Open Radio Access Network (RAN) enables flexible, AI-driven control of mobile networks through disaggregated, multi-vendor components. In this architecture, xApps handle real-time functions, whereas rApps in the non-real-time controller generate strategic policies. However, current rApp development remains largely manual, brittle, and poorly scalable as xApp diversity proliferates. In this work, we propose a multi-agent Agentic AI framework to automate rApp policy generation and orchestration. The architecture integrates three specialized large language model (LLM)-based agents, Perception, Reasoning, and Refinement, supported by retrieval-augmented generation (RAG) and memory-based analogical reasoning. These agents collectively analyze potential conflicts, synthesize intent-aligned control pipelines, and incrementally refine deployment decisions. Experiments across diverse deployment scenarios demonstrate that the proposed system achieves over 70% improvement in deployment accuracy and 95% reduction in reasoning cost compared to baseline methods, while maintaining zero-shot generalization to unseen intents. These results establish a scalable and conflict-aware solution for fully autonomous, zero-touch rApp orchestration in Open RAN.

Industry 5.0 envisions a cyber-physical future where humans and robots collaborate harmoniously, empowered by 6G connectivity and intelligent automation. Central to this vision is the ability to autonomously configure complex production pipelines based on diverse and evolving human intents. Existing orchestration technologies exhibit critical shortcomings in terms of self-learning, validation, error diagnosis, and rectification capabilities. To this end, we propose an Agentic AI orchestration framework that interprets human intents and dynamically assembles optimal technology pipelines using a self-improving, retrieval-augmented Large Language Model (LLM) and a Bayesian contextual-bandit selector. This enables dynamic adaptation in unpredictable factory environments. Our solution is validated in a cyber-physical testbed integrating Digital Twins (DTs), distributed AI, robotics, and real-world network infrastructure. Compared to baseline LLMs, our system reduces orchestration iterations by over 94% for a given intent and by around 90% for an unseen intent, showing rapid convergence and strong generalization. Real-world deployments mirror DT results, confirming both the fidelity of the simulation and the practical value of intent-driven orchestration for human-centric manufacturing.

The upcoming Sixth Generation (6G) of wireless networks builds on decades of advances and research in scientific areas such as Physics, Electronics & Communication, and Computational Systems. 6G will demand not only ultra-high throughput and low latency, but also scalable, privacy-preserving, and trustworthy coordination across distributed systems. Paradigms such as Fog/Edge Computing (FC/EC), Blockchain (BC), and Federated Learning (FL) each offer innovative solutions to different aspects of these requirements. The combined potential of these technologies, and how they can jointly impact 6G and its applications, are still open issues. Therefore, establishing a roadmap to understand their integration and synergy is needed. In this paper, we present a taxonomy-driven survey. We first analyze FC/EC, BC, and FL and their integration for 6G. Then, as our main contribution, we introduce a comprehensive taxonomy that categorizes seven integration levels (i.e., architecture features, functionalities, security and privacy mechanisms, data management strategies, energy efficiency mechanisms, applications and cross-cutting issues), and explore the effective integration of these paradigms by analyzing their unique characteristics, potential synergies, and opportunities to deliver 6G demands. Through this taxonomy, the study emphasizes transformative benefits such as enhanced data security, improved processing efficiency, and streamlined decentralized privacy-preserving mechanisms, which are actual needs of the in-developing 6G networks. Nonetheless, challenges such as scalability and performance issues and regulatory hurdles are also noted. The work also identifies key areas for future research, and current challenges, promoting exploration into the promising potential of combined FC/EC, BC, and FL solutions for 6G.

Distributed quantum computing (DQC) has emerged as a promising approach to overcome the scalability limitations of monolithic quantum processors in terms of computational capability. However, realising the full potential of DQC requires effective resource management and circuit scheduling. This involves efficiently assigning each circuit to a subset of quantum processing units (QPUs), based on factors such as their computational power and connectivity. In heterogeneous DQC networks with arbitrary connectivity topologies and non-identical QPUs, this becomes a complex challenge. This paper addresses resource management and circuit scheduling in such settings, with a focus on computing resource allocation in a quantum data centre. We propose circuit scheduling algorithms based on Mixed-Integer Linear Programming (MILP). Our MILP model accounts for errors arising from inter-QPU communication. In particular, the proposed schemes consider key factors, including network topology, QPU capacities, and quantum circuit structure, to make efficient scheduling and allocation decisions. Simulation results demonstrate that our proposed algorithms significantly improve circuit execution time and scheduling efficiency (measured by makespan and throughput), while also reducing inter-QPU communication overhead, compared to baseline strategies. This work provides valuable insights into resource management strategies for scalable and heterogeneous DQC systems.

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.

This paper addresses the challenge of robust cellular connectivity in dense, underdeveloped urban environments, specifically focusing on Kathmandu, Nepal. As cities grow, existing cellular infrastructure struggles to meet the demand for reliable, high-throughput, and low-latency communication services. The lack of investment in new technologies and the intricacies of the cities' landscape pose even more difficulties for robust connectivity. This work addresses the above challenges in a cost-effective and flexible way. We investigate the deployment of LTE Nomadic Nodes (NNs) at scale in order to enhance network capacity and coverage. Utilising a Digital Twin (DT), we simulate and optimise NN placement, considering Kathmandu's physical and environmental characteristics. Our approach leverages the DRIVE DT framework, which enables the systemic evaluation of various network configurations and user mobility scenarios. The results demonstrate that NNs significantly improve signal strength and expected user datarates, presenting a viable solution for enhancings urban cellular connectivity.

The integration of Artificial Intelligence (AI) within 6G networks is poised to revolutionize connectivity, reliability, and intelligent decision-making. However, the performance of AI models in these networks is crucial, as any decline can significantly impact network efficiency and the services it supports. Understanding the root causes of performance degradation is essential for maintaining optimal network functionality. In this paper, we propose a novel approach to reason about AI model performance degradation in 6G networks using the Large Language Models (LLMs) empowered Chain-of-Thought (CoT) method. Our approach employs an LLM as a “teacher” model through zero-shot prompting to generate teaching CoT rationales, followed by a CoT “student” model that is fine-tuned by the generated teaching data for learning to reason about performance declines. The efficacy of this model is evaluated in a real-world scenario involving a real-time 3D rendering task with multi-Access Technologies (mATs) including WiFi, 5G, and LiFi for data transmission. Experimental results show that our approach achieves over 97 % reasoning accuracy on the built test questions, confirming the validity of our collected dataset and the effectiveness of the LLM-CoT method. Our findings highlight the potential of LLMs in enhancing the reliability and efficiency of 6G networks, representing a significant advancement in the evolution of AI-native network infrastructures.

Unmanned aerial vehicle base station (UAV-BS) communication networks are considered as a promising solution for temporarily recovering urban telecommunication services interrupted by natural disasters. However, the deployment of UAV-BSs remains a challenge in disaster scenarios where terrestrial base stations may be unavailable, and users' locations (mobility in 3D, both on the ground and in the building) and requirements are constantly changing over time. In this paper, we propose a new digital twin (DT) framework to dynamically optimize UAV-BSs deployment in terms of both quantity and location while ensuring guaranteed network quality of service (QoS) and satisfied user requirements. It leverages a graph neural network (GNN) with new random walk for network modeling, a convolutional neural network (CNN) with online learning for QoS prediction, and deep reinforcement learning (DRL) models for optimizing UAV-BSs quantity and location. These three computing paradigms work collaboratively to respond to the evolving disaster context in an adaptive manner, improving UAV-BSs deployment subject to dynamic user requirements and mobility. Simulation results confirm the DT framework's effectiveness in optimizing UAV-BSs deployment in disaster scenarios.

Network slicing (NS) is a promising solution for media services, such as live streaming in telecom networks. NS enables customised network conditions for different applications and requirements. This customisation granularity is further enhanced through the use of 5G Quality of Service (QoS) flows for intra-slice management. Given the fact that network slices are becoming more dedicated to specific services' quality requirements, it becomes important to find service-aware NS methods that guarantee service quality while minimising resource consumption. To this end, this paper presents a Maximum Likelihood-based Network Slicing (MaxLiNS) method that minimises resource consumption with guaranteed Quality of Experience (QoE) for live low-latency streaming service under playback buffer level estimation and control. We evaluated the MaxLiNS method against existing service-agnostic and emerging service-aware NS methods on our End-to-End (E2E) 5G testbed. The results show that the MaxLiNS outperforms existing NS methods in terms of quality guarantee and resource consumption minimisation.

The disaggregated architecture of advanced Radio Access Networks (RANs) with diverse X-haul latencies, in conjunction with resource-limited multi-access edge computing networks, presents significant challenges in designing a general model in placing baseband and user plane functions to accommodate versatile 5G services. This paper proposes a novel approach, NetMind+, which leverages Deep Reinforcement Learning (DRL) to determine the function placement strategies in diverse and evolving RAN topologies, aiming at minimizing power consumption. NetMind+ resolves the problem with a maze-solving strategy, enabling a Markov Decision Process with standardized action space scales across different networks. Additionally, a Graph Convolutional Network (GCN) based encoding and an incremental learning mechanism are introduced, allowing features from different and dynamic networks to be aggregated into a single DRL agent. This facilitates the generalization capability of DRL and minimizes the negative retraining impact. In an example with three sub-networks, NetMind+ demonstrates a substantial 32.76% improvement in power savings and a 41.67% increase in service stability compared to benchmarks from the existing literature. Compared to traditional methods necessitating a dedicated DRL agent for each network, NetMind+ attains comparable performance with 70% of the training cost savings. Furthermore, it demonstrates robust adaptability during network variations, accelerating training speed by 50%.

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.

The increasing concerns of knowledge transfer and data privacy challenge the traditional gather-and-analyse paradigm in networks. Specifically, the intelligent orchestration of Virtual Network Functions (VNFs) requires understanding and profiling the resource consumption. However, profiling all kinds of VNFs is time-consuming. It is important to consider transferring the well-profiled VNF knowledge to other lack-profiled VNF types while keeping data private. To this end, this paper proposes a Federated Transfer Component Analysis (FTCA) method between the source and target VNFs. FTCA first trains Generative Adversarial Networks (GANs) based on the source VNF profiling data, and the trained GANs model is sent to the target VNF domain. Then, FTCA realizes federated domain adaptation by using the generated source VNF data and less target VNF profiling data, while keeping the raw data locally. The proposed FTCA enables efficient profiling knowledge transfer among different VNFs, while maintaining data privacy. Through FTCA, faster new VNF deployment can be expected. Experiments show that the proposed FTCA can effectively predict the required resources for the target VNF. Specifically, the RMSE index of the regression model decreases by 38.5% and the R-squared metric advances up to 68.6%.

The adoption of Artificial Intelligence (AI) based Virtual Network Functions (VNFs) has witnessed significant growth, posing a critical challenge in orchestrating AI models within next-generation 6G networks. Finding optimal AI model placement is significantly more challenging than placing traditional software-based VNFs, due to the introduction of numerous uncertain factors by AI models, such as varying computing resource consumption, dynamic storage requirements, and changing model performance. To address the AI model placement problem under uncertainties, this paper presents a novel approach employing a sequence-to-sequence (S2S) neural network which considers uncertainty estimations. The S2S model, characterized by its encoding-decoding architecture, is designed to take the service chain with a number of AI models as input and produce the corresponding placement of each AI model. To address the introduced uncertainties, our methodology incorporates the orthonormal certificate module for uncertainty estimation and utilizes fuzzy logic for uncertainty representation, thereby enhancing the capabilities of the S2S model. Experiments demonstrate that the proposed method achieves competitive results across diverse AI model profiles, network environments, and service chain requests.

The dis aggregated and hierarchical architecture of advanced RAN presents significant challenges in efficiently placing baseband functions and user plane functions in conjunction with Multi-Access Edge Computing (MEC) to accommodate diverse 5G services. Therefore, this paper proposes a novel approach NetMind, which leverages Deep Reinforcement Learning (DRL) to determine the function placement strategies in RANs with diverse topologies, aiming at minimizing power consumption. NetMind formulates the function placement problem as a maze-solving task, enabling a Markov Decision Process with standardized action space scales across different networks. Additionally, a Graph Convolutional Network (GCN) based encoding mechanism is introduced, allowing features from different networks to be aggregated into a single RL agent. That facilitates the RL agent's generalization capability and minimizes the negative impact of retraining on power consumption. In an example with three sub-networks, NetMind achieves comparable performance to traditional methods that require a dedicated DRL agent for each network, resulting in a 70 % reduction in training costs. Furthermore, it demonstrates a substantial 32.76% improvement in power savings and a 41.67 % increase in service stability compared to benchmarks from the existing literature.

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.

Integrating mobile networks with Non-3GPP networks provides a promising solution to mitigate the wireless RF spectrum scarcity. Despite the maturity of integration technologies, a comprehensive approach for radio resource allocation in highly dynamic and complex multiple Radio Access Technologies (multi-RAT) networks is still lacking. To tackle this challenge, this paper proposes an Access Traffic Management (ATM) system that enhances radio resource allocation during access, transmission, and handover processes. The system features a scalable and concise ATM-supported multi-RAT network architecture, supported by a Deep Deterministic Policy Gradient (DDPG) based Intelligent ATM (IATM) algorithm. To evaluate the proposed system, a Network Simulator 3 (NS3) based network simulation is built with realistic 5G and WiFi modules, interacting with the IATM algorithm in real time for decision making and policy improvement. Numerical improvements of our solution demonstrate its superiority over conventional steering modes. Our solution achieves an increase in resource utilization efficiency by 45% and 70% compared to the Active-Standby and Load-Balance steering modes, respectively. Moreover, it enhances link quality by a factor of three and doubles throughput without incurring any additional costs. Additionally, our solution significantly enhances session stability under conditions involving network size dynamics and UE mobility.

Under horizontal federated learning (HFL) in the Internet of Things (IoT) scenarios, different user data sets have significant similarities on the feature spaces, the final goal is to build a high-performance global model. However, not all features are great contributors when training the global HFL model, some features even impair the HFL. Besides, the curse of dimension will delay the training time and cause more energy consumption (EC). In this case, it is critical to remove irrelevant features from the local and select the useful overlapping features from a federated global perspective. In addition, the uncertainty of data being labeled and the nonindependent and identically distributed (non-IID) client data should also consider. This article introduces an unsupervised federated feature selection approach (named FSHFL) for HFL in IoT networks. First, a feature relevance outlier detection method is applied to the HFL participants to remove the useless features, which combines with the improved one-class support vector machine. Besides, a feature relevance hierarchical clustering (FRHC) algorithm is proposed for HFL overlapping feature selection. Experiment results on four IoT data sets show that the proposed methods can select better-federated feature sets among HFL participants, thus improving the performance of the HFL system. Specifically, the global model accuracy improves up to 1.68% since fewer irrelevant features. Moreover, FSHFL can lower the average training time as high as 6.9%. Finally, when the global model gets the same test accuracy, FSHFL can decrease the average EC of training the model by approximately 2.85% compared to federated average and roughly 68.39% compared to Fed-SGD.

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.

Multi-access edge computing (MEC) has been regarded as one of the essential technologies for mobile networks, by providing computing resources and services close to users, thereby, avoiding extra energy consumption and fitting the low-latency ultra-reliable requirements for emerging 5G applications. Task offloading policy plays a pivotal role in handling offloading requests and maximizing the network computing performance. Most recently developed offloading solutions are designed for instant rewards, therefore, neglecting the long-term computing resource optimization at the edge, which fail to deliver optimized network performance when a significant increase of computing requests appears. In this paper, with the objective of maximizing long-term offloading benefits on delay and energy consumption, task offloading policies are proposed to firstly avoid resource over-distribution through deep reinforcement learning (DRL) based resource reservation and server cooperation, and secondly maximize the average instant reward and the utilization of reserved resources by an optimization-based joint policy consisting of offloading decision, transmission power allocation and resource distribution. The DRL-based joint policy is evaluated in a simulated multi-server edge computing network. Compared to previous solutions, the DRL-based algorithms achieve higher and more reliable overall rewards. Of the implemented three DRL-based algorithms, fully cooperative multi-agent DRL accounts for cooperation between servers, achieving a 70.5% reduction in reward variance and a 13.4% increase in average rewards over 500 continuous operations. Resource balanced policies on long-term rewards help edge networks handle the explosive growth of 5G computing-intensive applications in the future.

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.

In this paper, we present a zero-touch network orchestrator to autonomously provide an end-to-end orchestration platform to orchestrate, monitor, and profile network services. Subsequently, we describe a new method to autonomously generate performance profiles of these network services and compute optimum resources required to meet the given KPIs and performance targets.

Summary form only given, as follows. The complete presentation was not made available for publication as part of the conference proceedings. This talk will make the case for Human-Centric-Networking as a key direction for Future Network evolution. Human-centricity will drive a revolution in the design of Future Networks, which will augment the importance of communication networks as social infrastructure in order to respond and play a pivotal role in addressing key social challenges concerning work, education, inclusion, equality, and react to emergencies such as pandemics. Hyper-connectivity and human-centricity will enable persistent personalized access to digital services and resources, both virtual and physical, without constraints of time and location. To enact such research we will need to rely on an inter-disciplinary end-to-end design methodology, embedding technological and social practices into the design of future network infrastructure and services. In addition to societal considerations, I will also address the commercial drivers for evolving from today’s device-centric to future human-centric-networks. Finally, I will discuss the need for new technological breakthroughs to enable human-centricity in the Next Generation Internet and 6G infrastructures.

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.

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.

To meet the challenge of flexible and dynamic resource provisioning for massive and various network services, we investigate the network function virtualization-resource allocation problem in the 5G network. For the first time, this problem is modelled as the congestion game to capture the effects of resource congestion on packet processing latency, optical-to-electronic and electronic-to-optical conversion latency. All the network service requests received at the same time are players trying to minimise their own end-to-end latency and resource consumption cost. A distributed online algorithm is designed and simulation results show that it can achieve 100% service acceptance ratio while the baseline algorithm cannot. If lower weighted resource consumption cost is set for 1ms and 5ms services, more such services will be routed to edge nodes and network operators will earn more. An experiment for network services with different packet sizes is carried out, and results prove that the proposed algorithm converges to Nash Equilibrium in 40 seconds and the latency requirements are all satisfied if the packet size is small.

To support ultra-low latency 5G services flexibly and use limited resources in Multi-access Edge Computing (MEC) servers efficiently, the study of latency-aware optimal hierarchical resource allocation for Service Function Chains in 5G becomes essential. In this regard, we address this resource allocation problem, for the first time, by designing a Mixed Integer Linear Programming (MILP) model based on a hierarchical 5G network interconnecting multiple MEC nodes. The objective is to minimize the total latency from five sources: processing, queueing, transmission, propagation, and optical-electronic-optical conversion. Experimental results prove that ultra-low latency requirements can be guaranteed and maximum usage of MEC node resources can be obtained. Then, a data rate-based heuristic algorithm is proposed, which can get ≤1.5 approximation ratio under different workload scenarios and achieve at least 1.7 times as much service acceptance ratio as the baseline approach.

Rate or link adaptation is the determination of the optimal modulation and coding scheme (MCS) that will maximize the performance under the current wireless channel conditions. A Software-Defined Networking (SDN) agent is a software element bridging an SDN controller and any legacy wireless network elements by providing the abstraction of these elements. In this paper, we present the work of an SDN approach for designing and implementing a Rate/Link Adaptation (RA) framework for wireless local area networks (WLAN). The framework provides support for real-time RA applications and flexibility to satisfy various degrees of Quality of Service (QoS) or Quality of Experience (QoE) requirements. We implement the proposed framework as an extension to the Wireless Open-Access Research Platform (WARP), an FPGA based Software-Defined Radio (SDR) platform, with evaluation results indicating the feasibility of using SDN-RA under the stringent time constraints posed by the WLAN. To demonstrate the effectiveness of decoupling rate decision functions from the underlying wireless interface card and to highlight its applicability for a diverse set of scenarios, we present a use case deployed over the framework focusing on rate adaptation for individual traffic, and display optimization in different aspects, such as the reduction transmission errors.

The present study focuses on the development of a dynamically re-configurable Information Communication Technology (ICT) infrastructure to support the sustainable development of railway network. Once data have been collected, the extracted knowledge is used to develop a set of applications that can improve the energy efficient operation of railway systems. A typical example includes the identification of the optimal driving profiles in terms of energy consumption. In the present study, this is achieved through the adoption of an optimization framework based on Data Envelopment Analysis (DEA). The performance of the proposed scheme is evaluated based on actual data collected at an operation tramway system. Preliminary results illustrate that when the proposed method is applied, a 10% reduction in the overall power consumption can be achieved.

Recently, a lot of research is focused on applying Software-Defined Networking (SDN) concepts on wireless networks. However, the current wireless systems are lack of SDN support and remain closed and (mostly) proprietary, which makes it difficult to integrate with SDN systems. The SDN agent is introduced to solve the above issues. An SDN agent is a software element bridging the SDN controller and any legacy wireless network elements (NEs) by providing the abstraction of these elements. The main advantage of this approach is that there is no modification to either the existing SDN elements or the 802.11 protocols, while the SDN controller is enabled to control and manage legacy wireless NEs. In this paper, we present an SDN agent framework for WLANs and describe an implementation of the proposed agent on the Wireless Open-Access Research Platform (WARP), an FPGA based open source Software-Defined Radio (SDR) platform. With the support from such an agent, innovative applications and functionalities can be developed for the WLAN access points (APs), such as dynamically slicing AP bandwidth among users and adapting the transmit power in flexible granularity, i.e. at per frame/per flow level.

Data analytics and scientific computing are two modern applications that in recent years have substantially changed their computation and communication needs, requiring additional processing capability and bandwidth to be able to keep pace with current demands. These applications are commonly processed within data centers, exchanging enormous volumes of data, rapidly stressing existing network infrastructures. Thus, it is crucial for data center operations and management to be able to understand and classify the communication demands of these applications. The traditional approaches for classifying application traffic are port-based and Deep Packet Inspection, both presenting issues with current network technology. Some recent works propose using machine learning plus statistical information collected from application flows to classify traffic. Applications running in data centers present communication patterns which can be recognized through their traffic matrices. So, the main contribution of this paper is a method that explores the textural information extracted from these matrices to classify the data center traffic using machine learning techniques. As a proof-of-concept, we implemented this method in a system named DCTraCS. The experimental dataset was gathered from two real data centers, collecting the traffic matrices of MapReduce and a set of scientific applications every second for a period of 30 minutes. For assessing our proposal, we compared it with other machine learning techniques for classifying application traffic found in current literature. Results show that our approach achieved the highest accuracy, classifying correctly over 99% of our data center applications.

Datacenter (DC) design has been moved toward the edge computing paradigm motivated by the need of bringing cloud resources closer to end users. However, the software defined networking (SDN) architecture offers no clue to the design of micro DCs (MDCs) for meeting complex and stringent requirements from next generation 5G networks. This is because canonical SDN lacks a clear distinction between functional network parts, such as core and edge elements. Besides, there is no decoupling between the routing and the network policy. In this paper, we introduce residue defined networking architecture (RDNA) as a new approach for enabling key features like ultra-reliable and low-latency communication in MDC networks. RDNA explores the programmability of residues number system as a fundamental concept to define a minimalist forwarding model for core nodes. Instead of forwarding packets based on classical table lookup operations, core nodes are tableless switches that forward packets using merely remainder of the division (modulo) operations. By solving a residue congruence system representing a network topology, we found out the algorithms and their mathematical properties to design RDNA's routing system that: 1) supports unicast and multicast communication; 2) provides resilient routes with protection for the entire route; and 3) is scalable for 2-tier Clos topologies. Experimental implementations on Mininet and NetFPGA SUME show that RDNA achieves 600 ns switching latency per hop with virtually no jitter at core nodes and sub-millisecond failure recovery time.

Edge Data Centres (EDC) are often managed by a single administrative entity with logically centralized control. The architectural split of control and data planes and the new control plane abstractions have been touted as Software-Defined Networking (SDN), where the OpenFlow protocol is one common choice for the standardized programmatic interface to data plane devices. However, in the design of an SDN architecture, there is no clear distinction between functional network parts such as core and edge elements. It means that all switches require to support lookups over hundreds of bits with complex actions that have to be specified by multiple tables. In this paper, we propose a new programmable architecture for EDC networks, named Residues Defined Networks (RDN). In RDN, a controller defines a network policy (e.g. connectivity protection) setting flow entries at the edges. Based on these entries, the edge switches assign routeIDs to flows. A route is defined as the remainder of the division (Residue) between a route-ID and a set of switch-IDs within RDN core. In case of failures, emergency routes are compactly encoded as programmable residues forwarding paths written into the packets. RDN scalability is evaluated considering 2-tier Clos topologies which cover mostly EDC deployments supporting up to 2304 servers. A RDN proof-of-concept prototype is implemented in Mininet for network emulation. Also, to increase the accuracy on latency measures, we implement RDN in NetFPGA that is validated in a testbed with 10Gbps Ethernet boards. RDN offers ultra-fast failure recovery (sub-milliseconds carrier grade), achieves low latency with RDN switching time per hop (≈0.6μs) and no jitter within the RDN core.

Scientific applications demand huge computational power connected through fast networks. They are developed using parallel kernel methods, usually implemented with the Message Passing Interface (MPI), presenting well-behaved communication patterns across computing nodes. The current network technologies do not allow defining traffic forwarding policies considering the different application traffic, resulting in an unbalanced load on the network links. Moreover, the devices are not concerned if the traffic is latency-sensitive or bandwidth-intensive. To handle this, we present NetSA, a framework exploiting the communication patterns of scientific applications, considering latency and bandwidth constraints, as the key logic for evenly placing the application flows on the network available paths. Through NetSA, the scientific application developer can easily modify the network behavior to best fit the application communication requirements. We have performed experiments for optimizing the MPI communication primitives and applied our solution to speed up scientific applications, obtaining an execution time reduction up to 27%.

Disaggregation of IT resources has been proposed as an alternative configuration for data centres. Comparing to the monolithic server approach that data centres are being built now, in a disaggregated data centre, CPU, memory and storage are separate resource blades and they are interconnected via a network fabric. That brings greater flexibility and improvements to the future data centres in terms of utilization efficiency and energy consumption. The key enabler for the disaggregated data centre is the network, which should support the bandwidth and latency requirements of the communication that is currently inside the server. In addition, a management software is required to create the logical connection of the resources needed by an application. In this paper, we propose a disaggregated data centre network architecture, we present the first scheduling algorithm specifically designed for disaggregated computing and we demonstrate the benefits that disaggregation will bring to operators.

This paper proposes a linear formulation and an iterative heuristic, both with traffic grooming capability, which can maximize the number of remaining available routes and minimize the number of transceivers in Elastic Optical Networks (EON). The aim of the proposal is to preserve the open capacity for the accommodation of future unknown demands. Case studies are carried out in order to analyze the basic properties of the formulation in a small network, and the heuristic is used for moderate larger networks. The results suggest that it is feasible to preserve enough open capacity to avoid blocking of future requests in EON with scarce resources.

This paper focuses on the design of cloud service provisioning schemes over converged optical network and computing infrastructures. A major issue linked with the operation of these infrastructures is their sustainability in terms of energy consumption and CO2emissions. Given that most of the power consumption of the converged infrastructures is attributed to the operation of computing resources, the concept of powering-up computing resources with renewable energy sources is becoming a promising solution. However, the time variability and uncertainty of cloud services as well as the stochastic nature of renewable energy sources makes the evaluation and exploitation of such systems challenging. To address this challenge, we propose a novel service provisioning scheme based on stochastic linear programming (SLP). To cope with the increasing computational complexity inherent in SLP formulations, dimensionality reduction techniques, such as the sample average approximation and Lagrangian relaxation, are adopted. Based on measurements from the National Solar Radiation Data Base, traffic statistics from the Internet2 measurement archive, and experimentations with real network configurations, it is proven that the proposed scheme is stable and achieves fast convergence to the optimal solution, while at the same time reduces the overall CO2emissions by up to 60% for different levels of demand requests. The performance of the proposed provisioning scheme is compared with traditional approaches.

Generally, data center's applications have different Quality of Service (QoS) requirements. Meanwhile, data center's tenants may give different priorities to performance and cost. Therefore, it is unsuitable to treat applications/tenants equally. In this paper, we adopt Dynamic Pricing (DP) to charge for the usage of bandwidth and provide tenants with capability to automatically response to the dynamic price. Further, for applications with tight delay requirements, we propose Dynamic Pricing with Bandwidth Reservation (DPBR), which can reserve bandwidth for specific applications. With the modelling of user satisfaction of cost and performance, we show that tenants with DP and DPBR can get better trade-offs between performance and cost. Comparing with Flat Pricing (FP), which is a representative of today's on-demand purchase option, we demonstrate that DPBR is a better option for tenants since it can maximize their satisfactions. The validity is demonstrated through numerical studies and simulations.

Software defined networking (SDN) and OpenFlow as the outcome of recent research and development efforts provided unprecedented access into the forwarding plane of networking elements. This is achieved by decoupling the network control out of the forwarding devices. This separation paves the way for a more flexible and innovative networking. While SDN concept and OpenFlow find their ways into commercial deployments, performance evaluation of the SDN concept and its scalability, delay bounds, buffer sizing and similar performance metrics are not investigated in recent researches. In spite of usage of benchmark tools (like OFlops and Cbench), simulation studies and very few analytical models, there is a lack of analytical models to express the boundary condition of SDN deployment. In this work we present a model based on network calculus theory to describe the functionality of an SDN switch and controller. To the best of our knowledge, this is for the first time that network calculus framework is utilized to model the behavior of an SDN switch in terms of delay and queue length boundaries and the analysis of the buffer length of SDN controller and SDN switch. The presented model can be used for network designers and architects to get a quick view of the overall SDN network deployment performance and buffer sizing of SDN switches and controllers.

Cloud computing is a new model of consuming and delivering IT and infrastructure resources. It enables users to obtain what they need, as they need it, from advanced applications to IT infrastructure and platform services, including virtual infrastructure, servers and storage. It can provide significant economies of scale and greater business agility, while accelerating the pace of innovation. Network virtualization, as a key enabling technology in resource provisioning for cloud, has attracted extensive attention from both academia and industry. It takes cloud services to the next level by delivering optimised resources, on-demand utilisation, flexibility and scalability. This paper proposes a novel architectural solution for future cloud service providers based on the concept of Infrastructure as a Service (IaaS) framework and IP network virtualization. A number of associated schemes have also been designed as building blocks for the proposed framework, including resource description and abstraction mechanisms, virtual network request method and a resource broker mechanism named Marketplace. The proposed framework is able to respond quickly to the infrastructure needs for those cloud services with dynamic resizing of the infrastructure by aggregation or partition to meet capacity requirements of services. At the same time, it improves the utilisation of providers' resources with the creation of an infrastructure incorporating the heterogeneous resources in the data centre. In addition, the proposed marketplace, which also allows the trading of IP network resources between infrastructure providers and cloud service providers, is an important and complementary innovation within the cloud landscape.

The future Internet evolution is driven by applications that require simultaneous real-time access to multiple heterogeneous IT resources interconnected by high-speed optical networks. In this paper, we propose a novel service-oriented resource orchestration model based on the optimization of heterogeneous IT and network resources owned by different Infrastructure Providers (InPs). The proposed model aims to achieve a global optimum from both the end-users' and InPs' point of view across different administrative domains. An integer linear program (ILP) is formulated to obtain optimal results that maximizes the number of accepted requests while minimizing resource usage. It is compared against a co-scheduling ILP model, whose objective is to maximize the number of accepted requests only. Finally, we propose a heuristic solution for scalability. Its performance is compared against (i) our proposed ILP (ii) a co-scheduling heuristic that aim to maximize number of accepted requests only and (iii) an algorithm that does not take into account cross-domain optimizations.

This paper focuses on next generation ubiquitous networks supporting the Future Internet. In this context, it proposes an architecture and an integration framework of wireless and wired network technologies supporting a variety of services with differing service requirements. More specifically the i

This paper presents a programmable multi-granular optical cross connect (MG-OXC) and network architecture deployable in multi-service and multi-provider networks. The concept of programmable MG-OXC is introduced to provide a way of utilizing multiple switching/transport granularities to efficiently

Ultra high performance digital media applications are now creating the need for new network architectures instead of shared IP links to provide them with dedicated, on-demand high capacity. These demands will be more critical in the future, as applications employing a real time environment become more common. Dynamic optical services at lambda and sub-lambda granularities are proposed because they guarantee the appropriate QoS in terms of bandwidth, jitter and latency. The technologies presented in this paper are merely initial considerations for use when providing the network services under investigation. Initial studies have shown that there is a lot of interest, and there are many advantages, in setting up network services to distribute high-performance media streams via optical networks to one or more locations.

This paper presents a novel solution for realization of service oriented optical networking. The solution is based on advanced optical burst switched network scenario utilizing novel service oriented optical burst switched core and edge router technologies. We demonstrate service-aware bandwidth reservation in a multi-granular OBS test-bed. We also demonstrate non-network services and data layer connections over OBS control plane by extending the JIT OBS protocol.

Grid-GMPLS (G2MPLS) is conceived as a powerful network control plane solution that enhances the standard ASON/GMPLS architecture providing single-step resource reservation, co-allocation and maintenance of both network and Grid resources. This paper identifies and discusses the main issues and considerations that arise by network research and educational networks and network operators in order to facilitate the dissemination of G2MPLS control plane. Interoperability issues and backwards compatibility with existing network control planes centre the scope of this study, which intends to demonstrate the feasibility of adopting the proposed architectures.

This paper presents a novel application-aware network architecture for evolving and emerging IT services and applications. It proposes and analyses network architectures that integrate Session Initiation Protocol (SIP) with Optical Burst Switched (OBS) protocols on a unified manner. We suggest various SIP-OBS layering architectures for possible deployment as well as a number of end-to-end resource discovery protocols (both for network and non-network resources). Finally the paper reports of a SIP-enpowered OBS Testbed where this approach was experimentally validated.

This paper presents hybrid optical router architectures (both edge and core) to support user-defined bandwidth reservations for emerging and evolving applications over wavelength channels (circuit), optical bursts or even optical packets. The edge router is based on the deployment of application-aware IP packet classification and burst/packet aggregation algorithms as well as agile and intelligent optical resource allocation. The mechanism is responsible for per application switching (OCS/OBS/OPS) service selection and Differentiated Service (DiffServ) provisioning. The optical core router can support all the abovementioned switching technologies. Both are generic and able to support any type of current or future application.

This paper presents a novel hybrid optical burst/circuit switched (OBCS) ingress edge router solution towards ubiquitous photonic Grid networking. It is based on the deployment of Grid application-aware packet classification and burst aggregation algorithms as well as agile and intelligent optical resource allocation. The proposed solution utilises a generic and highly scalable multi-dimension classification mechanism able to provide wire-speed classification at high bit rates up to 40 Gbps. The mechanism is responsible for per application switching (OBS/OCS) service selection and Grid Differentiated Service (GridDiffServ) provisioning. A CoS-Traffic-Time-LEngth-Service-oriented aSembly (COST2LESS) algorithm has been proposed to smooth the incoming Grid traffic and provide some CoS differentiation and initial results are presented. An agile optical data transmission mechanism has been also implemented to map Grid traffic asynchronously into optical bursts or wavelength channels (data plane) based on user/application-specific requirements. Furthermore an optical burst Ethernet switched (OBES) transport mechanism has been implemented to transport out-of- band control plane signalling information.

End-to-end on-demand scheduling of optical network resources for high-end grid applications has been studied by many national and international R&D organizations and research projects. Many new questions have arisen addressing technical, organizational and policy based issues.To address these challenges involved in building a global research network infrastructure, a strategic alliance between two international organizations has been formed; The Grid High-Performance Networking research group (GHPN) in GGF, mostly focusing in defining applications network requirements and network services; and GLIF, working towards enabling a globally interconnected lambda test-bed.Organized by the two organizations, the aims of this session are: (1) to increase community awareness and engagement to this common GHPN/GGF and GLIF research agenda; (2) to announce a new effort in collecting, reporting and analyzing experience concerning delivery of network services across heterogeneous optical domains. This effort will accelerate R&D problem solving in delivering lambda services in a global scale and will contribute towards standards regarding APIs and network interfaces among multiple network and Grid layers.

This paper presents a novel solution towards ubiquitous photonic grid networking. It is based on the deployment of long-reached and high-bandwidth optical infrastructure while taking advantage of recent developments in optical networking technologies such as optical burst switching. The proposed solution utilises optical burst switching and active router technologies. It aims to provide a physical infrastructure able to fulfil grid application requirements and make efficient use of network resources.

This work presents a novel solution towards a long-reach intelligent infrastructure for Grid networking. The proposed solution is based on the deployment of high capacity optical infrastructure whilst taking advantage of recent developments in optical networking technologies. Optical burst switching and a user network interface utilizing fast tunable optical technologies provide a physical infrastructure able to fulfill the Grid application requirements and make efficient use of network resources. Furthermore a control and management plane based on extensions of existing artifacts offers peer-to-peer distributed networking to enable Grid services.