Cellular-enabled collaborative robots are becoming paramount in Search-and-Rescue (SAR) and emergency response. Crucially dependent on resilient mobile network connectivity, they serve as invaluable assets for tasks like rapid victim localization and the exploration of hazardous, otherwise unreachable areas. However, their reliance on battery power and the need for persistent, low-latency communication limit operational time and mobility. To address this, and considering the evolving capabilities of 5G/6G networks, we propose a novel SAR framework that includes Mission Planning and Mission Execution phases and that optimizes robot deployment. By considering parameters such as the exploration area size, terrain elevation, robot fleet size, communication-influenced energy profiles, desired exploration rate, and target response time, our framework determines the minimum number of robots required and their optimal paths to ensure effective coverage and timely data backhaul over mobile networks. Our results demonstrate the trade-offs between number of robots, explored area, and response time for wheeled and quadruped robots. Further, we quantify the impact of terrain elevation data on mission time and energy consumption, showing the benefits of incorporating real-world environmental factors that might also affect mobile signal propagation and connectivity into SAR planning. This framework provides critical insights for leveraging next-generation mobile networks to enhance autonomous SAR operations.

The vision of intelligent networks capable of automatically configuring crucial parameters for tasks such as resource provisioning, anomaly detection or load balancing largely hinges upon efficient AI-based algorithms. Time series forecasting is a fundamental building block for network-oriented AI and current trends lean towards the systematic adoption of models based on deep learning approaches. In this paper, we pave the way for a different strategy for the design of predictors for mobile network environments, and we propose the Thresholded Exponential Smoothing (TES) framework, a hybrid Statistical Modeling and Deep Learning tool that allows for improving the performance of network Key Performance Indicator (KPI) forecasting. We adapt our framework to two state-of-the-art deep learning tools for time series forecasting, based on Recurrent Neural Networks and Transformer architectures. We experiment with TES by showcasing its superior support for three practical network management use cases, i.e. (i) anticipatory allocation of network resources, (ii) mobile traffic anomaly prediction, and (iii) mobile traffic load balancing. Our results, derived from traffic measurements collected in operational mobile networks, demonstrate that the TES framework can yield substantial performance gains over current state-of-the-art predictors in the applications considered.

Reconfigurable Intelligent Surfaces (RIS) enable dynamic electromagnetic control for 6G networks, but existing control schemes lack responsiveness to fast-varying network conditions, limiting their applicability for ultra-reliable low latency communications. This work address uplink delay minimization in multi-RIS scenarios with heterogeneous per-user latency and reliability demands. We propose Delay-Aware RIS Orchestrator (DARIO), an O-RAN-compliant framework that dynamically assigns RIS devices to users within short time windows, adapting to traffic fluctuations to meet per-user delay and reliability targets. DARIO relies on a novel Stochastic Network Calculus (SNC) model to analytically estimate the delay bound for each possible user–RIS assignment under specific traffic and service dynamics. These estimations are used by DARIO to formulate a Nonlinear Integer Program (NIP), for which an online heuristic provides near-optimal performance with low computational overhead. Extensive evaluations with simulations and real traffic traces show consistent delay reductions up to 95.7% under high load or RIS availability.

Smart factories enhance production efficiency and sustainability, but emergencies like human errors, machinery failures and natural disasters pose significant risks. In critical situations, such as fires or earthquakes, collaborative robots can assist first-responders by entering damaged buildings and locating missing persons, mitigating potential losses. Unlike previous solutions that overlook the critical aspect of energy management, in this paper we propose REACT, a smart energy-aware orchestrator that optimizes the exploration phase, ensuring prolonged operational time and effective area coverage. Our solution leverages a fleet of collaborative robots equipped with advanced sensors and communication capabilities to explore and navigate unknown indoor environments, such as smart factories affected by fires or earthquakes, with high density of obstacles. By leveraging real-time data exchange and cooperative algorithms, the robots dynamically adjust their paths, minimize redundant movements and reduce energy consumption. Extensive simulations confirm that our approach significantly improves the efficiency and reliability of search and rescue missions in complex indoor environments, improving the exploration rate by 10% over existing methods and reaching a map coverage of 97% under time critical operations, up to nearly 100% under relaxed time constraint.

With the rapid development of 5G technology and the increasing demand for autonomous mobile robots, there is a trend to leverage the ultra-low latency, high data rates, and reliable wireless connectivity offered by 5G to improve the perception and navigation of robots in unknown environments. This paper presents a novel approach for creating and exploiting radio-aware semantic maps to empower 5G-enabled mobile robots operating within an unknown environment. The proposed solution allows for smart offloading of robotic applications and task processing onto the edge systems while facilitating real-time data exchange, and enables robots to gather environment data from both onboard sensors and the mobile network for more efficient robot operation and resource orchestration decisions. A radio-aware semantic mapping framework is introduced, which combines radio signal quality information with semantic mapping techniques to create a comprehensive understanding of the environment, which may evolve over time. The semantic map, enriched with radio quality measurement data, enables mobile robots to make timely informed decisions by considering real-time radio quality variations. Our experimental evaluation demonstrates the effectiveness of adopting radio semantic maps to enhance real-time robot operations on navigation and task offloading in unstructured environments.

Reconfigurable Intelligent Surfaces (RIS) are a promising technology for creating smart radio environments by controlling wireless propagation. However, several factors hinder the integration of RIS technology into existing cellular networks, including the incompatibility of RIS control interfaces with 5G PHY/MAC procedures for synchronizing radio scheduling decisions and RIS operation, and the cost and energy limitations of passive RIS technology. This paper presents RISENSE, a system for practical RIS integration in cellular networks. First, we propose a novel, low-cost, and low-power RIS design capable of decoding control messages without complex baseband operations or additional RF chains, utilizing a power sensor and a network of microstrip lines and couplers. Second, we design an effective in-band wireless RIS control interface, compatible with 5G PHY/MAC procedures, that embeds amplitude-modulated (AM) RIS control commands directly into standard OFDM-modulated 5G data channels. Finally, we propose a low-overhead protocol that supports swift on-demand RIS re-configurability, making it adaptable to varying channel conditions and user mobility, while minimizing the wastage of 5G OFDM symbols. Our experiments validate the design of RISENSE and our evaluation shows that our system can re-configure a RIS at the same pace as users move, boosting 5G coverage where static or slow RIS controllers cannot.

This keynote presents a bold, transformative vision for the future of mobile connected systems based on Agentic AI. We will delve into our research on leveraging Small and Large Language Models (SLMs and LLMs) to create a new generation of intelligent, autonomous mobile networks. As a foundational proof-of-concept, we will introduce "TelecomRAG," a novel framework using Retrieval-Augmented Generation that enables LLMs to understand and reason over complex telecommunication standards with high precision and verifiability. Building on this, the talk will explore how to unlock the disruptive potential of Agentic AI to fundamentally reshape the design, deployment, and evolution of future connected systems.

The increasing miniaturization of Unmanned Aerial Vehicles (UAVs) has expanded their deployment potential to indoor and hard-to-reach areas. However, this trend introduces distinct challenges, particularly in terms of flight dynamics and power consumption, which limit the UAVs’ autonomy and mission capabilities. This paper presents a novel approach to overcoming these limitations by integrating Neural 3D Reconstruction (N3DR) with small UAV systems for fine-grained 3-Dimensional (3D) digital reconstruction of small static objects. Specifically, we design, implement, and evaluate an N3DR-based pipeline that leverages advanced models, i.e., Instant-ngp, Nerfacto, and Splatfacto, to improve the quality of 3D reconstructions using images of the object captured by a fleet of small UAVs. We assess the performance of the considered models using various imagery and pointcloud metrics, comparing them against the baseline Structure from Motion (SfM) algorithm. The experimental results demonstrate that the N3DR-enhanced pipeline significantly improves reconstruction quality, making it feasible for small UAVs to support high-precision 3D mapping and anomaly detection in constrained environments. In more general terms, our results highlight the potential of N3DR in advancing the capabilities of miniaturized UAV systems.

Localization of in-body devices is beneficial for Gastrointestinal (GI) diagnosis and targeted treatment. Traditional methods such as imaging and endoscopy are invasive and limited in resolution, highlighting the need for innovative alternatives. This study presents an experimental framework for Radio Frequency (RF)-backscatter-based in-body localization, inspired by the ReMix approach, and evaluates its performance in real-world conditions. The experimental setup includes an in-body backscatter device and various off-body antenna configurations to investigate harmonic generation and reception in air, chicken and pork tissues. The results indicate that optimal backscatter device positioning, antenna selection, and gain settings significantly impact performance, with denser biological tissues leading to greater attenuation. The study also highlights challenges such as external interference and plastic enclosures affecting propagation. The findings emphasize the importance of interference mitigation and refined propagation models to enhance performance.

In the era of Industry 4.0, precise indoor localization is vital for automation and efficiency in smart factories. Reconfigurable Intelligent Surfaces (RIS) are emerging as key enablers in 6G networks for joint sensing and communication. However, RIS faces significant challenges in Non-Line-of-Sight (NLOS) and multipath propagation, particularly in localization scenarios, where detecting NLOS conditions is crucial for ensuring not only reliable results and increased connectivity but also smart factory personnel's safety. This study introduces an AI-assisted framework employing a Convolutional Neural Network (CNN) customized for accurate Line-of-Sight (LOS) and NLOS classification to enhance RIS-based localization using measured, synthetic, mixedmeasured, and mixed-synthetic experimental data, that is, original, augmented, slightly noisy, and highly noisy data, respectively. Validated through such data from three different environments, the proposed customized-CNN (cCNN) model achieves$\mathbf{9 5. 0 \% - 9 9. 0 \%}$accuracy, outperforming standard pre-trained models like Visual Geometry Group 16 (VGG-16) with an accuracy of$\mathbf{8 5. 5 \% - 8 8. 0 \%}$. By addressing RIS limitations in NLOS scenarios, this framework offers scalable and highprecision localization solutions for 6G-enabled smart factories.

Rapid and accurate localization of individuals during search-and-rescue (SAR) missions is essential for reducing casualties in emergencies. Traditional methods often struggle in disaster scenarios, where obstacles like debris or dense foliage hinder performance, and reliance on user-side actions proves impractical for mission-critical operations. This paper presents a novel approach that leverages a 5G-new radio (NR)-based unmanned aerial vehicle (UAV) localization framework, integrating hybrid techniques with adaptive clustering strategies to localize user equipments (UEs). Unlike traditional methods, our system dynamically adjusts its trajectory to balance latency and accuracy, achieving UEs positioning accuracy within tens of centimeters during simulation tests. By integrating 5G-NR technology into UAV-based localization, our approach provides a robust and scalable solution for mission-critical SAR operations, significantly enhancing the latency and reliability of locating individuals in emergency situations.

The maturity and commercial roll-out of 5 G networks and its deployment for private networks makes 5G a key enabler for various vertical industries and applications, including robotics. Providing ultra-low latency, high data rates, and ubiquitous coverage and wireless connectivity, 5G fully unlocks the potential of robot autonomy and boosts emerging robotic applications, particularly in the domain of autonomous mobile robots. Ensuring seamless, efficient, and reliable navigation and operation of robots within a 5 G network requires a clear understanding of the expected network quality in the deployment environment. However, obtaining real-time insights into network conditions, particularly in highly dynamic environments, presents a significant and practical challenge. In this paper, we present a novel framework for building a Network Digital Twin (NDT) using real-time data collected by robots. This framework provides a comprehensive solution for monitoring, controlling, and optimizing robotic operations in dynamic network environments. We develop a pipeline integrating robotic data into the NDT, demonstrating its evolution with real-world robotic traces. We evaluate its performances in radio-aware navigation use case, highlighting its potential to enhance energy efficiency and reliability for 5Genabled robotic operations.

The Open Radio Access Network (O-RAN)-compliant solutions often lack crucial details for implementing effective control loops at various time scales. To overcome this, we introduce MAREA, an O-RAN-compliant mathematical framework designed for the allocation of radio resources to multiple ultra-Reliable Low Latency Communication (uRLLC) services. In the near-real-time (RT) control loop, MAREA employs a novel Martingales-based model to determine the guaranteed radio resources for each uRLLC service. Unlike traditional queueing theory approaches, this model ensures that the probability of packet transmission delays exceeding a predefined threshold—the violation probability—remains below a target tolerance. Additionally, MAREA uses a real-time control loop to monitor transmission queues and dynamically adjust guaranteed radio resources in response to traffic anomalies. To the best of our knowledge, MAREA is the first O-RAN-compliant solution that leverages Martingales for both near-RT and RT control loops. Simulations demonstrate that MAREA significantly outperforms reference solutions, achieving an average violation probability that is$\times 10$lower.

This paper presents a theoretical and mathematical framework for the design of a conformal reconfigurable intelligent surface (RIS) that adapts to non-planar geometries, which is a critical advancement for the deployment of RIS on non-planar and irregular surfaces as envisioned in smart radio environments. Previous research focused mainly on the optimization of RISs assuming a predetermined shape, while neglecting the intricate interplay between shape optimization, phase optimization, and mutual coupling effects. Our contribution, the Tailored 3D RIS (T3DRIS) framework, addresses this fundamental problem by integrating the configuration and shape optimization of RISs into a unified model and design framework, thus facilitating the application of RIS technology to a wider spectrum of environmental objects. The mathematical core of T3DRIS is rooted in optimizing the 3D deployment of the unit cells and tuning circuits, aiming at maximizing the communication performance. Through rigorous full-wave simulations and a comprehensive set of numerical analyses, we validate the proposed approach and demonstrate its superior performance and applicability over contemporary designs. This study—the first of its kind—paves the way for a new direction in RIS research, emphasizing the importance of a theoretical and mathematical perspective in tackling the challenges of conformal RISs.

The integration of Smart Surfaces in 6G communication networks, also dubbed as Reconfigurable Intelligent Surfaces (RISs), is a promising paradigm change gaining significant attention given its disruptive features. RISs are a key enabler in the realm of 6G Integrated Sensing and Communication (ISAC) systems where novel services can be offered together with the future mobile networks communication capabilities. This paper addresses the critical challenge of precisely localizing users within a communication network by leveraging the controlled-reflective properties of RIS elements without relying on more power-hungry traditional methods, e.g., GPS, adverting the need of deploying additional infrastructure and even avoiding interfering with communication efforts. Moreover, we go one step beyond: we build COLoRIS, anOpportunistic ISACapproach that leverages localization-agnostic RIS configurations to accurately position mobile users via trained learning models. Extensive experimental validation and simulations in large-scale synthetic scenarios show$\mathbf{5\%}$positioning errors (with respect to field size) under different conditions. Further, we show that a low-complexity version running in a limited off-the-shelf (embedded, low-power) system achieves positioning errors in the$\mathbf{11\%}$range at a negligible$\mathbf{+2.7\%}$energy expense with respect to the classical RIS.

The virtualization of Radio Access Networks (vRAN) is rapidly becoming a reality, driven by the increasing need for flexible, scalable, and cost-effective mobile network solutions. To mitigate energy efficiency concerns in vRAN deployments, two approaches are gaining attention: ($i$) sharing computing infrastructure among multiple virtualized base stations (vBSs); and ($ii$) relying upon general-purpose, low-cost CPUs. However, effectively realizing these approaches poses several challenges. In this paper, we first conduct a comprehensive experimental campaign on a vRAN platform to characterize the impact of computing and radio resource allocation on energy consumption and performance across various network contexts. This analysis reveals several key issues. First, determining the optimal allocation of computing resources is difficult because it depends on the context of each vBS (e.g., traffic load, channel quality) in a non-trivial and non-linear manner. Second, suboptimal resource assignment can lead to increased energy consumption or, even worse, degradation of users' Quality of Service. Third, the high dimensionality of the solution space hinders the effectiveness of traditional optimization or learning methods. To tackle these challenges, we propose AegisRAN, a framework for optimizing computing resource allocation in vRAN. AegisRAN addresses the dual objective of minimizing energy consumption while maintaining high system reliability. Moreover, when computing resources are overbooked, our solution ensures a fair resource partition based on vBS performance. AegisRAN leverages a discrete soft actor-critic algorithm combined with several techniques, including multi-step decision-making, action masking, digital twin-based training, and a tailored reward signal that mitigates feedback sparsity. Our evaluations demonstrate that AegisRAN achieves near-optimal performance and offers high flexibility across diverse network contexts and varying numbers of vBSs, with up to 25% improvement in energy savings compared to baseline solutions in medium-scale scenarios.

In the past few years, network infrastructures have transitioned from prominently hardware-based models to networks of functions, where software components provide the required functionalities with unprecedented scalability and flexibility. However, this new vision entails a completely new set of problems related to resource provisioning and the network function operation, making it difficult to manage the network function lifecycle management with traditional, human-in-the-loop approaches. Novel zero-touch management solutions promise autonomous network operation with limited human interactions. However, modeling network function behavior into compelling variables and algorithm is an aspect that such solutions must take into account. In this paper, we propose AZTEC+, a data-driven solution for anticipatory resource provisioning in network slicing scenarios. By leveraging a hybrid and modular deep learning architecture, AZTEC+ not only forecasts the future demands for target services but also identifies the best trade-offs to balance the costs due to the instantiation and reconfiguration of such resources. Our experimental evaluation, based on real-world network data, shows how AZTEC+ can outperform state-of-the-art management solutions for a large set of metrics.

5G mobile networks introduce a new dimension for connecting and operating mobile robots in outdoor environments, leveraging cloud-native and offloading features of 5G networks to enable fully flexible and collaborative cloud robot operations. However, the limited battery life of robots remains a significant obstacle to their effective adoption in real-world exploration scenarios. This paper explores, via field experiments, the potential energy-saving gains of OROS, a joint orchestration of 5G and Robot Operating System (ROS) that coordinates multiple 5G-connected robots both in terms of navigation and sensing, as well as optimizes their cloud-native service resource utilization while minimizing total resource and energy consumption on the robots based on real-time feedback. We designed, implemented and evaluated our proposed OROS in an experimental testbed composed of commercial off-the-shelf robots and a local 5G infrastructure deployed on a campus. The experimental results demonstrated that OROS significantly outperforms state-of-the-art approaches in terms of energy savings by offloading demanding computational tasks to the 5G edge infrastructure and dynamic energy management of on-board sensors (e.g., switching them off when they are not needed). This strategy achieves approximately ~15% energy savings on the robots, thereby extending battery life, which in turn allows for longer operating times and better resource utilization.

Autonomous reconfigurable intelligent surfaces (RISs) offer the potential to simplify deployment by reducing the need for real-time remote control between a base station (BS) and an RIS. However, we highlight two major challenges posed by autonomy. The first is implementation complexity, as autonomy requires hybrid RISs (HRISs) equipped with additional onboard hardware to monitor the propagation environment and perform local channel estimation (CHEST), a process known as probing. The second challenge, termed probe distortion, reflects a form of the observer effect: during probing, an HRIS can inadvertently alter the propagation environment, potentially disrupting the operations of other communicating devices sharing the environment. Although implementation complexity has been extensively studied, probe distortion remains largely unexplored. To further assess the potential of autonomous RISs, this paper comprehensively and pragmatically studies the fundamental trade-offs posed by these challenges collectively. In particular, we examine the robustness of an HRIS-assisted massive multiple-input multipleoutput (mMIMO) system by considering its critical components and stringent conditions. The latter include: 1) two extremes of implementation complexity, represented by minimalist operation designs of two distinct HRIS hardware architectures, and 2) an oblivious BS that fully embraces probe distortion. To make our analysis possible, we propose a physical-layer orchestration framework that aligns HRIS and mMIMO operations. We present empirical evidence that autonomous RISs remain promising under stringent conditions and outline research directions to deepen probe distortion understanding.

The advance towards 6G networks comes with the promise of unprecedented performance in sensing and communication capabilities. The feat of achieving those, while satisfying the ever-growing demands placed on wireless networks, promises revolutionary advancements in sensing and communication technologies. As 6G aims to cater to the growing demands of wireless network users, the implementation of intelligent and efficient solutions becomes essential. In particular, reconfigurable intelligent surfaces (RISs), also known as Smart Surfaces, are envisioned as a transformative technology for future 6G networks. The performance of RISs when used to augment existing devices is nevertheless largely affected by their precise location. Suboptimal deployments are also costly to correct, negating their low-cost benefits. This paper investigates the topic of optimal RISs diffusion, taking into account the improvement they provide both for the sensing and communication capabilities of the infrastructure while working with other antennas and sensors. We develop a combined metric that takes into account the properties and location of the individual devices to compute the performance of the entire infrastructure. We then use it as a foundation to build a reinforcement learning architecture that solves the RIS deployment problem. Since our metric measures the surface where given localization thresholds are achieved and the communication coverage of the area of interest, the novel framework we provide is able to seamlessly balance sensing and communication, showing its performance gain against reference solutions, where it achieves simultaneously almost the reference performance for communication and the reference performance for localization.

Recent advances in learning techniques have garnered attention for their applicability to a diverse range of real-world sequential decision-making problems. Yet, many practical applications have critical constraints for operation in real environments. Most learning solutions often neglect the risk of failing to meet these constraints, hindering their implementation in real-world contexts. In this paper, we propose a risk-aware decision-making framework for contextual bandit problems, accommodating constraints and continuous action spaces. Our approach employs an actor multi-critic architecture, with each critic characterizing the distribution of performance and constraint metrics. Our framework is designed to cater to various risk levels, effectively balancing constraint satisfaction against performance. To demonstrate the effectiveness of our approach, we first compare it against state-of-the-art baseline methods in a synthetic environment, highlighting the impact of intrinsic environmental noise across different risk configurations. Finally, we evaluate our framework in a real-world use case involving a 5G mobile network where only our approach satisfies consistently the system constraint (a signal processing reliability target) with a small performance toll (8.5% increase in power consumption).

The tremendous hype around autonomous driving is eagerly calling for emerging and novel technologies to support advanced mobility use cases. As car manufactures keep developing SAE level 3+ systems to improve the safety and comfort of passengers, traffic authorities need to establish new procedures to manage the transition from human-driven to fully-autonomous vehicles while providing a feedback-loop mechanism to fine-tune envisioned autonomous systems. Thus, a way to automatically profile autonomous vehicles and differentiate those from human-driven ones is a must.In this paper, we present a fully-fledged framework that monitors active vehicles using camera images and state information in order to determine whether vehicles are autonomous, without requiring any active notification from the vehicles themselves. Essentially, it builds on the cooperation among vehicles, which share their data acquired on the road feeding a machine learning model to identify autonomous cars. We extensively tested our solution and created the NexusStreet dataset, by means of the CARLA simulator, employing an autonomous driving control agent and a steering wheel maneuvered by licensed drivers. Experiments show it is possible to discriminate the two behaviors by analyzing video clips with an accuracy of ~ 80%, which improves up to ~ 93% when the target’s state information is available. Lastly, we deliberately degraded the state to observe how the framework performs under non-ideal data collection conditions.

Mission-critical operations, particularly in the context of Search-and-Rescue (SAR) and emergency response situations, demand optimal performance and efficiency from every component involved to maximize the success probability of such operations. In these settings, cellular-enabled collaborative robotic systems have emerged as invaluable assets, assisting first responders in several tasks, ranging from victim localization to hazardous area exploration. However, a critical limitation in the deployment of cellular-enabled collaborative robots in SAR missions is their energy budget, primarily supplied by batteries, which directly impacts their task execution and mobility. This paper tackles this problem, and proposes a search-and-rescue framework for cellular-enabled collaborative robots use cases that, taking as input the area size to be explored, the robots fleet size, their energy profile, exploration rate required and target response time, finds the minimum number of robots able to meet the SAR mission goals and the path they should follow to explore the area. Our results, i) show that first responders can rely on a SAR cellular-enabled robotics framework when planning mission-critical operations to take informed decisions with limited resources, and, ii) illustrate the number of robots versus explored area and response time trade-off depending on the type of robot: wheeled vs quadruped.

The Open Radio Access Network (O-RAN)-compliant solutions lack crucial details to perform effective control loops at multiple time scales. In this vein, we propose ORANUS, an O-RAN-compliant mathematical framework to allocate radio resources to multiple ultra Reliable Low Latency Communication (uRLLC) services. In the near-RT control loop, ORANUS relies on a novel Stochastic Network Calculus (SNC)-based model to compute the amount of guaranteed radio resources for each uRLLC service. Unlike traditional approaches as queueing theory, the SNC-based model allows ORANUS to ensure the probability the packet transmission delay exceeds a budget, i.e., the violation probability, is below a target tolerance. ORANUS also utilizes an RT control loop to monitor service transmission queues, dynamically adjusting the guaranteed radio resources based on detected traffic anomalies. To the best of our knowledge, ORANUS is the first O-RAN-compliant solution which benefits from SNC to carry out near-RT and RT control loops. Simulation results show that ORANUS significantly improves over reference solutions, with an average violation probability 10× lower.

Radio Access Network (RAN) virtualization, key for new-generation mobile networks, requires Hardware Accelerators (HAs) that swiftly process wireless signals from Base Stations (BSs) to meet stringent reliability targets. However, HAs are expensive and energy-hungry, which increases costs and has serious environmental implications. To address this problem, we gather data from our experimental platform and compare the performance and energy consumption of a HA (NVIDIA GPU V100) vs. a CPU (Intel Xeon Gold 6240R, 16 cores) for energy-friendly software processing. Based on the insights obtained from this data, we devise a strategy to offload workloads to HAs opportunistically to save energy while preserving reliability. This offloading strategy, however, needs to be configured in near-real-time for every BS sharing common computational resources. This renders a challenging multi-agent collaborative problem in which the number of involved agents (BSs) can be arbitrarily large and can change over time. Thus, we propose an efficient multi-agent contextual bandit algorithm called ECORAN1, which applies concepts from mean field theory to be fully scalable. Using a real platform and traces from a production mobile network, we show that ECORAN can provide up to 40% energy savings with respect to the approach used today by the industry.

RAN virtualization is revolutionizing the telco industry, enabling 5G Distributed Units to run using general-purpose platforms equipped with Hardware Accelerators (HAs). Recently, GPUs have been proposed as HAs, hinging on their unique capability to execute 5G PHY operations efficiently while also processing Machine Learning (ML) workloads. While this ambivalence makes GPUs attractive for cost-effective deployments, we experimentally demonstrate that multiplexing 5G and ML workloads in GPUs is in fact challenging, and that using conventional GPU-sharing methods can severely disrupt 5G operations. We then introduce YinYangRAN, an innovative O-RAN-compliant solution that supervises GPU-based HAs so as to ensure reliability in the 5G processing pipeline while maximizing the throughput of concurrent ML services. YinYangRAN performs GPU resource allocation decisions via a computationally-efficient approximate dynamic programming technique, which is informed by a neural network trained on real-world measurements. Using workloads collected in real RANs, we demonstrate that YinYangRAN can achieve over 50% higher 5G processing reliability than conventional GPU sharing models with minimal impact on co-located ML workloads. To our knowledge, this is the first work identifying and addressing the complex problem of HA management in emerging GPU-accelerated vRANs, and represents a promising step towards multiplexing PHY and ML workloads in mobile networks.

Open and virtualized Radio Access Networks (vRANs) are breeding a new market with unprecedented opportunities. However, carrier-grade vRANs today are expensive and energy-hungry, as they rely on hardware accelerators (HAs) that are dedicated to individual distributed units (DUs). In this paper, we argue that sharing pools of heterogeneous processors among DUs leads to more cost- and energy-efficient vRANs. We then design CloudRIC, a system that, powered by lightweight data-driven models, meets specific reliability targets while (i) coordinating access between DUs and heterogeneous computing infrastructure; and (ii) assisting DUs with compute-aware radio scheduling procedures. Experiments on a GPU-accelerated O-Cloud show that CloudRIC can achieve, respectively, 3x and 15x mean gains in energy- and cost-efficiency under real RAN workloads while ensuring 99.999% reliability even in dense scenarios.

Open and virtualized Radio Access Networks (vRANs) are breeding a new market with unprecedented opportunities. However, carrier-grade vRANs today are expensive and energy-hungry, as they rely on hardware accelerators (HAs) that are dedicated to individual distributed units (DUs). We demonstrate CloudRIC [17], a system that, powered by lightweight data-driven models, meets specific reliability targets while (i) coordinating access between DUs and heterogeneous computing infrastructure; and (ii) assisting DUs with compute-aware radio scheduling procedures. Using a user-friendly dashboard to control an experimental testbed remotely, we demonstrate that CloudRIC achieves comparable reliability performance to a DU-dedicated platform while offering up to 40x higher cost-efficiency and up to 6x higher energy efficiency when pooling resources for up to 70 DUs.

Next-generation Virtual Reality (VR) technology enables full-user immersion and support for multiuser Virtual Experiences (VEs). Given the low-cost and passive nature of intelligent reflecting surfaces (IRSs), this paper investigates the optimal design of a multi-user IRS-assisted VR network, where an IRS is optimally deployed in a confined space as a function of VR fully-immersed users' trajectory. In particular, we consider sum-rate maximization of all VR users and optimize the Access Point's (AP) active beamforming, and the IRS's placement, phase shifts, and radiation patterns in a confined indoor environment operating in millimeter Wave (mmWave) frequencies. We introduce the Alternating Optimization (AO) algorithm, decompose the problem into distinct sub-problems, and solve each problem optimally. That is, maximum-ratio transmission (MRT) is applied for optimal beamforming at the AP, optimal closed-from IRS phase shifts are determined using quadratic transformation, global optimization is conducted to determine the ideal locations for the IRS elements, and the monotonic optimal radiation pattern has been analyzed. Our findings highlight that strategically allocating the IRS's resources at optimal physical locations enhances signal stability and maximizes per-user throughput.

Contemporary research advances in nanotechnology and material science are rooted in the emergence of nanodevices as a versatile tool that harmonizes sensing, computing, wireless communication, data storage, and energy harvesting. These devices hold promise in precision medicine, offering novel pathways for disease diagnostics, treatment, and monitoring within the bloodstreams. Ensuring precise localization of events of diagnostic interest, which underpins the concept of flow-guided in-body nanoscale localization, would intuitively provide an added diagnostic value to the detected events. Raw data generated by the nanodevices is pivotal for this localization and consist of an event detection indicator and the time elapsed since the last passage of a nanodevice through the heart. The communication and energy constraints of the nanodevices lead to intermittent operation and unreliable communication, intrinsically affecting this data. This posits a need for comprehensively modelling the features of this data. These imperfections also have profound implications for the viability of existing flow-guided localization approaches, which are ill-prepared to address the intricacies of the environment. Our first contribution lies in an analytical model of raw data for flow-guided localization, dissecting how communication and energy capabilities influence the nanodevices’ data output. This model acts as a vital bridge, reconciling idealized assumptions with practical challenges of flow-guided localization. Toward addressing these practical challenges, we also present an integration of Graph Neural Networks (GNNs) into the flow-guided localization paradigm. GNNs, reinforced by the adaptability and resilience of Heterogeneous Graph Transformers (HGTs), excel in capturing complex dynamic interactions inherent to the localization of events sensed by the nanodevices. Our results highlight the potential of GNNs not only to enhance localization accuracy but also extend coverage to encompass the entire bloodstream.

Radio Access Networks virtualization (vRAN) is on its way becoming a reality driven by the new requirements in mobile networks, such as scalability and cost reduction. Unfortunately, there is no free lunch but a high price to be paid in terms of computing overhead introduced by noisy neighbors problem when multiple virtualized base station instances share computing platforms. In this paper, first, we thoroughly dissect the multiple sources of computing overhead in a vRAN, quantifying their different contributions to the overall performance degradation. Second, we design an AI-driven Radio Intelligent Controller (AIRIC) to orchestrate vRAN computing resources. AIRIC relies upon a hybrid neural network architecture combining a relation network (RN) and a deep Q-Network (DQN) such that: ($i$) the demand of concurrent virtual base stations is satisfied considering the overhead posed by the noisy neighbors problem while the operating costs of the vRAN infrastructure is minimized; and ($ii$) dynamically changing contexts in terms of network demand, signal-to-noise ratio (SNR) and the number of base station instances are efficiently supported. Our results show that AIRIC performs very closely to an offline optimal oracle, attaining up to 30% resource savings, and substantially outperforms existing benchmarks in service guarantees.

Reconfigurable intelligent surfaces (RISs) are expected to play a crucial role in reaching the key performance indicators (KPIs) for future 6G networks. Their competitive edge over conventional technologies lies in their ability to control the wireless environment propagation properties at will, thus revolutionizing the traditional communication paradigm that perceives the communication channel as an uncontrollable black box. As RISs transition from research to market, practical deployment issues arise. Major roadblocks for commercially viable RISs are i) the need for a fast and complex control channel to adapt to the ever-changing wireless channel conditions, and ii) an extensive grid to supply power to each deployed RIS. In this paper, we question the established RIS practices and propose a novel RIS design combining self-configuration and energy self-sufficiency capabilities. We analyze the feasibility of devising fully-autonomous RISs that can be easily and seamlessly installed throughout the environment, following the new internet-of-surfaces (IoS) paradigm, requiring modifications neither to the deployed mobile network nor to the power distribution system. In particular, we introduce ARES, an Autonomous RIS with Energy harvesting and Self-configuration solution. ARES achieves outstanding communication performance while demonstrating the feasibility of energy harvesting (EH) for RISs power supply in future deployments.

Indoor positioning is a major challenge for location-based services. WiFi deployments are often used to address indoor positioning. Yet, they requiremultiple access points, which may not be available or accessible for localization in all scenarios, or they make unrealistic assumptions for practical deployments. In this paper we presentSPRING+, a positioning system that extracts and processes Channel State Information (CSI) and Fine Time Measurements (FTM) from a single Access Point (AP) to localize commercial smartphones. First, we propose an adaptive method for estimating the Angle of Arrival (AOA) from CSI that works on single packets and leverages information from the estimated number of paths. Second, we present a new method to detect the first path using FTM measurements, robust to multipath scenarios. We evaluate SPRING+ in an extensive experimental campaign consisting of four different testbeds: i) generic indoor spaces, ii) generic indoor spaces with obstacles, iii) office environments and iv) home environments. Our results show that SPRING+ is able to achieve a median 2D positioning error between 1 and 1.8 meters with asingle WiFi AP.

Auto-scaling techniques aim to keep the right number of active servers for the current load: if this number is too small we risk service disruption, but if it is too large we waste resources. Despite the interest in the efficient operation of this type of systems, no prior work has addressed auto-scaling techniques for Network Function Virtualization (NFV) with stringent reliability requirements such as those envisioned in 5G (5 or 6 nines). To achieve such levels of reliability, we need to account for both the activation delay until servers become available (i.e., the wake-up or activation time) and the fallible nature of servers (which may fail with some probability). In this article, we build on control theory to design an auto-scaling technique for a server farm for NFV that guarantees certain reliability while minimizing the number of active resources. We show that the use of well-established tools from control theory results in convergence times much shorter than those obtained with state-of-the-art reinforcement learning techniques. This shows that, despite the current trend to apply machine learning to all sorts of networking problems, there may be some cases where other techniques (such as control theory) can be more suitable.

As upcoming, beyond-5G (B5G) wireless network generations are expected to deliver much better performance than existing solutions, Reconfigurable intelligent surfaces (RISs) are gaining relevance as one of the new key technologies able to facilitate such improvement. Interestingly, they can redesign how the propagation environment is conceived by giving an opportunity to programmatically alter it: they can be configured to behave as orientable mirrors, scatterers, or lenses. This flexibility allows for the successful exploitation of bands which provide superior performance in wireless links but present poor propagation properties. However, this fascinating technology comes at not negligible costs: RISs require ad-hoc design, deployment and management operations to be fully exploited. In this paper, we tackle one of the open problems in the RISs literature: the optimal placement. We propose a model-based and a model-free approach, respectively RISA and AI-RISA, showcasing their large-scale solutions on synthetic topologies to improve communication performance while solving the “dead-zone” coverage problem. Additionally, our frameworks are empirically validated within a realistic indoor scenario, the Rennes railway station, showing how a complex indoor propagation environment can be fully disciplined by an advanced RISs installation.

Every year millions of lives are lost in emergency situations. Finding missing people in the shortest possible time is the most effective tool to reduce such a death toll. However, this is challenging when victims are unable to communicate by themselves, located in large areas and/or difficult to reach. In this paper we present 3DSAR, a single-drone 3D cellular search-and-rescue solution, leveraging on 5G-new radio (NR), able to estimate the location of people through their mobile phones. Our novel 3DSAR design consists of 4 main components to improve the localization accuracy of state-of-the-art drone-based cellular localization solutions: i) distance estimator, ii) angles estimator, iii) 3D positioning, and iv) 3D unnamed aerial vehicles (UAV) prediction trajectory algorithm. Our results show that 3DSAR improves by an order of magnitude the positioning error of current single-drone solutions thanks to its dynamic 3D trajectory control.

The advent of reconfigurable intelligent surfaces (RISs) brings along significant improvements for wireless technology on the verge of beyond-fifth-generation networks (B5G). The proven flexibility in influencing the propagation environment opens up the possibility of programmatically altering the wireless channel to the advantage of network designers, enabling the exploitation of higher-frequency bands for superior throughput overcoming the challenging electromagnetic (EM) propagation properties at these frequency bands. However, RISs are not magic bullets. Their employment comes with significant complexity, requiring ad-hoc deployments and management operations to come to fruition. In this paper, we tackle the open problem of bringing RISs to the field, focusing on areas with little or no coverage. In fact, we present a first-of-its-kind deep reinforcement learning (DRL) solution, dubbed as D-RISA, which trains a DRL agent and, in turn, obtains an optimal RIS deployment. We validate our framework in the indoor scenario of the Rennes railway station in France, assessing the performance of our algorithm against state-of-the-art (SOA) approaches. Our benchmarks showcase better coverage, i.e., 10-dB increase in minimum signal-to-noise ratio (SNR), at lower computational time (up to - 25 %) while improving scalability towards denser network deployments.

Reconfigurable Intelligent Surfaces (RISs) are expected to be massively deployed in future beyond-5th generation wireless networks, thanks to their ability to programmatically alter the propagation environment, inherent low-cost and low-maintenance nature. Indeed, they are envisioned to be implemented on the facades of buildings or on moving objects. However, such an innovative characteristic may potentially turn into an involuntary negative behavior that needs to be addressed: an undesired signal scattering. In particular, RIS elements may be prone to experience failures due to lack of proper maintenance or external environmental factors. While the resulting Signal-to-Noise-Ratio (SNR) at the intended User Equipment (UE) may not be significantly degraded, we demonstrate the potential risks in terms of unwanted spreading of the transmit signal to non-intended UEs. In this regard, we consider the problem of mitigating such undesired effectby proposing two simple yet effective algorithms, which are based on maximizing the Signal-to-Leakage-and-Noise-Ratio (SLNR) over a predefined two-dimensional (2D) area and are applicable in the case of perfect channel-state-information (CSI) and partial CSI, respectively. Numerical and full-wave simulations demonstrate the added gains compared to leakage-unaware and reference schemes.

Future robotics systems aiming for true autonomy must be robust against dynamic and unstructured environments. The 5th generation (5G) mobile network is expected to provide ubiquitous, reliable and low-latency wireless communications to ground robots, especially in outdoor scenarios. Empowered by 5G, the digital transformation of robotics is emerging, enabled by the cloud-native paradigm and the adoption of edge-computing principles for heavy computational task offloading. However, wireless link quality fluctuates due to multiple aspects such as the topography of the deployment area, the presence of obstacles, robots' movement and the configuration of the serving base stations. This directly impacts not only the connectivity to the robots but also the performance of robot operations, resulting in severe challenges when targeting full robot autonomy. To address such challenges, in this paper, we propose a framework to build a semantic map based on radio quality. By means of our proposed approach, mobile robots can gain knowledge on up-to-date radio context map information of the surrounding environment, hence enabling reliable and efficient robotics operations.

Recent advances in robotics and nanotechnology resulted in a set of miniaturized Unmanned Aerial Vehicles (UAVs). Such small UAVs are envisioned to operate in hard-to-reach areas for enabling applications such as structural monitoring or content capturing. Towards showcasing this vision, we demonstrate a small UAV-supported setup for real-time autonomous generation of 3-Dimensional (3D) representations of static objects. In the setup, a small UAV (i.e., CrazyFlie 2.1) is envisioned to visit a set of locations, acting as a carrier and power source of a camera sensor. At each location, the sensor is expected to take a picture of the object and report it to the station. The station implements a pipeline for 3D reconstruction based on the pictures taken by the UAV.

5G cellular systems are slowly being deployed worldwide delivering the promised unprecedented levels of throughput and latency to hundreds of millions of users. At such scale security is crucial, and consequently, the 5G standard includes a new series of features to improve the security of its predecessors (i.e., 3G and 4G). In this work, we evaluate the actual deployment in practice of the promised 5G security features by analysing current commercial 5G networks from several European operators. By collecting 5G signalling traffic in the wild in several cities in Spain, we i) fact-check which 5G security enhancements are actually implemented in current deployments, ii) provide a rich overview of the implementation status of each 5G security feature in a wide range of 5G commercial networks in Europe and compare it with previous results in China, iii) analyse the implications of optional features not being deployed, and iv) discuss on the still remaining 4G-inherited vulnerabilities. Our results show that in European 5G commercial networks, the deployment of the 5G security features is still on the works. This is well aligned with results previously reported from China [16] and keeps these networks vulnerable to some 4G attacks, during their migration period from 4G to 5G.

The roll-out phase of the next generation of mobile networks (5G) has started and operators are required to devise deployment solutions while pursuing localization accuracy maximization. Enabling location-based services is expected to be a unique selling point for service providers now able to deliver critical mobile services, e.g., autonomous driving, public safety, remote operations. In this paper, we propose a novel roll-out base station placement solution that, given a Throughput-Positioning Ratio (TPR) target, selects the location of new-generation base stations (among available candidate sites) such that the throughput and localization accuracy are jointly maximized. Moving away from the canonical position error bound (PEB) analysis, we develop a realistic framework in which each positioning measurement is affected by errors depending upon the actual wireless channel between the measuring base station and the target device. Our solution, referred to as LOKO, is a fast-converging algorithm that can be readily applied to current 5G (or future) roll-out processes. LOKO is validated by means of an exhaustive simulation campaign considering real existing deployments of a major European network operator as well as synthetic scenarios.

Virtualized base stations (vBS) can be implemented in diverse commodity platforms and are expected to bring unprecedented operational flexibility and cost efficiency to the next generation of cellular networks. However, their widespread adoption is hampered by their complex configuration options that affect in a non-traditional fashion both their performance and their power consumption requirements. Following an in-depth experimental analysis in a bespoke testbed, we characterize the vBS power cost profile and reveal previously unknown couplings between their various control knobs. Motivated by these findings, we develop a Bayesian learning framework for the orchestration of vBSs and design two novel algorithms: (i) BP-vRAN, which employs online learning to balance the vBS performance and energy consumption, and (ii) SBP-vRAN, which augments our optimization approach with safe controls that maximize performance while respecting hard power constraints. We show that our approaches are data-efficient, i.e., converge an order of magnitude faster than state-of-the-art Deep Reinforcement Learning methods, and achieve optimal performance. We demonstrate the efficacy of these solutions in an experimental prototype using real traffic traces.

The 5G mobile networks extend the capability for supporting collaborative robot operations in outdoor scenarios. However, the restricted battery life of robots still poses a major obstacle to their effective implementation and utilization in real scenarios. One of the most challenging situations is the execution of mission-critical tasks that require the use of various on-board sensors to perform simultaneous localization and mapping (SLAM) of unexplored environments. Given the time-sensitive nature of these tasks, completing them in the shortest possible time is of the highest importance. In this paper, we analyze the benefits of 5G-enabled collaborative robots by enhancing the intelligence of the robot operation through joint orchestration of Robot Operating System (ROS) and 5G resources for energy-saving goals, addressing the problem from both offline and online manners. We propose OROS, a novel orchestration approach that minimizes mission-critical task completion times as well as overall energy consumption of 5G-connected robots by jointly optimizing robotic navigation and sensing together with infrastructure resources. We validate our 5G-enabled collaborative framework by means of MATLAB/Simulink, ROS software and Gazebo simulator. Our results show an improvement between 3.65% and 11.98% in exploration task by exploiting 5G orchestration features for battery savings when using 3 robots.

Future mobile networks need to support intelligent services which collect and process data streams at the network edge, so as to offer real-time and accurate inferences to users. However, the widespread deployment of these services is hindered by the unprecedented energy cost they induce to the network, and by the difficulties in optimizing their end-to-end operation. To address these challenges, we propose a Bayesian learning framework for jointly configuring the service and the Radio Access Network (RAN), aiming to minimize the total energy consumption while respecting accuracy and latency service requirements. Using a fully-fledged prototype with a software-defined base station (vBS) and a GPU-enabled edge server, we profile a typical video analytics service and identify new performance trade-offs and optimization opportunities. Accordingly, we tailor the proposed learning framework to account for the (possibly varying) network conditions, user needs, and service metrics, and apply it to a range of experiments with real traces. Our findings suggest that this approach effectively adapts to different hardware platforms and service requirements, and outperforms state-of-the-art benchmarks based on neural networks.

Radio Access Network (RAN) slicing involves several challenges. In particular, the Mobile Network Operator (MNO) must ensure —before deploying each slice—that corresponding requirements can be met throughout its lifetime. For ultra-Reliable Low Latency Communication (uRLLC) slices, the MNO must guarantee the packet transmission delay within a delay budget with a certain probability. Most existing solutions focus on allocating dynamically radio resources to maximize the number of packets, whose transmission delay is within the delay budget. However, these solutions do not ensure the violation probability is below a target value in the long term. In this paper, we focus on slicing from a planning perspective. Specifically, we propose a Stochastic Network Calculus (SNC)-based model, which given the amount of radio resources allocated for a uRLLC slice, the target violation probability and the traffic demand distribution, provides the delay bound for such conditions. Additionally, we propose heuristics for planning uRLLC slices. Interestingly, such heuristics benefit from the proposed SNC-based model to compute the amount of radio resources to be assigned to each slice while its delay bound, given a target violation probability, is within the delay budget. We validate the SNC-based model and demonstrate the effectiveness of the heuristics.

Future generations of wireless networks will offer unrivalled performance via unprecedented solutions: meta-surfaces will drive such revolution by enabling control over the surrounding propagation environment, always portrayed as a tamper-proof black box. The reconfigurable intelligent surface (RIS) technology, envisioned as the discrete version of a metasurface, can dynamically alter the propagation of the impinging signals by, e.g., steering the corresponding beams towards controllable directions. This will unlock new application opportunities and deliver advanced end-user services.However, this fascinating solution comes at non-negligible costs: RISs require ad-hoc design, deployment and management operations to be fully exploited. In this paper, we tackle the RISs placement problem from a theoretical viewpoint, showcasing a large-scale solution on synthetic topologies to improve communication performance while solving the dead-zone problem. Additionally, our mathematical framework is empirically validated in a realistic indoor scenario, the Rennes railway station, showing how a complex indoor propagation environment can be fully disciplined by an advanced RIS installation.

Reconfigurable Intelligent Surfaces (RISs) are considered one of the key disruptive technologies towards future 6G networks. RISs revolutionize the traditional wireless communication paradigm by controlling the wave propagation properties of the impinging signals at will. A major roadblock for RIS is though the need for a fast and complex control channel to continuously adapt to the ever-changing wireless channel conditions. In this paper, we ask ourselves the question: Would it be feasible to remove the need for control channels for RISs? We analyze the feasibility of devising Self-Configuring Smart Surfaces that can be easily and seamlessly installed throughout the environment, following the new Internet-of-Surfaces (IoS) paradigm, without requiring modifications of the deployed mobile network. To this aim we design MARISA, a self-configuring metasurfaces absorption and reflection solution. Our results show that MARISA achieves outstanding performance, rivaling with state-of-the-art control channel-driven RISs solutions.

In this poster, we present the Reconfigurable Intelligent Surface (RIS) that we designed, built, and tested. At first, the RIS technology is briefly discussed, subsequently, our prototype details are explained, and finally, we conclude by showing the obtained test results. Our RIS design comprises arrays of patch antennas, delay lines, and programmable radio-frequency (RF) switches that enable almost-passive 3D beamforming, i.e., without active RF components.

Battery life for collaborative robotics scenarios is a key challenge limiting operational uses and deployment in real life. Mission-Critical tasks are among the most relevant and challenging scenarios. As multiple and heterogeneous on-board sensors are required to explore unknown environments in simultaneous localization and mapping (SLAM) tasks, battery life problems are further exacerbated. Given the time-sensitivity of mission-critical operations, the successful completion of specific tasks in the minimum amount of time is of paramount importance. In this paper, we analyze the benefits of 5G-enabled collaborative robots by enhancing the Robot Operating System (ROS) capabilities with network orchestration features for energy-saving purposes. We propose OROS, a novel orchestration approach that minimizes mission-critical task completion times of 5G-connected robots by jointly optimizing robotic navigation and sensing together with infrastructure resources. Our results show that OROS significantly outperforms state-of-the-art solutions in exploration tasks completion times by exploiting 5G orchestration features for battery life extension.

Forecasting is a task of ever increasing importance for the operation of mobile networks, where it supports anticipatory decisions by network intelligence and enables emerging zero-touch service and network management models. While current trends in forecasting for anticipatory networking lean towards the systematic adoption of models that are purely based on deep learning approaches, we pave the way for a different strategy to the design of predictors for mobile network environments. Specifically, following recent advances in time series prediction, we consider a hybrid approach that blends statistical modelling and machine learning by means of a joint training process of the two methods. By tailoring this mixed forecasting engine to the specific requirements of network traffic demands, we develop a Thresholded Exponential Smoothing and Recurrent Neural Network (TES-RNN) model. We experiment with TES-RNN in two practical network management use cases, i.e., (i) anticipatory allocation of network resources, and (ii) mobile traffic anomaly prediction. Results obtained with extensive traffic workloads collected in an operational mobile network show that TES-RNN can yield substantial performance gains over current state-of-the-art predictors in both applications considered.

Natural disasters affect millions of people every year. Finding missing persons in the shortest possible time is of crucial importance to reduce the death toll. This task is especially challenging when victims are sparsely distributed in large and/or difficult-to-reach areas and cellular networks are down. In this paper we present SARDO, a drone-based search and rescue solution that leverages the high penetration rate of mobile phones in the society to localize missing people. SARDO is an autonomous, all-in-one drone-based mobile network solution that does not require infrastructure support or mobile phones modifications. It builds on novel concepts such as pseudo-trilateration combined with machine-learning techniques to efficiently locate mobile phones in a given area. Our results, with a prototype implementation in a field-[1], show that SARDO rapidly determines the location of mobile phones ($\sim \!3$min/UE) in a given area with an accuracy of few tens of meters and at a low battery consumption cost ($\sim \!5\%$). State-of-the-art localization solutions for disaster scenarios rely either on mobile infrastructure support or exploit onboard cameras for human/computer vision, IR, thermal-based localization. To the best of our knowledge, SARDO is the first drone-based cellular search-and-rescue solution able to accurately localize missing victims through mobile phones.

The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex dependencies between computing and radio resources make vRAN resource control particularly daunting. We present vrAIn, a dynamic resource orchestrator for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data (traffic and channel quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithm based on an actor-critic neural network structure and a classifier to map contexts into resource control decisions. We have evaluated vrAIn experimentally, using an open-source LTE stack over different platforms, and via simulations over a production RAN. Our results show that: (i) vrAIn provides savings in computing capacity of up to 30% over CPU-agnostic methods; (ii) it improves the probability of meeting QoS targets by 25% over static policies; (iii) upon computing capacity under-provisioning, vrAIn improves throughput by 25% over state-of-the-art schemes; and (iv) it performs close to an optimal offline oracle. To our knowledge, this is the first work that thoroughly studies the computational behavior of vRANs and the first approach to a model-free solution that does not need to assume any particular platform or context.

Neural networks (NNs) are increasingly popular in developing NIDS, yet can prove vulnerable to adversarial examples. Through these, attackers that may be oblivious to the precise mechanics of the targeted NIDS add subtle perturbations to malicious traffic features, with the aim of evading detection and disrupting critical systems. Defending against such adversarial attacks is of high importance, but requires to address daunting challenges. Here, we introduce TIKI- TAKA, a general framework for(i)assessing the robustness of state-of-the-art deep learning-based NIDS against adversarial manipulations, and which(ii)incorporates defense mechanisms that we propose to increase resistance to attacks employing such evasion techniques. Specifically, we select five cutting-edge adversarial attack types to subvert three popular malicious traffic detectors that employ NNs. We experiment with publicly available datasets and consider both one-to-all and one-to-one classification scenarios, i.e., discriminating illicit vs benign traffic and respectively identifying specific types of anomalous traffic among many observed. The results obtained reveal that attackers can evade NIDS with up to 35.7% success rates, by only altering time-based features of the traffic generated. To counteract these weaknesses, we propose three defense mechanisms: model voting ensembling, ensembling adversarial training, and query detection. We demonstrate that these methods can restore intrusion detection rates to nearly 100% against most types of malicious traffic, and attacks with potentially catastrophic consequences (e.g., botnet) can be thwarted. This confirms the effectiveness of our solutions and makes the case for their adoption when designing robust and reliable deep anomaly detectors.

Virtualization and network slicing offer an unprecedented opportunity to mobile network operators: open their physical network infrastructure platform to the concurrent deployment of multiple logical self-contained networks, namelynetwork slices. In this paper, we propose and analyzeONETS, an Online NETwork Slicing solution that$\textbf {i}$) builds on the budgeted lock-up multi-armed bandit mathematical model and properties,$\textbf {ii}$) derives its analytical bounds in our proposed extension for network slicing,$\textbf {iii}$) seamlessly integrates into the 3GPP architecture,$\textbf {iv}$) proves its feasibility through a proof-of-concept implementation on commercial hardware considering three network slices and$\textbf {v}$) allows for the design of a low-complexity online network slice brokering solution that maximizes multiplexing gains.

Supporting Edge AI services is one of the most exciting features of future mobile networks. These services involve the collection and processing of voluminous data streams, right at the network edge, so as to offer real-time and accurate inferences to users. However, their widespread deployment is hampered by the energy cost they induce to the network. To overcome this obstacle, we propose a Bayesian learning framework for jointly configuring the service and the Radio Access Network (RAN), aiming to minimize the total energy consumption while respecting desirable accuracy and latency thresholds. Using a fully-fledged prototype with a software-defined base station (BS) and a GPU-enabled edge server, we profile a state-of-the-art video analytics AI service and identify new performance trade-offs. Accordingly, we tailor the optimization framework to account for the network context, the user needs, and the service metrics. The efficacy of our proposal is verified in a series of experiments and comparisons with neural network-based benchmarks.

The adoption of Unmanned Aerial Vehicles (UAVs) for public safety applications has skyrocketed in the last years. Leveraging on Physical Random Access Channel (PRACH) preambles, in this paper we pioneer a novel localization technique for UAVs equipped with cellular base stations used in emergency scenarios. We exploit the new concept of Orthogonal Time Frequency Space (OTFS) modulation (tolerant to channel Doppler spread caused by UAVs motion) to build a fully standards-compliant OTFS-modulated PRACH transmission and reception scheme able to perform time-of-arrival (ToA) measurements. First, we analyze such novel ToA ranging technique, both analytically and numerically, to accurately and iteratively derive the distance between localized users and the points traversed by the UAV along its trajectory. Then, we determine the optimal UAV speed as a trade-off between the accuracy of the ranging technique and the power needed by the UAV to reach and keep its speed during emergency operations. Finally, we demonstrate that our solution outperforms standard PRACH-based localization techniques in terms of Root Mean Square Error (RMSE) by about 20% in quasi-static conditions and up to 80% in high-mobility conditions.

Network virtualization is intended to be a key element of new generation networks. However, it is no clear how the implantation of this new paradigm will affect the power consumption of the network. To shed light on this relatively unexplored topic, we evaluate and analyze the power consumption of virtualized Base Station (vBS) experimentally. In particular, we measure the power consumption associated with uplink transmissions as a function of different variables such as traffic load, channel quality, modulation selection, and bandwidth. We find interesting tradeoffs between power savings and performance and propose two linear mixed-effect models to approximate the experimental data. These models allow us to understand the power behavior of the vBS and select power-efficient configurations. We release our experimental dataset hoping to foster further efforts in this research area.

Radio Access Network Virtualization (vRAN) will spearhead the quest towards supple radio stacks that adapt to heterogeneous infrastructure: from energy-constrained platforms deploying cells-on-wheels (e.g., drones) or battery-powered cells to green edge clouds. We perform an in-depth experimental analysis of the energy consumption of virtualized Base Stations (vBSs) and render two conclusions: (i) characterizing performance and power consumption is intricate as it depends on human behavior such as network load or user mobility; and (ii) there are many control policies and some of them have non-linear and monotonic relations with power and throughput. Driven by our experimental insights, we argue that machine learning holds the key for vBS control. We formulate two problems and two algorithms: (i) BP-vRAN, which uses Bayesian online learning to balance performance and energy consumption, and (ii) SBP-vRAN, which augments our Bayesian optimization approach with safe controls that maximize performance while respecting hard power constraints. We show that our approaches are data-efficient and have provably performance, which is paramount for carrier-grade vRANs. We demonstrate the convergence and flexibility of our approach and assess its performance using an experimental prototype.

Vehicle-to-everything (V2X) is expected to become one of the main drivers of 5G business in the near future. Dedicated network slices are envisioned to satisfy the stringent requirements of advanced V2X services, such as autonomous driving, aimed at drastically reducing road casualties. However, as V2X services become more mission-critical, new solutions need to be devised to guarantee their successful service delivery even in exceptional situations, e.g. road accidents, congestion, etc. In this context, we propose π-ROAD, a deep learning framework to automatically learn regular mobile traffic patterns along roads, detect non-recurring events and classify them by severity level. π-ROAD enables operators to proactively instantiate dedicated Emergency Network Slices (ENS) as needed while re-dimensioning the existing slices according to their service criticality level. Our framework is validated by means of real mobile network traces collected within 400 km of a highway in Europe and augmented with publicly available information on related road events. Our results show that π-ROAD successfully detects and classifies non-recurring road events and reduces up to 30% the impact of ENS on already running services.

RAN virtualization will become a key technology for the last mile of next-generation mobile networks driven by initiatives such as the O-RAN alliance. However, due to the computing fluctuations inherent to wireless dynamics and resource contention in shared computing infrastructure, the price to migrate from dedicated to shared platforms may be too high. Indeed, we show in this paper that the baseline architecture of a base station's distributed unit (DU) collapses upon moments of deficit in computing capacity. Recent solutions to accelerate some signal processing tasks certainly help but do not tackle the core problem: a DU pipeline that requires predictable computing to provide carrier-grade reliability.

We demonstrate Nuberu. The scenario consists of a DU under test (DuT), and one or more DUs sharing computing resources. A dashboard lets us control (𝑖) the type of DuT: “Baseline”, implemented with a legacy full-fledged eNB, or Nuberu; (𝑖𝑖) the number of competing vDUs; and (𝑖𝑖𝑖) their SNR. A second screen shows real-time metrics: (𝑖) the processing latency of the TBs from each vDU instance; (𝑖𝑖) the throughput performance of DuT; (𝑖𝑖𝑖) the processing latency of DU jobs from DuT; and (𝑖𝑣) the ratio of latency constraint violations of DuT jobs. We show how the throughput attained by the baseline DU approach collapses upon sufficiently high computing interference from the competing DUs. Conversely, we show that the DU design introduced in [3] preserves reliability irrespective of the computing interference.

Massive access for Internet-of-Things (IoT) in beyond 5G networks represents a daunting challenge for conventional bandwidth-limited technologies. Millimeter-wave technologies (mmWave)-which provide large chunks of bandwidth at the cost of more complex wireless processors in harsher radio environments-is a promising alternative to accommodate massive IoT but its cost and power requirements are an obstacle for wide adoption in practice. In this context, meta-materials arise as a key innovation enabler to address this challenge by Re-configurable Intelligent Surfaces (RISs). In this article we take on the challenge and study a beyond 5G scenario consisting of a multi-antenna base station (BS) serving a large set of single-antenna user equipments (UEs) with the aid of RISs to cope with non-line-of-sight paths. Specifically, we build a mathematical framework to jointly optimize the precoding strategy of the BS and the RIS parameters in order to minimize the system sum mean squared error (SMSE). This novel approach reveals convenient properties used to design two algorithms, RISMA and Lo- RISMA, which are able to either find simple and efficient solutions to our problem (the former) or accommodate practical constraints with low-resolution RISs (the latter). Numerical results show that our algorithms outperform conventional benchmarks that do not employ RIS (even with low-resolution meta-surfaces) with gains that span from 20% to 120% in sum rate performance.

In addition to CPRI, new functional splits have been defined in 5G creating diverse fronthaul transport bandwidth and latency requirements. These fronthaul requirements shall be fulfilled simultaneously together with the backhaul requirements by an integrated fronthaul and backhaul transport solution. In this paper, we analyze the technical challenges to achieve an integrated transport solution in 5G and propose specific solutions to address these challenges. These solutions have been implemented and verified with pre-commercial equipment. Our results confirm that an integrated fronthaul and backhaul transport dubbed Crosshaul can meet all the requirements of 5G fronthaul and backhaul in a cost-efficient manner.

Empowered bynetwork softwarization, 5G systems have become the key enabler to foster the digital transformation of the vertical industries by expanding the scope of traditional mobile networks and enriching the network service offerings. To make this a reality, we propose anautomationsolution for vertical services provisioning and hierarchical Service Level Agreement (SLA) management.Service scalingis one of the most essential operations to adapt the service deployments and resource allocations to ensure SLA fulfilment. Three different scaling levels are addressed in this work: application-, service- and resource-level. We have implemented our solution in a proof-of-concept of a virtualized mobile network platform, spanning over three geographically-distributed sites. To evaluate our solution, we leverage field tests, focusing onautomotive vertical servicescomprising a mission-critical application (collision-avoidance) and an entertainment one (video streaming). The results demonstrate the excellent performance of our solution, and its ability to automatically deploy vertical services and ensure their SLAs through different levels of service scaling.

Virtualized radio access networks (vRAN) are emerging as a key component of wireless cellular networks, and it is therefore imperative to optimize their architecture. vRANs are decentralized systems where the Base Station (BS) functions can be split between the edge Distributed Units (DUs) and Cloud computing Units (CUs); hence they have many degrees of design freedom. We propose a framework for optimizing the number and location of CUs, the function split for each BS, and the association and routing for each DU-CU pair. We combine a linearization technique with a cutting-planes method to expedite theexactproblem solution. The goal is to minimize the network costs and balance them with the criterion of centralization, i.e., the number of functions placed at CUs. Using data-driven simulations we find that multi-CU vRANs achieve cost savings up to 28% and improve centralization by 77%, compared to single-CU vRANs. Interestingly, we see non-trivial trade-offs among centralization and cost, which can be aligned or conflicting based on the traffic and network parameters. Our work sheds light on the vRAN design problem from a new angle, highlights the importance of deploying multiple CUs, and offers a rigorous optimization tool for balancing costs and performance.

Network Slicing is expected to become a game changer in the upcoming 5G networks and beyond, enlarging the telecom business ecosystem through still-unexplored vertical industry profits. This implies that heterogeneous service level agreements (SLAs) must be guaranteed per slice given the multitude of predefined requirements. In this paper, we pioneer a novel radio slicing orchestration solution that simultaneously provides latency and throughput guarantees in a multi-tenancy environment. Leveraging on a solid mathematical framework, we exploit the exploration-vs-exploitation paradigm by means of a multi-armed-bandit-based (MAB) orchestrator, LACO, that makes adaptive resource slicing decisions with no prior knowledge on the traffic demand or channel quality statistics. As opposed to traditional MAB methods that are blind to the underlying system, LACO relies on system structure information to expedite decisions. After a preliminary simulations campaign empirically proving the validness of our solution, we provide a robust implementation of LACO using off-the-shelf equipment to fully emulate realistic network conditions: near-optimal results within affordable computational time are measured when LACO is in place.

We study the important and challenging problem of virtualized radio access network (vRAN) design in its most general form. We develop an optimization framework that decides the number and deployment locations of central/cloud units (CUs); which distributed units (DUs) each of them will serve; the functional split that each BS will implement; and the network paths for routing the traffic to CUs and the network core. Our design criterion is to minimize the operator's expenditures while serving the expected traffic. To this end, we combine a linearization technique with a cutting-planes method in order to expedite the exact solution of the formulated problem. We evaluate our framework using real operational networks and system measurements, and follow an exhaustive parameter-sensitivity analysis. We find that the benefits when departing from single-CU deployments can be as high as 30% for our networks, but these gains diminish with the further addition of CUs. Our work sheds light on the vRAN design from a new angle, highlights the importance of deploying multiple CUs, and offers a rigorous framework for optimizing the costs of Multi-CUs vRAN.

With the advent of revolutionary technologies, such as virtualization and softwarization, a novel concept for 5G networks and beyond has been unveiled: Network Slicing. Initially driven by the research community, standardization bodies as 3GPP have embraced it as a promising solution to revolutionize the traditional mobile telecommunication market by enabling new business models opportunities. Network Slicing is envisioned to open up the telecom market to new players such as Industry Verticals, e.g., automotive, smart factories, e-health, etc. Given the large number of potential new business players, dubbed as network tenants, novel solutions are required to accommodate their needs in a cost-efficient and secure manner. In this paper, we propose NSBchain, a novel network slicing brokering (NSB) solution, which leverages on the widely adopted Blockchain technology to address the new business models needs beyond traditional network sharing agreements. NSBchain defines a new entity, the Intermediate Broker (IB), which enables Infrastructure Providers (InPs) to allocate network resources to IBs through smart contracts and IBs to assign and re-distribute their resources among tenants in a secure, automated and scalable manner. We conducted an extensive performance evaluation by means of an open-source blockchain platform that proves the feasibility of our proposed framework considering a large number of tenants and two different consensus algorithms.

The combination of network softwarization with network slicing enables the provisioning of very diverse services over the same network infrastructure. However, it also creates a complex environment where the orchestration of network resources cannot be guided by traditional, human-in-the-loop network management approaches. New solutions that perform these tasks automatically and in advance are needed, paving the way to zero-touch network slicing. In this paper, we propose AZTEC, a data-driven framework that effectively allocates capacity to individual slices by adopting an original multi-timescale forecasting model. Hinging on a combination of Deep Learning architectures and a traditional optimization algorithm, AZTEC anticipates resource assignments that minimize the comprehensive management costs induced by resource overprovisioning, instantiation and reconfiguration, as well as by denied traffic demands. Experiments with real-world mobile data traffic show that AZTEC dynamically adapts to traffic fluctuations, and largely outperforms state-of-the-art solutions for network resource orchestration.

As 5G deployments start to roll-out, indoor solutions are increasingly pressed towards delivering a similar user experience. Wi-Fi is the predominant technology of choice indoors and major vendors started addressing this need by incorporating the mmWave band to their products. In the near future, mmWave devices are expected to become pervasive, opening up new business opportunities to exploit their unique properties.In this paper, we present a novel PASsive Intrusion Detection system, namely PASID, leveraging on already deployed indoor mmWave communication systems. PASID is a software module that runs in off-the-shelf mmWave devices. It automatically models indoor environments in a passive manner by exploiting regular beamforming alignment procedures and detects intruders with a high accuracy. We model this problem analytically and show that for dynamic environments machine learning techniques are a cost-efficient solution to avoid false positives. PASID has been implemented in commercial off-the-shelf devices and deployed in an office environment for validation purposes. Our results show its intruder detection effectiveness (~99% accuracy) and localization potential (~ 2 meters range) together with its negligible energy increase cost (~ 2%).

The dynamic management of network resources is both a critical and challenging task in upcoming multi-tenant mobile networks, which requires allocating capacity to individual network slices so as to accommodate future time-varying service demands. Such an anticipatory resource configuration process must be driven by suitable predictors that take into account the monetary cost associated to overprovisioning or underprovisioning of networking capacity, computational power, memory, or storage. Legacy models that aim at forecasting traffic demands fail to capture these key economic aspects of network operation. To close this gap, we present DeepCog, a deep neural network architecture inspired by advances in image processing and trained via a dedicated loss function. Unlike traditional traffic volume predictors, DeepCog returns a cost-aware capacity forecast, which can be directly used by operators to take short- and long-term reallocation decisions that maximize their revenues. Extensive performance evaluations with real-world measurement data collected in a metropolitan-scale operational mobile network demonstrate the effectiveness of our proposed solution, which can reduce resource management costs by over 50% in practical case studies.

It is now commonly agreed that future 5G Networks will build upon the network slicing concept. The ability to provide virtual, logically independent “slices” of the network will also have an impact on the models that will sustain the business ecosystem. Network slicing will open the door to new players: the infrastructure provider, which is the owner of the infrastructure, and the tenants, which may acquire a network slice from the infrastructure provider to deliver a specific service to their customers. In this new context, how to correctly handle resource allocation among tenants and how to maximize the monetization of the infrastructure become fundamental problems that need to be solved. In this paper, we address this issue by designing a network slice admission control algorithm that (i) autonomously learns the best acceptance policy while (ii) it ensures that the service guarantees provided to tenants are always satisfied. The contributions of this paper include: (i) an analytical model for the admissibility region of a network slicing-capable 5G Network, (ii) the analysis of the system (modeled as a Semi-Markov Decision Process) and the optimization of the infrastructure providers revenue, and (iii) the design of a machine learning algorithm that can be deployed in practical settings and achieves close to optimal performance.

Network densification over space and spectrum is expected to be key to enabling the requirements of next generation mobile systems. The pitfall is that radio resource allocation becomes substantially more complex. In this paper, we propose LaSR, a practical multi-connectivity scheduler for OFDMA-based multi-RAT systems. LaSR makes optimal discrete control actions by solving a sequence of simple optimization problems that do not require prior information of traffic patterns. In marked contrast to previous work, the flexibility of our approach allows us to construct scheduling policies that achieve a good balance between system cost and utility satisfaction, while jointly operate across heterogeneous RATs, accommodate real-system requirements, and guarantee system stability. Examples of system requirements considered in this paper include (but are not limited to): constraints on how scheduling data can be encoded onto signaling protocols (e.g., LTE's DCI), delays when turning on/off radio units, or on/off cycles when using unlicensed spectrum. We evaluate our scheduler via a thorough simulation campaign in a variety of scenarios with e.g., mobile users, RATs using unlicensed spectrum (using a duty cycle access mechanism), imperfect queue state information, and constrained signaling protocol.

Mass events represent one of the most challenging scenarios for mobile networks because, although their date and time are usually known in advance, the actual demand for resources is difficult to predict due to its dependency on many different factors. Based on data provided by a major European carrier during mass events in a football stadium comprising up to 30.000 people, 16 base station sectors and 1 Km2area, we performed a data-driven analysis of the radio access network infrastructure dynamics during such events. Given the insights obtained from the analysis, we developed ARENA, a model-free deep learning Radio Access Network (RAN) capacity forecasting solution that, taking as input past network monitoring data and events context information, provides guidance to mobile operators on the expected RAN capacity needed during a future event. Our results, validated against real events contained in the dataset, illustrate the effectiveness of our proposed solution.

The combination of recent emerging technologies such as network function virtualization (NFV) and network programmability (SDN) gave birth to the novel Network Slicing paradigm. 5G networks consist of multi-tenant infrastructures capable of offering leased network “slices” to new customers (e.g., vertical industries) enabling a new telecom business model: Slice-as-a-Service (SlaaS). However, as the service demand gets increasingly dense, slice requests congestion may occur leading to undesired waiting periods. This may turn into impatient tenant behaviors that increase potential loss of the business attractiveness to customers. In this paper, we aim to: 1) study the slicing admission control problem by means of a multi-queuing system for heterogeneous tenant requests; 2) derive its statistical behavior model; 3) find out the rational strategy of impatient tenants waiting in queue-based slice admission control systems; 4) prove mathematically and empirically the benefits of allowing infrastructure providers to share its information with the upcoming tenants; and 5) provide a utility model for network slices admission optimization. Our results analyze the capability of the proposed SlaaS system to be approximately Markovian and evaluate its performance as compared to a baseline solution.

Recently released 5G networks empower the novel Network Slicing concept. Network slicing introduces new business models such as allowing telecom providers to lease a virtualized slice of their infrastructure to tenants such as industry verticals, e.g. automotive, e-health, factories, etc. However, this new paradigm poses a major challenge when applied to Radio Access Networks (RAN): how to achieve revenue maximization while meeting the diverse service level agreements (SLAs) requested by the infrastructure tenants? In this paper, we propose a new analytical framework, based on stochastic geometry theory, to model realistic RANs that leverage the business opportunities offered by network slicing. We mathematically prove the benefits of slicing radio access networks as compared to non-sliced infrastructures. Based on this, we design a new admission control functional block, STORNS, which takes decisions considering per slice SLA guaranteed average experienced throughput. A radio resource allocation strategy is introduced to optimally allocate transmit power and bandwidth (i.e., a slice of radio access resources) to the users of each infrastructure tenant. Numerical results are illustrated to validate our proposed solution in terms of potential spectral efficiency, and compare it against a non-slicing benchmark.

The combination of recent emerging technologies such as network function virtualization (NFV) and network programmability (SDN) gave birth to the Network Slicing revolution. 5G networks consist of multi-tenant infrastructures capable of offering leased network “slices” to new customers (e.g., vertical industries) enabling a new telecom business model: Slice-as-a-Service (SlaaS). In this paper, we aim i) to study the slicing admission control problem by means of a multi-queuing system for heterogeneous tenant requests, ii) to derive its statistical behavior model, and iii) to provide a utility-based admission control optimization. Our results analyze the capability of the proposed SlaaS system to be approximately Markovian and evaluate its performance as compared to legacy solutions.

Network slicing is a new paradigm for future 5G networks where the network infrastructure is divided into slices devoted to different services and customized to their needs. With this paradigm, it is essential to allocate to each slice the needed resources, which requires the ability to forecast their respective demands. To this end, we present DeepCog, a novel data analytics tool for the cognitive management of resources in 5G systems. DeepCog forecasts the capacity needed to accommodate future traffic demands within individual network slices while accounting for the operator's desired balance between resource overprovisioning (i.e., allocating resources exceeding the demand) and service request violations (i.e., allocating less resources than required). To achieve its objective, DeepCog hinges on a deep learning architecture that is explicitly designed for capacity forecasting. Comparative evaluations with real-world measurement data prove that DeepCog's tight integration of machine learning into resource orchestration allows for substantial (50% or above) reduction of operating expenses with respect to resource allocation solutions based on state-of-the-art mobile traffic predictors. Moreover, we leverage DeepCog to carry out an extensive first analysis of the trade-off between capacity overdimensioning and unserviced demands in adaptive, sliced networks and in presence of real-world traffic.

The virtualization of radio access networks (vRAN) is the last milestone in the NFV revolution. However, the complex dependencies between computing and radio resources make vRAN resource control particularly daunting. We present vrAIn, a dynamic resource controller for vRANs based on deep reinforcement learning. First, we use an autoencoder to project high-dimensional context data (traffic and signal quality patterns) into a latent representation. Then, we use a deep deterministic policy gradient (DDPG) algorithm based on an actor-critic neural network structure and a classifier to map (encoded) contexts into resource control decisions. We have implemented vrAIn using an open-source LTE stack over different platforms. Our results show that vrAIn successfully derives appropriate compute and radio control actions irrespective of the platform and context: (i) it provides savings in computational capacity of up to 30% over CPU-unaware methods; (ii) it improves the probability of meeting QoS targets by 25% over static allocation policies using similar CPU resources in average; (iii) upon CPU capacity shortage, it improves throughput performance by 25% over state-of-the-art schemes; and (iv) it performs close to optimal policies resulting from an offline oracle. To the best of our knowledge, this is the first work that thoroughly studies the computational behavior of vRANs, and the first approach to a model-free solution that does not need to assume any particular vRAN platform or system conditions.

While the application of the NFV paradigm into the network is proceeding full steam ahead, there is still one last mile- stone to be achieved in this context: the virtualization of the radio access network (vRAN). Due to the very complex de- pendency between the radio conditions and the computing resources needed to provide the baseband processing func- tionality, attaining an efficient resource control is particularly challenging. In this demonstration, we will showcase vrAIn, a vRAN dynamic resource controller that employs deep re- inforcement learning to perform resource assignment deci- sions. vrAIn, which is implemented using an open-source LTE stack over a Linux platform, can achieve substantial sav- ings in the used CPU resources while maintaining the target QoS for the attached terminals and maximize throughput when there is a deficit of computational capacity.

This paper focuses on optimizing resource allocation amongst a set of tenants, network slices, supporting dynamic customer loads over a set of distributed resources, e.g., base stations. The aim is to reap the benefits of statistical multiplexing resulting from flexible sharing of `pooled' resources, while enabling tenants to differentiate and protect their performance from one another's load fluctuations. To that end we consider a setting where resources are grouped into Virtual Resource Pools (VRPs) wherein resource allocation is jointly and dynamically managed. Specifically for each VRP we adopt a Share-Constrained Proportionally Fair (SCPF) allocation scheme where each tenant is allocated a fixed share (budget). This budget is to be distributed equally amongst its active customers which in turn are granted fractions of their associated VRP resources in proportion to customer shares. For a VRP with a single resource, this translates to the well known Generalized Processor Sharing (GPS) policy. For VRPs with multiple resources SCPF provides a flexible means to achieve load elastic allocations across tenants sharing the pool. Given tenants' per resource shares and expected loads, this paper formulates the problem of determining optimal VRP partitions which maximize the overall expected shared weighted utility while ensuring protection guarantees. For a high load/capacity setting we exhibit this network utility function explicitly, quantifying the benefits and penalties of any VRP partition, in terms of network slices' ability to achieve performance differentiation, load balancing, and statistical multiplexing. Although the problem is shown to be NP-Hard, a simple greedy heuristic is shown to be effective. Analysis and simulations confirm that the selection of optimal VRP partitions provide a practical avenue towards improving network utility in network slicing scenarios with dynamic loads.

The economic sustainability of future mobile networks will largely depend on the strong specialization of its offered services. Network operators will need to provide added value to their tenants, by moving from the traditional one-size-fits-all strategy to a set of virtual end-to-end instances of a common physical infrastructure, named network slices, which are especially tailored to the requirements of each application. Implementing network slicing has significant consequences in terms of resource management: service customization entails assigning to each slice fully dedicated resources, which may also be dynamically reassigned and overbooked in order to increase the cost-efficiency of the system. In this paper, we adopt a data-driven approach to quantify the efficiency of resource sharing in future sliced networks. Building on metropolitan-scale real-world traffic measurements, we carry out an extensive parametric analysis that highlights how diverse performance guarantees, technological settings, and slice configurations impact the resource utilization at different levels of the infrastructure in presence of network slicing. Our results provide insights on the achievable efficiency of network slicing architectures, their dimensioning, and their interplay with resource management algorithms at different locations and reconfiguration timescales.

Network slicing to enable resource sharing among multiple tenants-network operators and/or services-is considered as a key functionality for next generation mobile networks. This paper provides an analysis of a well-known model for resource sharing, the share-constrained proportional allocation mechanism, to realize network slicing. This mechanism enables tenants to reap the performance benefits of sharing, while retaining the ability to customize their own users' allocation. This results in a network slicing game in which each tenant reacts to the user allocations of the other tenants so as to maximize its own utility. We show that, for elastic traffic, the game associated with such strategic behavior converges to a Nash equilibrium. At the Nash equilibrium, a tenant always achieves the same or better performance than that of a static partitioning of resources, thus providing the same level of protection as static partitioning. We further analyze the efficiency and fairness of the resulting allocations, providing tight bounds for the price of anarchy and envy-freeness. Our analysis and extensive simulation results confirm that the mechanism provides a comprehensive practical solution to realize network slicing. Our theoretical results also fills a gap in the analysis of this resource allocation model under strategic players.

Network slicing is considered one of the main pillars of the upcoming 5G networks. Indeed, the ability to slice a mobile network and tailor each slice to the needs of the corresponding tenant is envisioned as a key enabler for the design of future networks. However, this novel paradigm opens up to new challenges, such as isolation between network slices, the allocation of resources across them, and the admission of resource requests by network slice tenants. In this paper, we address this problem by designing the following building blocks for supporting network slicing: i) traffic and user mobility analysis, ii) a learning and forecasting scheme per slice, iii) optimal admission control decisions based on spatial and traffic information, and iv) a reinforcement process to drive the system towards optimal states. In our framework, namely RL-NSB, infrastructure providers perform admission control considering the service level agreements (SLA) of the different tenants as well as their traffic usage and user distribution, and enhance the overall process by the means of learning and the reinforcement techniques that consider heterogeneous mobility and traffic models among diverse slices. Our results show that by relying on appropriately tuned forecasting schemes, our approach provides very substantial potential gains in terms of system utilization while meeting the tenants' SLAs.

Network slicing allows mobile operators to offer, via proper abstractions, mobile infrastructure (radio, networking, computing) to vertical sectors traditionally alien to the telco industry (e.g., automotive, health, construction). Owning to similar business nature, in this paper we adopt yield management models successful in other sectors (e.g. airlines, hotels, etc.) and so we explore the concept of slice overbooking to maximize the revenue of mobile operators.

Virtualized Radio Access Network (vRAN) architectures constitute a promising solution for the densification needs of 5G networks, as they decouple Base Stations (BUs) functions from Radio Units (RUs) allowing the processing power to be pooled at cost-efficient Central Units (CUs). vRAN facilitates the flexible function relocation (split selection), and therefore enables splits with less stringent network requirements compared to state-of-the-art fully Centralized (C-RAN) systems. In this paper, we study the important and challenging vRAN design problem. We propose a novel modeling approach and a rigorous analytical framework, FluidRAN, that minimizes RAN costs by jointly selecting the splits and the RUs-CUs routing paths. We also consider the increasingly relevant scenario where the RAN needs to support multi-access edge computing (MEC) services, that naturally favor distributed RAN (D-RAN) architectures. Our framework provides a joint vRAN/MEC solution that minimizes operational costs while satisfying the MEC needs. We follow a data-driven evaluation method, using topologies of 3 operational networks. Our results reveal that (i) pure C-RAN is rarely a feasible upgrade solution for existing infrastructure, (ii) FluidRAN achieves significant cost savings compared to D-RAN systems, and (iii) MEC can increase substantially the operator's cost as it pushes vRAN function placement back to RUs.

By providing especially tailored instances of a virtual network,network slicing allows for a strong specialization of the offered services on the same shared infrastructure. Network slicing has profound implications on resource management, as it entails an inherent trade-off between: (i) the need for fully dedicated resources to support service customization, and (ii) the dynamic resource sharing among services to increase resource efficiency and cost-effectiveness of the system. In this paper, we provide a first investigation of this trade-off via an empirical study of resource management efficiency in network slicing. Building on substantial measurement data collected in an operational mobile network (i) we quantify the efficiency gap introduced by non-reconfigurable allocation strategies of different kinds of resources, from radio access to the core of the network, and (ii) we quantify the advantages of their dynamic orchestration at different timescales. Our results provide insights on the achievable efficiency of network slicing architectures, their dimensioning, and their interplay with resource management algorithms.

Virtualized radio access network (vRAN) architectures and multiple-access edge computing (MEC) systems constitute two key solutions for the emerging Tactile Internet applications and the increasing mobile data traffic. Their efficient deployment, however, requires a careful design tailored to the available network resources and user demand. In this paper, we propose a novel modeling approach and a rigorous analytical framework, MEC-vRAN joint design problem (MvRAN), that minimizes vRAN costs and maximizes MEC performance. Our framework selects jointly the base-station function splits, the fronthaul routing paths, and the placement of MEC functions. We follow a data-driven evaluation method, using topologies of three operational networks and experiments with a typical face-recognition MEC service. Our results reveal that MvRAN achieves significant cost savings (up to 2.5 times) compared to non-optimized centralized RAN or decentralized RAN systems, and MEC pushes the vRAN functions to radio units and hence can increase substantially the network cost.

Cloud Radio Access Network (C-RAN) will become a main building block for 5G. However, the stringent requirements of current fronthaul solutions hinder its large-scale deployment. In order to introduce C-RAN widely in 5G, the next generation fronthaul interface (NGFI) will be based on a cost-efficient packet-based network with higher path diversity. In addition, NGFI shall support a flexible functional split of the RAN to adapt the amount of centralization to the capabilities of the transport network. In this paper we question the ability of standard techniques to route NGFI traffic while maximizing the centralization degree-the goal of C-RAN. We propose two solutions jointly addressing both challenges: (i) a nearly-optimal backtracking scheme, and (ii) a low-complex greedy approach. We first validate the feasibility of our approach in an experimental proof-of-concept, and then evaluate both algorithms via simulations in large-scale (real and synthetic) topologies. Our results show that state-of-the-art techniques fail at maximizing the centralization degree and that the achievable C-RAN centralization highly depends on the underlying topology structure.

Autonomous management and orchestration (MANO) of virtualized resources and services, especially in large-scale network function virtualization (NFV) environments, is a big challenge owing to the stringent delay and performance requirements expected of a variety of network services. The quality-of-decisions (QoD) of a MANO system depends on the quality and timeliness of the information received from the underlying monitoring system. The data generated by monitoring systems is a significant contributor to the network and processing load of MANO systems, impacting thus their performance. This raises a unique challenge: how to jointly optimize the QoD of MANO systems while at the same minimizing their monitoring loads at runtime? This is the main focus of this paper. In this context, we propose a novel automated NFV orchestration solution, namely z-TORCH (zero Touch Orchestration) that jointly optimizes the orchestration and monitoring processes by exploiting machine-learning-based techniques. The objective is to enhance the QoD of MANO systems achieving a near-optimal placement of virtualized network functions at minimum monitoring costs.

Future mobile networks will exploit unlicensed spectrum to boost capacity and meet growing user demands cost-effectively. The 3rdGeneration Partnership Project (3GPP) has recently defined a License Assisted Access (LAA) scheme to enable global Unlicensed LTE (U-LTE) deployment, aiming at 1) ensuring fair coexistence with incumbent WiFi networks, i.e., impacting on their performance no more than another WiFi device; and 2) achieving superior airtime efficiency as compared with WiFi. We show the standardized LAA fails to simultaneously fulfill these objectives, and design an alternative orthogonal (collision-free) listen-before-talk coexistence paradigm that provides a substantial improvement in performance, yet imposes no penalty on existing WiFi networks. We derive two optimal transmission policies, ORLA and OLAA, that maximize LAA throughput in both asynchronous and synchronous (i.e., with alignment to licensed anchor frame boundaries) modes of operation, respectively. We present a comprehensive evaluation through which we demonstrate that, when aggregating packets, IEEE 802.11ac WiFi can be more efficient than LAA, whereas our proposals attains 100% higher throughput, without harming WiFi. We further show that long U-LTE frames incur up to 92% throughput losses on WiFi when using 3GPP LAA, whilst ORLA/OLAA sustain >200% gains at no cost, even in the presence of non-saturated WiFi and/or in multi-rate scenarios.

In a virtualized radio access network (RAN), baseband processing is performed by software running in cloud-computing platforms. However, current protocol stacks were not designed to run in this kind of environment; the high variability on the computational resources consumed by RAN functions may lead to eventual computational outages (where frames are not decoded on time), severely degrading the resulting performance. In this paper, we address this issue by re-designing two key functions of the protocol stack: 1) scheduling, to select the transmission of those frames that do not result in computational outages, and 2) modulation and coding scheme (MCS) selection, to downgrade the selected MCS in case no sufficient computational resources are available. We formulate the resulting problem as a joint optimization and compute the (asymptotically) optimal solution to this problem. We further show that this solution involves solving an NP-hard problem, and propose an algorithm to obtain an approximate solution that is computationally efficient while providing bounded performance over the optimal. We thoroughly evaluate the proposed approach via simulation, showing that it can provide savings as high as 80% of the computational resources while paying a small price in performance.

Technologies that enable network slicing are expected to be a key component of next generation mobile networks. Their promise lies in enabling tenants (such as mobile operators and/or services) to reap the cost and performance benefits of sharing resources while retaining the ability to customize their own allocations. When employing dynamic sharing mechanisms, tenants may exhibit strategic behavior, optimizing their choices in response to those of other tenants. This paper analyzes dynamic sharing in network slicing when tenants support inelastic users with minimum rate requirements. We propose a NEtwork Slicing (NES) framework combining: 1) admission control; 2) resource allocation; and 3) user dropping. We model the network slicing system with admitted users as a NES game; this is a new class of game where the inelastic nature of the traffic may lead to dropping users whose requirements cannot be met. We show that, as long as admission control guarantees that slices can satisfy the rate requirements of all their users, this game possesses a Nash equilibrium. Admission control policies (a conservative and an aggressive one) are considered, along with a resource allocation scheme and a user dropping algorithm, geared at maintaining the system in Nash equilibria. We analyze our NES framework's performance in equilibrium, showing that it achieves the same or better utility than static resource partitioning, and bound the difference between NES and the socially optimal performance. Simulation results confirm the effectiveness of the proposed approach.

The increasing deployment of smart devices using mobile networks is pushing operators to consider efficient ways to tailor their infrastructure to the Internet of Things (IoT) diverse requirements and traffic characteristics. A promising approach to address this need is the novel concept of network slicing, which aims at allocating portions of network resources to specific tenants, such as enhanced mobile broadband (eMBB), IoT, e-health, connected vehicles, etc. While this has been traditionally done with long-term agreements between network operators and tenants as MVNOs, in this work we focus on a new business model where network operators offer network slices as a service (SlaaS). In particular, we propose a novel system comprising an IoT Broker managing massive IoT network slices services and a Network Slice Broker that through bi-directional negotiations are able to efficiently allocate and orchestrate network resources.

In addition to providing substantial performance enhancements, future 5G networks will also change the mobile network ecosystem. Building on the network slicing concept, 5G allows to “slice” the network infrastructure into separate logical networks that may be operated independently and targeted at specific services. This opens the market to new players: the infrastructure provider, which is the owner of the infrastructure, and the tenants, which may acquire a network slice from the infrastructure provider to deliver a specific service to their customers. In this new context, we need new algorithms for the allocation of network resources that consider these new players. In this paper, we address this issue by designing an algorithm for the admission and allocation of network slices requests that (i) maximises the infrastructure provider's revenue and (ii) ensures that the service guarantees provided to tenants are satisfied. Our key contributions include: (i) an analytical model for the admissibility region of a network slicing-capable 5G Network, (ii) the analysis of the system (modelled as a Semi-Markov Decision Process) and the optimisation of the infrastructure provider's revenue, and (iii) the design of an adaptive algorithm (based on Q-learning) that achieves close to optimal performance.

Network slicing to enable resource sharing among multiple tenants-network operators and/or services-is considered a key functionality for next generation mobile networks. This paper provides an analysis of a well-known model for resource sharing, the `share-constrained proportional allocation' mechanism, to realize network slicing. This mechanism enables tenants to reap the performance benefits of sharing, while retaining the ability to customize their own users' allocation. This results in a network slicing game in which each tenant reacts to the user allocations of the other tenants so as to maximize its own utility. We show that, under appropriate conditions, the game associated with such strategic behavior converges to a Nash equilibrium. At the Nash equilibrium, a tenant always achieves the same, or better, performance than under a static partitioning of resources, hence providing the same level of protection as such static partitioning. We further analyze the efficiency and fairness of the resulting allocations, providing tight bounds for the price of anarchy and envy-freeness. Our analysis and extensive simulation results confirm that the mechanism provides a comprehensive practical solution to realize network slicing. Our theoretical results also fill a gap in the literature regarding the analysis of this resource allocation model under strategic players.

The emerging network slicing paradigm for 5G provides new business opportunities by enabling multi-tenancy support. At the same time, new technical challenges are introduced, as novel resource allocation algorithms are required to accommodate different business models. In particular, infrastructure providers need to implement radically new admission control policies to decide on network slices requests depending on their Service Level Agreements (SLA). When implementing such admission control policies, infrastructure providers may apply forecasting techniques in order to adjust the allocated slice resources so as to optimize the network utilization while meeting network slices' SLAs. This paper focuses on the design of three key network slicing building blocks responsible for (i) traffic analysis and prediction per network slice, (ii) admission control decisions for network slice requests, and (iii) adaptive correction of the forecasted load based on measured deviations. Our results show very substantial potential gains in terms of system utilization as well as a trade-off between conservative forecasting configurations versus more aggressive ones (higher gains, SLA risk).

Next 5G networks will force service and network providers to support a huge variety of final services with very different requirements in terms of bandwidth, latency, etc. In parallel, vertical industries, as customers, will use 5G networks as technical enablers to support their businesses, demanding appropriate mechanisms for a flexible access and control of network and computing resource slices in the locations where such vertical have business. Since the footprint and the availability of resources to support the variety of services could be limited on the primary provider side, open environments enabling the trading of resources in the form of slices are required to facilitate the sharing of infrastructure with the necessary isolation and scalability. Here, this is exemplified by the proposal of adaptations between two prevalent architectures being defined in the EU H2020 projects 5G-Crosshaul and 5GExchange for allowing the trading of crosshaul resources enabling 5G services for Verticals.

The paper elaborates on the technological and architectural innovations researched and developed by 5G-PPP Phase 1 projects and covering innovation areas such as 5G system design and evaluation, novel air interfaces, network management and security as well as virtualization and service deployment aspects.

This paper addresses the slicing of radio access network resources by multiple tenants, e.g., virtual wireless operators and service providers. We consider a criterion for dynamic resource allocation amongst tenants, based on a weighted proportionally fair objective, which achieves desirable fairness/protection across the network slices of the different tenants and their associated users. Several key properties are established, including: the Pareto-optimality of user association to base stations, the fair allocation of base stations' resources, and the gains resulting from dynamic resource sharing across slices, both in terms of utility gains and capacity savings. We then address algorithmic and practical challenges in realizing the proposed criterion. We show that the objective is NP-hard, making an exact solution impractical, and design a distributed semi-online algorithm, which meets performance guarantees in equilibrium and can be shown to quickly converge to a region around the equilibrium point. Building on this algorithm, we devise a practical approach with limited computational information and handoff overheads. We use detailed simulations to show that our approach is indeed near-optimal and provides substantial gains both to tenants (in terms of capacity savings) and end users (in terms of improved performance).

Resource allocation in multi-operator scenarios requires an estimate of the tenants' traffic needs. This is necessary in the scenario where a Mobile Network Operator (MNO) owns the Radio Access Network (RAN) and many Mobile Virtual Network Operators (MVNOs) act as resellers of their host network's capacity under their own brands, to their own customers. In such scenarios, the forecasted MVNO traffic is the basis for providing resources suitable with the corresponding MVNOs demand. To that end, the dynamic provision of resources among MVNOs should be performed in flexible, short-term time scales. In this paper, we effectively address this issue by integrating the capacity broker into the 3rd Generation Partnership Project (3GPP) network management architecture using the minimum set of enhancements. In addition, to fully exploit its capabilities, we propose the Multi-tenant Slicing (MuSli) of capacity algorithm, to allocate resources towards MVNOs in coarse time scales. MuSli considers the estimated capacity and the impact of the traffic type (i.e., guaranteed QoS and Best-Effort) in each MVNO, to provide better utilization of the host network's capacity. Our results highlight the gains in the number of served requests without compromising their service quality.

The emerging 5G systems are envisioned to support higher data volumes and a plethora of different services with diverse QoS demands. To accommodate such service requirements, a cost efficient and flexible network architecture considering different service types is desired. The adoption of C-RAN can reduce infrastructure costs especially for dense deployments while at the same time centralize and hence optimize certain operations related with the control and data plane of the associated cells. This paper investigates such C-RAN approach in the context of TDD networks enabling a cell-less experience for users residing within overlapping areas. In particular, users are allowed to utilize selected sub-frames from different cells forming, in this way, a customized cell-less frame in a flexible manner. A queueing model and analysis is provided for optimizing power control and delay targets. A simulation study shows that our cell-less proposal significantly advances the state of the art both in terms of application and system performance.

This paper presents the proof-of-concept evaluation of a Resource Aware VNF Agnostic (RAVA) NFV orchestration method that is designed to enhance the Quality of Decision (QoD) of a cloud controller by optimizing the life cycle management decisions that it takes in order to manage the resources in a cloud infrastructure (e.g., a data center). The RAVA method proposes a novel concept of deriving the affinity scores for the plurality of resource units with reference to a specific resource unit for each individual Virtual Machine (VM) instance hosting a Virtualized Network Function (VNF). This affinity score, referred to as Reference Resource Affinity Score (RRAS), will enable the cloud controller to perform precise and efficient resource tailoring or dimensioning; and hence will optimize its decisions and actions related to the management and orchestration of the virtualized resources inside the cloud infrastructure. The motivation behind proposing RAVA is to enhance the Network Functions Virtualization (NFV) Management and Orchestration (MANO) system capabilities towards the realization of a Carrier Cloud, an important vision for the future 5G architecture. The evaluation results presented in this paper are based on an OpenStack based proof-of-concept implementation of the RAVA method.

The provision of service-oriented network resource virtualization, commonly known as network slicing, is envisioned as an answer to the increasing diversity of application demands in evolving 5G mobile networks. Network slicing is helpful in isolating a specified amount of resources in order to accommodate diverse services having heterogeneous requirements that may be conflicting. In this paper, we propose a service-oriented network resource slicing scheme for a Time Division Duplex (TDD) network that, for a pre-defined time duration, forms service-specific network slices based on traffic prediction. The aim of the proposed slicing scheme is to enhance the services, Quality of Experience (QoE) and system resource utilization efficiency by introducing a new degree of flexibility upon allocating resources to different tenants. System-level simulation analysis shows that the proposed scheme improves the performance of high priority services and boosts resource utilization at negligible performance loss for low-priority traffic.

This paper proposes a conceptually novel, adaptive and future-proof 5G mobile network architecture. The proposed architecture enables unprecedented levels of network customisability, ensuring stringent performance, security, cost and energy requirements to be met; as well as providing an API-driven architectural openness, fuelling economic growth through over-the-top innovation. Not following the 'one system fits all services' paradigm of current architectures, the architecture allows for adapting the mechanisms executed for a given service to the specific service requirements, resulting in a novel service- and context-dependent adaptation of network functions paradigm. The technical approach is based on the innovative concept of adaptive (de)composition and allocation of mobile network functions, which flexibly decomposes the mobile network functions and places the resulting functions in the most appropriate location. By doing so, access and core functions no longer (necessarily) reside in different locations, which is exploited to jointly optimize their operation when possible. The adaptability of the architecture is further strengthened by the innovative software-defined mobile network control and mobile multi-tenancy concepts.

The traditional model of single ownership of the mobile network infrastructure is being challenged by the forecasted mobile data tsunami and the resulting CAPEX and OPEX costs. In this context, the sharing of network infrastructure among operators has emerged as a way to ensure operators' future cost competitiveness. While the elementary concepts related to passive network sharing are already being exploited today, active network sharing is raising in importance to enable further reduction of network expenses in a substantial and sustainable way. The work presented in this paper addresses this challenge by designing a RAN Multi- tenant cell Slicing Controller (RMSC) that allows to flexibly share the RAN resources among multiple virtual operators (tenants). Three different possible designs for the RMSC controller are proposed, ranging from a fully distributed system with no inter-base station communication to a fully centralized solution with all information available. The proposed solutions are benchmarked against a distributed static slicing solution and a centralized load balancing solution, considering realistic scenarios of uneven user location distribution per tenant. The performance results obtained indicate that the proposed RMSC schemes can significantly outperform traditional solutions for multi-tenant mobile networks.

Current IEEE 802.11 WLANs suffer from the well-known rate anomaly problem, which can drastically reduce network performance. Opportunistic relaying can address this problem, but three major considerations, typically considered separately by prior work, need to be taken into account for an efficient deployment in real-world systems: 1) relaying could imply increased power consumption, and nodes might be heterogeneous, both in power source (e.g., battery-powered versus socket-powered) and power consumption profile; 2) similarly, nodes in the network are expected to have heterogeneous throughput needs and preferences in terms of the throughput versus energy consumption tradeoff; and 3) any proposed solution should be backwards-compatible, given the large number of legacy 802.11 devices already present in existing networks. In this paper, we propose a novel framework, Self-Optimizing, Legacy-Compatible Opportunistic Relaying (SOLOR), which jointly takes into account the above considerations and greatly improves network performance even in systems comprised mostly of vanilla nodes and legacy access points. SOLOR jointly optimizes the topology of the network, i.e., which are the nodes associated to each relay-capable node; and the relay schedules, i.e., how the relays split time between the downstream nodes they relay for and the upstream flow to access points. Our results, obtained for a large variety of scenarios and different node preferences, illustrate the significant gains achieved by our approach. Specifically, SOLOR greatly improves network throughput performance (more than doubling it) and power consumption (up to 75% reduction) even in systems comprised mostly of vanilla nodes and legacy access points. Its feasibility is demonstrated through testbed experimentation in a realistic deployment.

Intercell coordination and cooperation techniques are some of the most promising approaches to increase the spectral efficiency of future wireless systems as required by the forecasted market needs. Among them, intercell coordinated scheduling (ICCS) arises as a near-term feasible solution due to its lower inter-BS communication requirements when compared to full cooperative approaches. In this paper we present our proposed Reservation Information Aware Intercell Coordinated Scheduling (RIA-ICCS) solution which considers application reservation information when constructing an interference graph for ICCS purposes. Our results shows that i) RIA-ICCS allows to significantly reduce the number of edges in an interference graph for ICCS solutions and its benefit increases as the number of mobile stations grows, i.e., when the system needs it most and ii) the reduced number of edges in the interference graph can be effectively translated to a lower blocking probability using state-of-the-art resource allocation algorithms.

Mobile operators are facing increasing energy prices to operate their networks. At the same time, the demand for broadband wireless access is steadily increasing, driven by the success of smart phones and new services like machine-to-machine communication. In this paper we propose and evaluate a novel asymmetric user assignment scheme, which enables operators to save energy, while satisfying the capacity demands. The main innovation is to separate the association of users to base stations in uplink and downlink, such that in macro/micro overlay scenarios parts of the radio access network can be switched off. Based on system-level simulations we show that our scheme enables energy savings of up to 15% and 60% over typical macro and micro cell deployments, respectively. We further discuss its technical feasibility and implications on the system design. All numerical results are obtained in accordance with the guidelines and requirements of IMT-Advanced systems.

ABSTRACT Wireless LAN is becoming a pervasive wireless access technology that can be found in almost any mobile device such as laptops, PDAs, portable game consoles and mobile phones. Each of these groups of devices have a different set of requirements according to their intended use and applications but most of them share two main requirements: QoS support to satisfy applications' demands and power saving functionality to achieve an operating time according to users' expectations. IEEE 802.11e defines two centralized solutions in order to address these problems: Hybrid Coordination Channel Access (HCCA) for QoS and Scheduled Automatic Power Save Delivery (S‐APSD) for power saving. The focus of our work in this paper is the analysis and evaluation of a proposed centralized scheduler that makes use of both aforementioned IEEE 802.11e QoS and power saving solutions. Our contributions are as follows: (i) Design and analytical modeling of a proposed centralized scheduler (DRA) that maximizes the minimum distance between the resource allocations with pseudo‐polynomial complexity, (ii) Extensive performance evaluation of the QoS and power saving benefits of theDistributionproposal (DRA) as compared to a genericGroupingone (GRA), and (iii) Evaluation of the complexity and scalability of the proposal to assess its feasibility in practice. Copyright © 2010 John Wiley & Sons, Ltd.

Admission control algorithms must ensure that, when a new QoS resource reservation is accepted, reservations already present in the system continue having their QoS guarantees honored. In this paper we consider different approaches to compute the aggregated allocated capacity in WiMAX networks and, based on their limitations, propose the E-Diophantine solution. The mathematical foundations for the designed approach are provided along with the performance improvements to be expected, both in accuracy and computational terms, as compared to three alternatives of increasing complexity. Finally, the different solutions considered are evaluated with OPNET's WiMAX simulator in a realistic scenario.

WiMAX is one of the most promising technologies to provide broadband wireless access in the near future. In this paper we identify a key element for the performance of a WiMAX network, the DL-MAP packing algorithm, which mainly determines the usage efficiency of the available radio resources and investigate potential differences that could appear between WiMAX equipment vendors in the maximum capacity of the system due to the packing approach used. Our results show that the performance of simple DL-MAP packing algorithms might be significantly outperformed by more complex ones resulting in a clear differentiation factor among manufacturers.

The integration of the wireless LAN technology in mobile devices such as cellular phones or PDAs has become a user need due to its popularity for providing high speed wireless Internet access at a low cost. Such devices though should meet users' expectations with regard to QoS, e.g., guarantee a reasonable voice quality when VoIP is used, and power saving efficiency, e.g., standby and calling times should be similar to the ones of cellular phones. IEEE 802.11e defines QoS and power saving enhancements that should allow the wireless LAN technology address users' wishes in such specific devices. Our focus is the study of the distributed power saving mechanism of 802.11e, i.e., U-APSD, as compared to the legacy 802.11 power saving mode in order to assess its suitability for solving the challenges of the upcoming mobile devices requirements. Our contributions are as follows. We provide first an overview of the U-APSD functionality. Then, we describe in detail our proposed implementation of the U-APSD mechanism, Adaptive U-APSD (AU-APSD), a generic solution that requires only information available at the MAC layer. Finally, we quantify the performance improvements that are obtained with our proposed AU-APSD implementation as compared to the legacy 802.11 power save mode.

The popularity of wireless LANs, due to their low cost provision of high speed wireless Internet access, has resulted in a strong trend toward the integration of this technology in the upcoming all-in-one mobile devices that could include, for instance, cellular, wireless LAN and personal digital assistant (PDA) capabilities. Such devices, though, require power saving mechanisms in order to guarantee a reasonable battery duration. The 802.11 standard provides a power save mode that reduces the wireless LAN technology power consumption, however, this mode can result in downlink delays (AP to station) unacceptable for the QoS of some applications, e.g., VoIP. To overcome this problem, we propose an adaptive power save mode algorithm (APSM) that adapts the data frames MAC downlink delay of a certain station according to the downlink frame interarrival time observed at the AP MAC layer. We conducted an evaluation of our proposal with respect to downlink delay, power efficiency and signaling load using the OPNET simulator and compared its performance with the 802.11 standard power save mode and two different static alternatives. The results show the effectiveness of our algorithm in providing a soft upper bound to the MAC downlink delay while significantly decreasing the power consumption and requiring a signaling load similar to that of the standard power save mode.

Mobile communication systems increasingly adopt Internet protocol solutions for transport of control and data traffic. To optimize scalability of the mobile communication infrastructure as well as to save scarce radio bandwidth and mobile energy resources, mobile devices can enter a power save mode and refrain from sending superfluous location information towards the network in case the device is idle. Such systems utilize paging to locate and reactivate mobile devices in power save mode, as well as to initiate re-establishment of routing information in the network. The well accepted wireless LAN standard IEEE802.11 supports mechanisms for power saving while a mobile terminal is associated with a particular access point. But paging control of mobile devices in power save mode beyond the scope of a single access point is not part of the standard IEEE802.11 application. In this paper, we propose a mechanism to integrate and utilize existing IEEE802.11 power save mode with an IP paging architecture and protocol without the need to modify the IEEE802.11 standard. In addition to the IP paging protocol operation, the proposal covers an appropriate addressing and identification scheme, which can be utilized for other access technologies as well. An analytical evaluation of energy and paging delay costs allows estimation of the proposed mechanism's efficiency, which might be sub-optimal for high load conditions, but appropriate to support migration scenarios towards future heterogeneous access mobile communication networks.

The substitution of ATM transport by IP in future UMTS Radio Access Networks (UTRAN) introduces several performance challenges that need to be addressed to guarantee the feasibility of its deployment. The significant increase of the overhead requires of header compression and multiplexing methods to achieve a usage of the UTRAN resources similar to the ATM one. Additionally, the specific UTRAN transport needs require the adaptation of standard packet scheduling mechanisms to efficiently use the network resources while providing the required QoS. Our results show that, applying header compression plus multiplexing techniques and taking into account the specific UTRAN synchronization requirements for QoS scheduling, very significant performance improvements can be obtained.

This paper presents a Mobile IPv6-based overlay network architecture for heterogeneous environments, designed entirely based on IPv6, that aims to be implemented seamlessly irrespectively of the supporting network infrastructure. All transmission technologies are handled at the physical and data-link layers, imposing IPv6-based protocols for all higher layer communications and signaling. The architecture builds on Mobile IPv6 including improved fast handover, and integrates quality-of-service and authentication, authorization, accounting, and charging control per user. The most critical issues of the proposed architecture, mainly related to the handover process, were subject of a performance evaluation via ns-2 simulations. Finally, a field trial of the system was implemented, overlaying part of the GEANT infrastructure between Madrid and Stuttgart, which results are presented here.

We performed a simulative evaluation of standard Mobile IPv6 via ns-2 for a 'hot spot deployment' scenario. The simulation scenario comprises four access routers and up to 30 mobile nodes that move randomly and communicate in accordance with IEEE 802.11 wireless LAN standard. The study collected the performance metrics of all mobile nodes from the system. As data traffic video, VoIP, and TCP sources were considered. The goal of the study was to obtain quantitative results of the improvements provided by HMIPv6 with respect to handoff latency, packet loss, signaling load and bandwidth per station as well as an indication of the number of users that could be accommodated depending on the traffic source. Moreover, we performed a 'stress-test' of the protocol to investigate the behavior of the protocol in extreme cases, e.g. under channel saturation conditions. In addition to the quantitative results provided, the simulations taught us insights on the protocol performance not easily gained without performing simulations. For example, we learned that i) in our scenario a low HMIPv6 signaling load reduction outside of the micro-mobility domain implies a significant increase within it, ii) under high saturation conditions we can expect a better performance of HMIPv6 in latency terms but not in packet losses or bandwidth and iii) the consideration of network coverage user unawareness impact the performance results.

We conducted a simulative evaluation of the overall performance of fast handovers for mobile IPv6 in comparison with the baseline mobile IPv6 using the network simulator ns-2 for a 'hot spot' deployment scenario. The simulation scenario comprises four access routers and up to 50 mobile nodes that move randomly and communicate in accordance with the IEEE 802.11 wireless LAN standard. The study provides quantitative results of the QoS improvements obtained by FMIPv6 with respect to handoff latency, packet loss rate and bandwidth per station. The simulation environment allowed us also to investigate the behavior of the protocol in extreme cases, e.g. under channel saturation conditions and considering different traffic sources: CBR, VoIP, video and TCP transfers. As a complementary part of the study, the signaling load costs associated to the performance improvements provided by the enhancement proposal was analysed. While some simulation remits corroborate the intention of the protocol specification, other results give insights not easily gained without performing simulations.

With weighted fair queuing, the link's bandwidth is distributed among competing flows proportionally to their weights. In this paper we propose an extension of the DCF function of IEEE 802.11 to provide weighted fair queuing in wireless LAN. Simulation results show that the proposed scheme is able to provide the desired bandwidth distribution independent of the flows' aggressiveness and their willingness to transmit. Backwards compatibility is provided such that legacy IEEE 802.11 terminals receive a bandwidth corresponding to the default weight.

The random waypoint model is a commonly used mobility model for simulations of wireless communication networks. In this paper, we present analytical derivations of some fundamental stochastic properties of this model with respect to: (a) the length and duration of a movement epoch, (b) the chosen direction angle at the beginning of a movement epoch, and (c) the cell change rate of the random waypoint mobility model when used within the context of cellular networks. Our results and methods can be used to compare the random waypoint model with other mobility models. The results on the movement epoch duration as well as on the cell change rate enable us to make a statement about the 'degree of mobility' of a certain simulation scenario. The direction distribution explains in an analytical manner the effect that nodes tend to move back to the middle of the system area.

In this paper, we propose ARME (Assured Rate MAC Extension), an extension of the IEEE 802.11 MAC protocol to provide throughput guarantees. The proposed extension relies on the distributed coordination function (DCF) with a modified algorithm for the computation of the contention window (CW). Best effort service (with no throughput guarantee) is supported by the functionality of the current 802.11 standard in such a way that legacy IEEE 802.11 terminals behave as best effort terminals in ARME. The performance of the proposed extension has been extensively evaluated through simulation; simulation results show that IEEE 802.11 devices using ARME behave well for different types of traffic and different source rates.