article, we present the design and implementation of the software-defined IoT management (SDIM) framework based on software-defined networking (SDN)-enabled architecture that is purposely built for the edge computing multidomain wireless sensor networks (WSNs). This framework can dynamically provision the IoT devices to enable machine-to-machine (M2M) communication as well as continuous operational fault detection for WSNs. Unlike the existing approaches in the literature, SDIM is mainly deployed at multiaccess edge computing (MEC) nodes and is integrated with the cloud by aggregating multidomain topology information. Backed by the experimental results over the University of Bristol 5G test network, we demonstrate in practice that our framework outperforms the implementations of the lightweight M2M (LWM2M) and NETCONF Light IoT device management protocols when deployed autonomously at the network edge and/or the cloud. Specifically, SDIM edge deployments can lower the average device provisioning time as high as 46% compared to LWM2M and 60.3% compared to NETCONF Light. Moreover, it can decrease the average operational fault detection time by approximately 33% compared to LWM2M and roughly 40% compared to NETCONF Light. Also, SDIM reduces control operations time up to 27%, posing a powerful feature for use cases with time-critical control requirements. Last, SDIM manages to both reduce CPU consumption and to have important energy consumption gains at the network edge, which can reach as high as 20% during device provisioning and 4.5%-4.9% during fault detection compared to the benchmark framework deployments.

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.

RAN slicing is one of the key enabler to enable virtualization of a BS and its delivery as a service with different levels of network isolation and sharing so as to accommodate the needs of mobile network operators and verticals. In this demonstration, we show a prototype of a RAN slicing runtime system to enable flexible slice customization on the top of a disaggregated RAN infrastructure [1] with different levels of isolation and sharing in terms of resources and network functions, while retaining the quality of service (QoS) for different slice instances. Furthermore, a novel plug & play network application chaining framework empowered by a network software development kit (SDK) is demonstrated to show how the multi-service programmability on per-slice basis can be achieved. Our demonstration is based on the OpenAirlnterface [3], Mosaic-5G FlexRAN [4] and LL-MEC [2] platforms. Finally, we highlight how the the proposed approach can be extended to an end-to-end network slicing scenario.

We present our recent work investigating how mobility prediction can be exploited for improving the performance of mobile users in two directions: proactive caching requested content close to the network attachment points where a mobile has a high probability to connect to and DASH (Dynamic Adaptive Streaming over HTTP) video quality adaptation. For proactive caching we discuss a new model to proactively cache content based on both mobility prediction and content popularity. An important feature of the model is that it dynamically adapts caching decisions to the relative importance of the two factors. For DASH adaptation we discuss a procedure that exploits mobility and throughput prediction to select the quality levels of video segments requested by a DASH player in order to achieve improved QoE, in terms of both high video quality and few video quality switches.

Name resolution is at the heart of Information-Centric Networking (ICN), where names are used to both identify information and/or services, and to guide routing and forwarding inside the network. The ICN focus on information, rather than hosts, raises significant concerns regarding the scalability of the required Name Resolution System (NRS), especially when considering global scale, inter-domain deployments. In the route-by-name approach to NRS construction, name resolution and the corresponding state follow the routing infrastructure of the underlying inter-domain network. The scalability of the resulting NRS is therefore strongly related to the topological and routing characteristics of the network. However, past work has largely neglected this aspect. In this paper, we present a detailed investigation and comparison of the scalability properties of two route-by-name inter-domain NRS designs, namely, DONA and CURLING. Based on both real, full-scale inter-domain topology traces and synthetic, scaled-down topologies, our work quantifies a series of important scalability-related performance aspects, including the distribution of name-resolution state across the Internet topology and the associated processing and signaling overheads. We show that by avoiding DONA's exchange of state across peering links, CURLING results in deployment costs proportional to the total number of downstream customers of each Autonomous System. This translates to a 62-fold global state size reduction, at the expense of a 2.78-fold increase in lookup processing load, making CURLING a feasible approach to ICN name resolution.

The current paper presents extensions to a distributed user mobility-based proactive caching scheme that supports individual users' requests, and a brief discussion of the benefits from exploiting user-centric features. The approach applies to Heterogeneous Wireless Networks (HWNs) for offloading traffic volumes to small cells and for reducing delay for specific categories of mobile users and mobile application scenarios through Efficient Proactive Caching (EPC) decisions at small cells. The approach is designed to support mobile users' requests for content not treated by popularity-based caching. Here, we discuss how proactive caching decisions can jointly utilize individual user mobility and data popularity to enhance the benefits of cache decisions for individuals to a broader set of mobiles requesting the same data.

We present a distributed proactive caching approach that exploits user mobility information to decide where to proactively cache data to support seamless mobility, while efficiently utilizing cache storage using a congestion pricing scheme. The proposed approach is applicable to the case where objects have different sizes and to a two-level cache hierarchy, for both of which the proactive caching problem is hard. Our evaluation results show how various system parameters influence the delay gains of the proposed approach, which achieves robust and good performance relative to an oracle and an optimal scheme for a flat cache structure.

Information-Centric Networking (ICN) is constantly gaining momentum within the Future Internet research community. In the PURSUIT research project we are developing a clean-slate Pub/Sub Internetworking (PSI or Ψ) approach with integrated seamless mobility support. The novel ICN mechanisms supported in Ψ, along with smartly placed in-network caches, enable the architecture to handle both mobile and fixed devices in a uniform way. This paper presents a blueprint for optimizing mobility support in Ψ without modifications to the architecture or add-on solutions. We demonstrate a micro-mobility scenario that describes the functionality of Ψ's core components in supporting mobility and then sketch our plans for future work and a proper assessment of these designs.

NA