Given the rise in the usage of artificial intelligence models and machine learning approaches in our day-to-day lives, it has become increasingly important to explain these models to increase user trust. Hyperdimensional Computing (HDC) has been introduced as a powerful, energy-efficient algorithmic framework that is intrinsically less opaque than (deep) neural networks. Nevertheless, the possibility of explaining and interpreting the HDC-based classification model has not yet been explored explicitly. Therefore, this work proposes an explanation method and an interpretation method for the HDC-based classification model working with tabular data. The proposed methods have been successfully evaluated on three tabular data sets with a diverse number of samples, features, and classes. Their faithfulness is validated with coherence checks, the deletion and insertion metrics, and a feature ablation study. The results of the proposed explanation method align well with the well-studied LIME explanations.

In Reinforcement Learning, Unsupervised Skill Discovery tackles the learning of several policies for downstream task transfer. Once these skills are learnt, the question of how best to use and combine them remains an open problem. The General Policy Improvement Theorem (GPI) creates a policy stronger than any individual skill by selecting the highest-valued policy, generally evaluated with Successor Features. However, the GPI policy is unable to mix and combine the skills at decision time to formulate stronger plans. In this paper, we propose to adopt a model-based setting in order to make such planning possible, and formally show that a forward search improves on the GPI policy and any shallower searches under some approximation term. We argue for decision-time planning, and design a family of algorithms, GPI-Tree Search Algorithms , to use Monte Carlo Tree Search (MCTS) with GPI. These algorithms foster the skills and Q-value priors of the GPI framework to guide and improve the search, which we back up with visual intuition for the different design choices. Our experiments show that the resulting policies are much stronger than the GPI policy alone, even under approximation; they can also improve beyond the linear constraint of Successor Features.

To properly orchestrate challenging services such as those deployed for Vehicle-to-Everything (V2X) use cases, MANO systems need to be intelligent and automated. Network Function Virtualization (NFV) and Machine Learning (ML) provide opportunities for automating MANO operations, and this paper presents our MI-enhAnced Edge Service orchesTRatiOn (MAESTRO) algorithm that makes proactive ML-driven decisions for edge service relocation to ensure Quality of Service (QoS) guarantees for V2X services. Moreover, to validate the effectiveness of our proposed solution, we have performed the experimentation using real-life testbeds for high computing and smart mobility i.e., Smart Highway and Virtual Wall, located in Antwerp and Gent, Belgium. The contribution of our paper is two-fold: i) we study the interrelation between the Key Performance Indicators (KPIs) measured at the vehicle client side, and the infrastructure metrics at the edge computing nodes and ii) we propose and evaluate an ML-based quality-aware algorithm that automates edge service orchestration to decrease average latency while guaranteeing high service availability and reliability.

Cloud and edge Data-center (DC) are designed to allocate computing resources dynamically to users based on the agreed Service Level Agreement (SLA). However, the ever-increasing demand for beyond 5G services necessitates an efficient workload management. A key challenge in this regard is auto-scaling, a dynamic process that adjusts computing resources to meet fluctuating system demands, optimizing resource utilization and cost efficiency. Traditional auto-scaling algorithms, which rely on fixed thresholds or control-theory, may face limitations in modern DC which are characterized by diverse, dynamic, and multi-user workloads. In this paper, we propose a Reinforcement Learning (RL)-based controller that extends the capacity of the state-of-the-art RL-based auto-scalers to the multi-user workload scenario. We compare the proposed RL agent against the well-known Proportional-Integral (PI) controller and a Threshold (THD)-based controller in a multi-user workload scenario in terms of created Cloud-native Network Functions (CNFs) and peak latency performed in a discrete event simulator.

Automated Guided Vehicles (AGV) are omnipresent, and are able to carry out various kind of preprogrammed tasks. Unfortunately, a lot of manual configuration is still required in order to make these systems operational, and configuration needs to be re-done when the environment or task is changed. As an alternative to current inflexible methods, we employ a learning based method in order to perform directed exploration of a previously unseen environment. Instead of relying on handcrafted heuristic representations, the agent learns its own environmental representation through its embodiment. Our method offers loose coupling between the Reinforcement Learning (RL) agent, which is trained in simulation, and a separate, on real-world images trained task module. The uncertainty of the task module is used to direct the exploration behavior. As an example, we use a warehouse inventory task, and we show how directed exploration can improve the task performance through active data collection. We also propose a novel environment representation to efficiently tackle the sim2real gap in both sensing and actuation. We empirically evaluate the approach both in simulated environments and a real-world warehouse.

Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things devices and near-sensor or on-device processing. HDC is computationally less complex than traditional deep learning algorithms and achieves moderate to good classification performance. This letter proposes to extend the training procedure in HDC by taking into account not only wrongly classified samples but also samples that are correctly classified by the HDC model but with low confidence. We introduce a confidence threshold that can be tuned for each data set to achieve the best classification accuracy. The proposed training procedure is tested on UCIHAR, CTG, ISOLET, and HAND data sets for which the performance consistently improves compared to the baseline across a range of confidence threshold values. The extended training procedure also results in a shift toward higher confidence values of the correctly classified samples, making the classifier not only more accurate but also more confident about its predictions.

Road weather conditions such as ice, snow, or heavy rain can have a significant impact on driver safety. Vehicle safety technologies have a reactive nature to these conditions. In this paper, we discuss the state of our research using a vehicle fleet equipped with external sensors to enhance road weather services. We present the architecture to share data amongst stakeholders. Next, the data are investigated. Significant trends in the data can be found when the rain starts or stops using correlation and relative measurements. This is followed by an investigation of the placed sensors to ensure qualitative measurements. Lastly, we discuss a road weather model that is adapted to make use of these car sensor observations.

Next-generation mobile networks are expected to flaunt highly (if not fully) automated management. To achieve such a vision, Artificial Intelligence (AI) and Machine Learning (ML) techniques will be key enablers to craft the required intelligence for networking, i.e., Network Intelligence (NI), empowering myriad of orchestrators and controllers across network domains. In this paper, we elaborate on the DAEMON architectural model, which proposes introducing a NI Orchestration layer for the effective end-to-end coordination of NI instances deployed across the whole mobile network infrastructure. Specifically, we first outline requirements and specifications for NI design that stem from data management, control timescales, and network technology characteristics. Then, we build on such analysis to derive initial principles for the design of the NI Orchestration layer, focusing on (i) proposals for the interaction loop between NI instances and the NI Orchestrator, and (ii) a unified representation of NI algorithms based on an extended MAPE-K model. Our work contributes to the definition of the interfaces and operation of a NI Orchestration layer that foster a native integration of NI in mobile network architectures.

The plethora of heterogeneous and diversified services in 5G and beyond requires from networks to be flexible, adaptable, and programmable, i.e., to be able to correspondingly adapt to changes. As human intervention might significantly increase delays in MANagement and Orchestration (MANO) operations, automation and intelligence become imperative for orchestrating services and resources, especially the ones with stringent requirements for latency and capacity, such as Vehicle-to-Everything (V2X) services. As virtualization and Artificial Intelligence (AI) promise to mitigate those challenges towards enabling true automation in MANO operations, in this paper we present our effort towards building and fully utilizing the real-life testbeds, such as Smart Highway and Virtual Wall, located in Belgium, to conduct realistic experimentation and validation of distributed orchestration intelligence in a dynamic network such as V2X system.

As manual Management and Orchestration (MANO) of services and resources might delay the execution of MANO operations and negatively impact the performance of 5G and beyond Vehicle-to-Everything (V2X) services, applying AI in MANO to enable automation and intelligence is an imperative. The Network Function Virtualization (NFV), Software Defined Networking (SDN), and Artificial Intelligence (AI), could all together mitigate those challenges, and enable true automation in MANO operations. Thus, in this demo paper we will showcase the use of real-life testbed environments (Smart Highway and Virtual Wall, Belgium) and the Proof-of-Concept that we build to conduct realistic experimentation and validation of intelligent and distributed MANO in a dynamic network such as a V2X system.

To enable autonomous vessels to operate on inland waterways, they need to detect, track and localize objects at close range to safely navigate. We deployed current deep learning techniques to detect and track these objects. As there are no large labeled datasets of European inland waterways, we used transfer learning to overcome the lack of data. By using preexisting similar datasets, we were able to significantly decrease the required amount of labeled data from the target distribution. Furthermore, we improved the mean Average Precision from 0.461 to 0.814 by using a limited number of labeled target data samples. We estimated the relative distance of the objects based on the generated bounding boxes. The information from the camera is then combined with LiDar data to generate a top-view map of the environment which is used as input for an object-avoidance control agent. All these methods can run in real-time on the vessel with an fps of 1.83 on a 2.7GHz vCPU.

The service placement problem considers the placement of multiple connected services across a heterogeneous device network and is one of the core problems of fog computing. We discuss the complexity of this service placement problem, and propose a model for solving it using Multi-Objective Reinforcement Learning (MORL) methodologies. Using a trained neural network greatly reduces the resource consumption of the placement algorithm, making it viable for resource-constrained scenarios. Starting from state-of-the-art techniques, we develop a generic max reward formulation model and apply several MORL methodologies, which solve the placement problem in scenarios where the preference weights change. We compare the results to a baseline methodology and showcase the value of MORL on the placement problem.

Traffic Classification (TC) systems allow inferring the application that is generating the traffic being analyzed. State-of-the-art TC algorithms are based on Deep Learning (DL) and have outperformed traditional methods in complex and modern scenarios, even if traffic is encrypted. Most of the works on TC assume the traffic flows on a wired network under the same network management domain. This assumption limits the capabilities of TC systems in wireless networks since users’ traffic on one network domain can be negatively impacted by undetected users’ traffic from other network domains or detected ones but with no traffic context in a shared spectrum. To solve this problem, we introduce a novel framework to achieve TC at any layer on the radio network stack. We propose a spectrum-based procedure that uses a DL-based classifier to realize this framework. We design two DL-based classifiers, a novel Convolutional Neural Network (CNN) spectrum-based TC and a Recurrent Neural Networks (RNN) as baseline architecture, and benchmark their performance on three TC tasks at different radio stack layers. The datasets were generated by combining packet traces from real transmissions with an 802.11 standard-compliant waveform generator. Performance evaluations show that the best model can achieve an accuracy above 92% in the most demanding TC task, a drop of only 4.37% in accuracy compared to a byte-based DL approach, with micro-second per-packet prediction time, which is very promising for delivering real-time spectrum-based traffic analyzers.

Convolutional neural networks (CNNs) have accomplished magnificent performance on object classification tasks. This work introduces a novel image classification approach based on feature vector fusion of two CNN architectures using graph attention networks (GAT). In the proposed method we extract feature maps from shallow and deep layers of two CNN architectures. These extracted feature vectors are represented as nodes in a graph, and edges between nodes are constructed based on similarities between the feature vectors. The GAT is used to aggregate and fuse connected nodes based on their importance and relevance to the classification task. We believe that this approach compensates for convolution defects during feature processing when using a single CNN. This paper attempts to show that graph-based deep learning can be used to fuse two CNN architectures and not to push the state-of-the-art of image classification accuracy. Our experimental results prove that GAT can be used to fuse feature vectors resulting from CNN architectures.

The numerous applications of industrial automation have always posed many challenges for wireless connectivity. In the last decade, IEEE 802.15.4e time-slotted channel hopping (TSCH) networks have provided high reliability and low-power operation in such challenging industrial environments. Typically, TSCH networks employ one modulation at the physical layer and are thus limited by the characteristics of the chosen modulation in terms of, among others, data rate, reliability and energy efficiency. To tackle these limitations and to improve network performance and flexibility in those challenging industrial environments, this work explores the simultaneous use of multiple modulations in a TSCH network. Traditionally, TSCH relies on fixed-duration slots, large enough to send a packet of any size given the fixed data rate. In order to avoid wasting airtime when simultaneously using modulations with different data rates, we propose the concept of slot bonding. This allows the creation of different-sized bonded slots with a duration adapted to the data rate of each chosen modulation. To analyze the proposed slot bonding technique, we formally describe the TSCH slot bonding problem in terms of optimizing the packet delivery ratio while minimizing radio on time, with the inclusion of parent selection and interference avoidance. Afterward, we propose a genetic algorithm that allows us to implement the problem and find solutions heuristically. Finally, we provide insights into preferred parent selection and modulation configurations by using this heuristic approach during extensive simulation experimentation in which the scalability advantage of slot bonding over longer fixed-duration slots is also shown.

Current industrial Internet of Things (IoT) demands are calling for more flexible and programmable networks that ensure high reliability in dynamic mission-critical scenarios. Centralized software-defined networking (SDN) offers high levels of flexibility and programmability that traditional distributed IoT protocols cannot offer. However, the use of SDN in IoT is currently not really lifting off due to wireless links unreliability, excessive control overhead, and devices' limited resources. In order to reduce the impact of these issues, Whisper enables SDN-like capabilities in IoT by centrally controlling the distributed routing and scheduling planes in the IoT network (things overlay). To do so, the Whisper controller carefully sends computed messages compatible with the standardized distributed protocols already running in the network that change the default protocols' behavior. However, as many other SDN-on-IoT approaches, Whisper is currently limited to the IoT network scope and remains as yet another independent network management silo. In this article, we argue that IoT network control should be jointly coordinated by the same SDN instance that also manages the wired segments. In order to do so, we present a new fully programmable solution that shifts the Whisper scope from the edge to the core, deploying and testing such architecture in real-world large-scale testbeds. We use 6TiSCH as industrial IoT enabler and the open network operating system platform to orchestrate all network segments. Finally, we report the technical challenges, discussing the lessons learned, and demonstrating the feasibility and suitability of this Whisper-based solution to provide an efficient and programmable end-to-end control over a heterogeneous network domain.

Current Software Defined Networking (SDN) techniques allow improving network control and flexibility. However its use in IoT is not trivial because IoT networks are unreliable and highly resource-constrained. Among some of the existing solutions proposed in the literature, Whisper enables SDN-like control over the packet forwarding and cell allocation of IoT devices by injecting in the network artificial, but still standard compliant messages that alter the default protocol behavior. Since Whisper uses carefully computed routing and scheduling messages that are compatible with the distributed protocols run in the network, it reduces the overhead in the network and operates without modifying the IoT devices' firmware. However, as other SDN-on-IoT technologies, Whisper is currently limited to the IoT network scope and remains as yet another independent network management silo. In this paper we propose a new higher-level architecture that allows to fully integrate the IoT SDN network management into a network operating system, such as ONOS, by using Whisper in order to provide an integral end-to-end softwarization. We also describe the interaction between the Whisper platform and the orchestrator and test our solution with real 6TiSCH-compatible hardware in the ONOS platform. Finally, we discuss the requirements and technical challenges to fully leverage Whisper to provide an efficient and programmable end-to-end control over an heterogeneous network domain.

Due to the varying conditions in traffic and resource availability in networks nowadays, maintaining continuity of network service and satisfying QoS and QoE requirements became a challenging task. If considered in a highly diversified environment in terms of technology and administration, it gets even more complicated, and appropriate service and resource management solutions are mandatory. Thus, the aim of this paper is to present our specific perspective of the ongoing European H2020 5G-CARMEN project, addressing the importance of proactive reconfiguration of network services and their migration between different domains. Leveraging 5G technology and MEC platform, our management platform for automated low-latency-aware VNF placement and migration will enable orchestration of network services and resources across different administrative and technology domains.

Recently, the operation of LTE in unlicensed bands has been proposed to cope with the ever-increasing mobile traffic demand. However, the deployment of LTE in such bands implies sharing spectrum with mature technologies such as Wi-Fi. Several studies have discussed this coexistence problem by suggesting that LTE implements different adaptation mechanisms that allow transmission possibilities to Wi-Fi. While such adaptation mechanisms exist, they still negatively impact Wi-Fi performance, mainly due to the lack of collaboration/coordination mechanisms that inform about the co-located networks' activities. In this paper, we propose a distributed spectrum management framework that enhances the performance of Wi-Fi, as a particular case, by detecting harmful co-located wireless networks and changes the Wi-Fi's operating central frequency to avoid them. The framework is based on a Convolutional Neural Network (CNN) that can identify different wireless technologies and provides spectrum usage statistics. Experiments were carried out in a real-life testbed, and the results show that Wi-Fi maintains its performance when using our framework. This translates in an increase of at least 40% on the overall throughput compared to a non-managed operation of Wi-Fi.

Dynamic Spectrum Access allows using the spectrum opportunistically by identifying wireless technologies sharing the same medium. However, detecting a given technology is, most of the time, not enough to increase spectrum efficiency and mitigate coexistence problems due to radio interference. As a solution, recognizing traffic patterns may lead to select the best time to access the shared spectrum optimally. To this extent, we present a traffic recognition approach that, to the best of our knowledge, is the first non-intrusive method to detect traffic patterns directly from the radio spectrum, contrary to traditional packet-based analysis methods. In particular, we designed a Deep Learning (DL) architecture that differentiates between Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) traffic, burst traffic with different duty cycles, and traffic with varying rates of transmission. As input to these models, we explore the use of images representing the spectrum in time and time-frequency. Furthermore, we present a novel data randomization approach to generate realistic synthetic data that combines two state-of-the-art simulators. Finally, we show that after training and testing our models in the generated dataset, we achieve an accuracy of ≥ 96 % and outperform state-of-the-art methods based on IP-packets with DL.

Low-power wireless mesh networks provide connectivity for a wide range of applications in industrial scenarios. For many years, IEEE 802. 15.4e Time-Slotted Channel Hopping (TSCH) networks have proven their efficiency in such environments, providing high reliability and low-power operation. TSCH networks run on top of one physical (PHY) layer and are thus limited by the characteristics of the chosen PHY layer in terms of, among others, data rate, reliability and energy efficiency. To tackle these limitations and to improve network performance and flexibility in those challenging industrial environments, this work explores the simultaneous use of multiple PHYs, and more specifically multiple modulation and coding schemes (MCSs), in a TSCH network. Traditionally, TSCH relies on fixed-duration slots, large enough to send a packet of any size given the fixed data rate. In order to avoid wasting airtime when simultaneously using multiple PHYs or MCSs with different data rates, we first introduce the concept of slot bonding. This allows the creation of different-sized bonded slots with a duration adapted to the data rate of each chosen PHY. Afterwards, we formally describe TSCH slot bonding using a Mixed Integer Linear Program (MILP) model. Finally, we use this model to determine the optimal MCS configuration with a short slot frame length that causes network saturation and show the scalability advantage of slot bonding in terms of packet delivery ratio.

The combination of 5G and Multi-access Edge Computing (MEC) technologies can bring significant benefits to vehicular networks, providing means for achieving enhanced Quality of Service (QoS), and Quality of Experience (QoE) of wide variety of vehicular applications. Although beneficial in terms of latency reduction, the edge of the architecture for communication networks produces enormous heterogeneity of network services and resources. This challenge becomes even more severe when different administration domains are taken into consideration. Thus, efficient network Management and Orchestration (MANO) of network resources and services are inevitable. As ETSI provided guidelines and standardization for NFV MANO components, the MEC platform can be used to host network services, while MANO systems are in charge of network service management and orchestration. In this paper, we focus on the specific impact that the Virtualized Infrastructure Manager (VIM) has on the performance of the whole MANO system, used for management and orchestration of MEC services and resources in vehicular networks by enabling the on-demand service instantiation, and service teardown. In our testbed-based evaluation, we measured the network service instantiation and termination delays when evaluating: a) OpenStack and Amazon Web Services (AWS) as VIMs for Open Source MANO (OSM), and b) OpenStack and Docker in case of Open Baton. Such performance analysis with a strong experimental component can serve as a baseline for researchers and industry towards exploiting the opportunities that existing MANO solutions provide.

The fifth generation of mobile networks (5G) and the Software- Defined Radio Access Networks (SD- RAN) architecture envision to support lower latency, enhanced reliability, massive connectivity, and improved energy efficiency. In this context, low latency is considered crucial and Ultra-Reliable Low Latency Communication (URLLC) as one of the key enablers. Currently, IEEE 802.11 networks cannot be programmed fine-grained enough nor manage multiple networks at runtime. Besides, in such scenarios, the coarse-grained level of monitoring information has been hindering troubleshooting and management. In this paper, we present an SDN-based framework where fine-grained End-to-End (E2E) network statistics can be gathered using Inband Network Telemetry (INT) and used for network control and management. With such fine-grained network information, we show how our system can enhance the Quality of Service (QoS) delivery through slice orchestration in IEEE 802.11 Radio Access Networks (RANs).

Spectrum sharing is a reality closer than one might think. Dynamic and intelligent spectrum allocation, where different networks collaborate to optimize spectrum usage jointly, is required to overcome spectrum scarcity. Artificial Intelligence (AI) can play a major role to solve this complex problem in dynamic environments with continuously changing data requirements. A part of the problem can be solved by using smart AI-enabled flow control. Smart flow control can have a major impact on the spectrum footprint of mobile networks where it can optimize the Quality of Service for the own and neighboring networks. This paper presents the architecture and the basic principles of the dynamic spectrum footprint control based on flow prioritization of the SCATTER radio system, a wireless endto-end communication system that participated in the DARPA Spectrum Collaboration Challenge. The flow control mechanism is a policy-based framework.

Wireless networks are ubiquitous in today’s world and consist of an ever-expanding number of heterogeneous consumer devices and communication technologies. As modern devices support multiple communication technologies, efforts have been made to efficiently manage this plethora of technologies by supporting functionalities such as simultaneous usage or handovers.However, existing solutions are missing both the fine-grained control and intelligence to offer seamless inter-technology management and network optimizations. As a result, technologies operate in an isolated manner, network management is inefficient, and the requirements of users and modern applications are not being met. In contrast, we present intelligent and dynamic multi-technology network management that breaks this isolation, abstracting the connectivity decisions from the user and application level. Different contributions are made: first of all, we introduce a framework for inter-technology management that enables, among others, seamless handovers and packet-based load balancing. Next, we propose different algorithms that can be deployed on top of the novel, or existing, management solutions to increase the network-wide throughput by providing more intelligent network configurations, taking into account mobility and real-time requirements. Finally, as management approaches rely on an accurate overview of the network state, we also consider the monitoring aspect and investigate the detection of traffic patterns in the radio spectrum. Our contributions are evaluated through practical implementations in real-life prototypes.

The MAC layer of the IEEE 802.11 standard deploys a CSMA/CA protocol to regulate the access to the shared medium. Not only other IEEE 802.11 stations but also non-IEEE 802.11 devices can be a source of interference, causing collisions and, therefore, re-transmissions, leading to an increased packet latency and a decrease of throughput. As in general, the non-IEEE 802.11 devices do not employ the IEEE8 802.11 CSMA/CA protocol (in particular carrier sensing and the behavior when the medium is sensed busy), the impact of the interference they cause may lead to vital performance degradation of the IEEE 802.11 network. This impact of non-IEEE 802.11 interfering sources on the network performance has not been accurately modeled yet in literature. In this paper, we first characterize a non-IEEE 802.11 interfering source by employing an on-off process. Then we propose, based on earlier results from Bianchi, an analytical model to predict latency and throughput in a saturated as well as an unsaturated network, considering that an interfering source is present. The model utilizes a Markov chain to correctly characterize the behavior of the back-off algorithm of a tagged station in the presence of an interfering source, as well as a Quasi Birth-Death (QBD) process to model the station’s packet queue behavior. We show that we can accurately estimate the impact of non-IEEE 802.11 inference on IEEE 802.11 performance. The model is validated through a comparison with measurements in a real IEEE 802.11 network as well as with an ns3-simulation, whereby a very good agreement is achieved (a difference less than 2%).

Many Internet of Things (IoT) applications require a distributed architecture for decision making either because of a lack of a centralized system, failure-prone connectivity to a centralized system or because the imposed latency to contact such a system is too high for real-time applications. Often, these IoT applications fall in the domain of reinforcement learning (RL), e.g., autonomous robot navigation in smart factories and traffic signal control in smart cities. However, RL-based applications require a long learning time. To overcome this limitation and scale with the number of agents, parallel RL (PRL) algorithms run multiple RL agents in parallel and on distributed environments. However, deploying PRL algorithms in such environments entails a communication overhead that increases the (actual) execution time. The state-of-the-art PRL algorithms are designed for reducing the learning time while assuming no (or limited) communication overhead. In this article, we present a novel partitioning algorithm that minimizes the communication overhead in PRL running on IoT environments. To the best of our knowledge, this is the first work that focuses on solving the communication overhead of distributing PRL algorithms without requiring any a priori knowledge about the structure of the problem. The proposed algorithm intelligently combines a dynamic state partitioning strategy, which exploits the agent's exploration capabilities to build partition knowledge while learning, with an efficient mapping of agents to partitions, which reduces the communication among agents. Performance evaluations show that the proposed algorithm can achieve almost no communication among PRL agents at the converged state.

Wireless network technologies are becoming more and more popular. Because of this, important parts of the wireless spectrum become overloaded. Static spectrum allocation, which has been the norm for decades, is not suitable anymore. To maintain the high demand for spectrum and the continuous development of new wireless technologies, there is a need for an intelligent, dynamic spectrum allocation mechanism, where different network technologies collaboratively optimize the spectrum usage. New wireless network paradigms, such as Neutral Host Networks (NHNs) and private 5G, require a smart, spectrum-footprint-aware flow control algorithm to overcome the spectrum scarcity in collaborative way. This article presents a strategy, vision and flow control mechanism to implement collaboration in a Quality of Service (QoS)-driven way. The solution in this article is based on policies which may activate depending on its current and neighbor's network states. Through a flow ordering and selection strategy, these policies optimize the spectrum footprint, based on the performance and QoS-requirements of the own and surrounding networks. The proposed algorithm is tested extensively and validated on a large scale during the DARPA Spectrum Collaboration Challenge (SC2) competition. The results of the SC2 final event and intermediate scrimmages showed that the proposed approach increased the score, indicating increased inter-network collaboration was achieved.

Internet of Things (IoT)-based solutions for sport analytics aim to improve performance, coaching, and strategic insights. These factors are especially relevant in cycling, where real-time data should be available anytime, anywhere, even in remote areas where there are no infrastructure-based communication technologies (e.g., LTE and Wi-Fi). In this article, we present an experience report on the use of state-of-the-art IoT technologies in cycling, where a group of cyclists can form a reliable and energy efficient mesh network to collect and process sensor data in real-time, such as heart rate, speed, and location. This data is analyzed in real-time to estimate the performance of each rider and derive instantaneous feedback. Our solution is the first to combine a local body area network to gather the sensor data from the cyclist and a 6TiSCH network to form a multihop long-range wireless sensor network in order to provide each bicycle with connectivity to the sink (e.g., a moving car following the cyclists). In this article, we present a detailed technical description of this solution, describing its requirements, options, and technical challenges. In order to assess such a deployment, we present a large publicly available data-set from different real-world cycling scenarios (mountain road cycle racing and cyclo-cross) which characterizes the performance of the approach, demonstrating its feasibility and evidencing its relevance and promising possibilities in a cycling context for providing low-power communication with reliable performance.

The new medium access method of IEEE 802.11ah, called restricted access window (RAW), divides stations into different groups, and only allows stations in the same group to access the channel simultaneously, in order to reduce collisions and thus achieve better performance (e.g., throughput). However, the existing station grouping strategies only support homogeneous scenarios where all stations use the same modulation and coding scheme (MCS) and packet size. A surrogate model is an efficient mathematical model that represents the behavior of a complex system, trained with a limited set of labeled input-output data samples. In this article, we present a surrogate model that can accurately predict RAW performance under a given RAW configuration in heterogeneous networks. Different from the homogeneous scenario, heterogeneous networks are defined by a large number of parameters, leading to an enormous design space, i.e., the order of 10(17) possible data points. This is too big to achieve feasible training convergence. In this article, we present a novel training methodology that leads to a new design space with highly reduced size, i.e., the order of 10(5) data points. The surrogate model converges when less than 6000 labeled data points are used for training, which is only a tiny portion of the whole design space. The results show that, the relative error between model prediction and simulation results is less than 0.1 for 95% of the data points, in the areas of the design space studied. Its low complexity and high precision make the proposed model a valuable tool to develop real-time RAW optimization algorithms for heterogeneous IEEE 802.11ah networks.

An important aspect of managing multi access point (AP) IEEE 802.11 networks is the support for mobility management by controlling the handover process. Most handover algorithms, residing on the client station (STA), are reactive and take a long time to converge, and thus severely impact Quality of Service (QoS) and Quality of Experience (QoE). Centralized approaches to mobility and handover management are mostly proprietary, reactive and require changes to the client STA. In this paper, we first created an Software-Defined Networking (SDN) modular handover management framework called HuMOR, which can create, validate and evaluate handover algorithms that preserve QoS. Relying on the capabilities of HuMOR, we introduce ABRAHAM, a machine learning backed, proactive, handover algorithm that uses multiple metrics to predict the future state of the network and optimize the load to ensure the preservation of QoS. We compare ABRAHAM to a number of alternative handover algorithms in a comprehensive QoS study, and demonstrate that it outperforms them with an average throughput improvement of up to 139%, while statistical analysis shows that there is significant statistical difference between ABRAHAM and the rest of the algorithms.

In the unlicensed spectrum, many wireless technologies (e.g Wi-Fi, Bluetooth) use the same spectrum for wireless transmission. This often results in cross-technology interference effects, which are hard to address. Without new methods to manage this shared spectrum, wireless communication is increasingly challenging as too many nodes attempt at accessing the same spectrum. Collaboration between different wireless networks that use the same spectrum will be required to handle this massive amount of devices. In this paper, we present two algorithms based on Neural Networks (NNs) to demonstrate that a function approximation can accurately predict free slots in a Multiple Frequencies Time Division Multiple Access (MF-TDMA) network. By observing the spectrum, we are able to do online learning and let the corresponding NN predict the behavior of the spectrum a second in advance using our approach. We are able to reduce the number of collisions by half if the nodes from other networks are sending data following a Poisson distribution. When the nodes of the other network follow a more periodic traffic pattern, a collision reduction of factor 15 could be achieved.

In the last decade, several routing algorithms have been proposed in ad hoc wireless networks. However, most of them require either a high bandwidth, to maintain a full routing table, or suffer a high delay with packet flooding over the network, when the routes are discovered on-demand. As a solution, hybrid approaches, i.e. algorithms that combine on-demand route discovery with proactive updates of the available routes, have shown a good trade-off between low communication overhead and quality of the found routes. One of the approaches used in hybrid algorithms is Multi-Agent Reinforcement Learning (MARL), where the routing problem is addressed as a complex distributed control and learning problem. However, state-of-the-art MARL routing algorithms suffer from some limitations such as either lack of exploration or exploration at the cost of a high communication overhead, slow convergence under network dynamics, or no support for Quality of Service (QoS). In order to overcome such limitations, in this paper, we propose the Q2-Routing algorithm, which merges existing techniques in wireless routing and enhances them by using techniques from the MARL domain. Simulation results showed that the proposed algorithm is able to outperform well-known ad-hoc routing algorithms in dynamic environments under QoS constraints.

Today's electronic devices have multiple communication technologies available at any time. Currently, the application layer or the user needs to manually switch between them, depending on the networks in range. No holistic and adaptive approach exists that can manage all technologies and devices at once. To this extent, we previously proposed the inter-technology management framework ORCHESTRA. The framework is the first of its kind in providing fine-grained packet-level control across different network technologies in a network-wide manner. In this paper, we present a real-life implementation of this framework and show that it can cope well with mobility requirements of users by offering seamless inter-technology handovers.

The Restricted Access Window (RAW) mechanism proposed by IEEE 802.11ah promises to address one of the major problems of the Internet of Things (IoT): high channel contention in large-scale densely deployed sensor networks. The RAW feature allows the Access Point (AP) to divide stations into different groups, with only the stations in the same group being allowed to access the channel simultaneously. Existing station grouping strategies only support homogeneous scenarios, where all sensor stations have the same fixed data transmission interval, modulation and coding scheme (MCS) and packet size. In this paper, we present two contributions to address this issue. First, a surrogate model that predicts RAW performance given specific network conditions and RAW configuration parameters. It is fast to train and can be solved in real-time. Second, the Model-Based RAW Optimization Algorithm (MoROA), which uses the surrogate model to determine the optimal RAW configuration in real-time, for heterogeneous stations and dynamic traffic. We compare the accuracy of our surrogate model to simulation results. Performance of MoROA is compared to existing RAW optimization algorithms and traditional 802.11 channel access methods. The results shows that the trained surrogate model can accurately predict RAW performance with a relative error less than 7% and 10% for 95% and 98% of the RAW configurations respectively. MoROA achieves a throughput up to twice as high as traditional 802.11 channel access functions in dense heterogeneous networks.

Modern connected devices are equipped with the ability to connect to the Internet using a variety of different wireless network technologies. Current network management solutions fail to provide a fine-grained, coordinated, and transparent answer to this heterogeneity, while the lower layers of the OSI stack simply ignore it by providing full separation of layers. To address this, we propose the ORCHESTRA framework to manage the different devices in heterogeneous wireless networks and introduce capabilities such as packet-level dynamic and intelligent handovers (both interand intra-technology), load balancing, replication, and scheduling. The framework is the first of its kind in providing a fine-grained packet-level control across different technologies by introducing a fully transparent virtual medium access control layer and an software-defined networking-like controller with global intelligence. Furthermore, we present a novel optimization problem formulation that can be solved to optimally configure the network. We provide a thorough evaluation through simulations and a prototype implementation. We show that our framework enables, in a real-life setting, transparent and realtime inter-technology handovers and that coordinated load balancing can double the network-wide throughput across different scenarios.

Today's local area networks consist of an ever-expanding number of heterogeneous consumer devices and communication technologies. Despite supporting multiple technologies, those devices tend to connect to the Internet using a single technology, based on predefined priorities. This static behavior does not allow the network to unlock its full potential, which becomes increasingly more important as the quality of service (QoS) requirements of services grow. Moreover, existing approaches make use of theoretical models that assume, unrealistically, full knowledge of the network. To this extent, we present a multi-technology flow-management load balancing framework that dynamically re-routes traffic through heterogeneous networks, in order to maximize the global throughput, based on changing network conditions and QoS demands. Along a problem formulation, we focus on the estimation of wireless and dynamic network characteristics and provide a thorough evaluation through simulations and a prototype implementation. We show that our framework is indeed capable of responding to dynamic network events in real-time and offers an increased overall throughput by optimally using the network's capacity. This results in a throughput increase of around 20 % on average.

Network function (NF) virtualization is a promising way for service providers to improve configurability of the offered network services. First, NFs and their corresponding flows can be embedded in the substrate network in an automated way. Second, the modularity offered by the description of a service as a composition of NFs and their interconnecting virtual links, enables tuning of the service's logical structure. A major challenge with respect to the management of these environments is the placement of service requests in the physical infrastructure, comprising NFs that can only be instantiated on particular hosts, due to latency, legislation, or hardware-related constraints. These location constraints are known to complicate the resource allocation. This paper proposes two service placement algorithms with better coordination between the composition and embedding phases. We formulate the combined service embedding and chain composition problem as an integer linear program and then, propose a fast heuristic based on greedy chain selection that iteratively adds virtual NF chains to the composition and embeds them at the same time. Simulation experiments show that the proposed cross-layer optimization can significantly increase the acceptance ratio and reduce the embedding cost.

Current mobile consumer devices are equipped with the ability to connect to the Internet using a variety of heterogeneous wireless network technologies (e.g., Wi-Fi and LTE). These devices generally opt to statically connect using a single technology, based on predefined priorities. This static behavior does not allow the network to unlock its full potential, which becomes increasingly more important as the requirements of services, in terms of for example throughput and reliability, grow. Multipath TCP (MPTCP) is a solution that allows the simultaneous use of multiple network interfaces. However, it does this uncoordinated for a single connection between two endpoints. Therefore, this paper proposes a Software-Defined Networking (SDN) architecture to enable coordinated multi-path routing across the several networks for mobile devices. Moreover, we propose a novel weighted MPTCP scheduler that allows the transmission of certain controllable percentages of data per network interface. The proposed idea is evaluated through a real-life prototype implementation with a smartphone.

Cloud providers rely on fault-tolerance mechanisms to realize high-availability services on best-effort infrastructure. Service replication limits the data-loss caused by failure, at the expense of additional operational costs. Recently, with the advent of Mobile Edge Computing, cloud environments are becoming increasingly heterogeneous and dynamic, by the incorporation of (very) unreliable and resource-constrained devices. In this paper, we investigate how to devise an economically viable replication strategy, for a given service on a particular cloud environment. Previous work either focused on finding replication strategies for stateless services, ignoring recovery processes and correlated failures, or considered system dynamics, while lacking Service Level Agreement (SLA)-awareness. We approach the replica management problem as a run-time revenue maximization problem. Our proposed Dynamic Programming (DP) algorithm can generate the optimal replication strategy over the application lifetime. Through extensive simulations, we show that our algorithm significantly improves provider revenue over a wide range of cloud- and SLA-conditions, and adapt its strategy to evolving operating conditions. The results show that coupling dynamic failure models with SLA-awareness can lead to profitable replication strategies, even in cases where providers currently turn a loss.

Since its introduction in 2012, telecommunications operators have been applying the Network Function Virtualization principle to their core infrastructure, leading to more agile and cost-efficient deployments. While these Virtualized Network Functions (VNFs) are traditionally implemented using Virtual Machines (VMs), efforts are starting to shift to containerized VNF implementations, further improving agility and cost-efficiency. Furthermore, telecom applications often require extreme networking performance in terms of throughput and latency. While research has shown that containers outperform VMs on this front, it is currently unclear how the choice of container provider influences network performance. In this paper we compare the networking performance of Linux container implementations Docker, rkt and LXC. Throughput and latency are evaluated for single-host host, bridge (or NAT) and macvlan network configurations. This is, to the best of our knowledge, the first comparison featuring all three major Linux container implementations. We show that LXC performs best, with Docker and rkt showing throughputs of respectively up to 35 % and 58 % lower. Of the considered networking implementations, the macvlan network performs best. While it experiences a significant performance degradation when many containers are chained together, a single container using macvlan can outperform even a bare metal implementation when enough CPU resources are available.

Wi-Fi network roaming is the act of moving a wireless device from one Wi-Fi access point (AP) to another Wi-Fi AP. In urban environments, where APs are densely deployed, users would greatly benefit from roaming between these APs. Standards for Wi-Fi-network roaming have been developed (e.g. IEEE 802.11r), but are rarely implemented. The absence of a widely used standard leads to device-dependent roaming mechanisms, which brings numerous disadvantages. 5G-EmPOWER is an example of a framework that brings the Software-Defined Networking (SDN) paradigm to wireless networks. The framework solves the problem of network roaming by allowing users to connect to their own unique virtual AP and managing their connection to the WAN behind the scenes. This allows the 5G-EmPOWER controller to seamlessly handover users from one physical AP to another. Currently, a single physical controller manages the 5G-EmPOWER control plane. The use of a single system over a distributed system has known disadvantages (e.g. greater cost, single point of failure). In this paper, we present DiMob, which distributes the SDN control plane among multiple controllers. We show that DiMob maintains a seamless handover, while offering the advantages of a distributed system. We demonstrate, for example, that adding an additional node can save approximately 30 % in CPU usage for each controller.

Local area networks (LANs) are employed by a plethora of heterogeneous consumer devices, equipped with the ability to connect to the Internet using a variety of different wireless network technologies. Existing solutions and the lower layers of the OSI stack are unfit to cope with this heterogeneity. For instance, dynamical inter-technology switching is user-of application-based. We propose the ORCHESTRA framework to manage the different devices in heterogeneous wireless local area networks (WLANs) and introduce capabilities such as packet-level dynamic and intelligent handovers (both inter- and intratechnology), load balancing, replication, and scheduling. The framework consists of a controller that is capable of communicating with both existing Software-Defined Networking (SDN) and Network Function Virtualization (NFV) controllers and with devices containing a newly introduced virtual Medium Access Control (MAC) layer. We show that the virtual MAC enables transparent and real-time inter-technology handovers and that our solution scales up to two thousands of clients.

The popularity of the IEEE 802.11 (Wi-Fi) standard has resulted in a plethora of hotspot deployments. While home hotspots offer high and consistent performance, at large-scale events such as conferences and festivals, Wi-Fi performance is often poor and highly fluctuating. There are several factors explaining this increased difficulty: the required scale, the complexity of backhaul network topologies, the density of devices connected to the access point (AP), and the interference caused by both people and radio frequency (RF) equipment. While these factors are all known to degrade the performance of public hotspots, little is known about the actual performance of IEEE 802.11 at large-scale events. In this paper, we present the results of quantitative Wi-Fi performance measurement study undertaken at a music festival with 80,000 visitors over a geographical area of 0.3 square kilometres. Two separate networks were constructed for this study. The first was an IEEE 802.11n-based wireless mesh consisting of 37 devices in 15 nodes working as a network backhaul and the second an IEEE 802.11n/ac-based public hotspot that was accessible by the festival goers. We characterise the performance of the wireless spectrum and illustrate the impact of interference factors such as crowds and RF equipment. Finally, we report on the results of the deployment of a public hotspot at the festival, focusing more on application-layer metrics parameters such as user experience and session statistics. The results show that the interference at such events is so high that adaptations to the protocol configuration are needed to improve performance.

The current local area networks (LANs) are occupied by a large variety of heterogeneous consumer devices, equipped with the ability to connect to the Internet using a variety of different network technologies (e.g., Ethernet, 2.4 and 5GHz Wi-Fi). Nevertheless, devices generally opt to statically connect using a single technology, based on predefined priorities. This static behaviour does not allow the network to unlock its full potential, which becomes increasingly more important as the requirements of services, in terms of latency and throughput, grow. In this paper we present a real-life SDN-based implementation of our previously proposed algorithm that addresses this problem.

Today's local area networks (LANs) consist of a plethora of heterogeneous consumer devices, equipped with the ability to connect to the Internet using a variety of different network technologies (e.g., Ethernet, Power-Line, 2.4 and 5GHz Wi-Fi). Nevertheless, devices generally opt to statically connect using a single technology, based on predefined priorities. This static behaviour does not allow the network to unlock its full potential, which becomes increasingly more important as the requirements of services, in terms of latency and throughput, grow. To address this issue, we present a load balancing algorithm that dynamically selects a suitable interface and path through the network for each flow, based on service requirements, bandwidth availability and current link quality. The goal of the algorithm is to find an optimal path configuration for all the flows across the network that maximizes the global throughput. It dynamically adapts to changing network conditions, the arrival and departure of flows and link failures. The problem is formulated as a Mixed Integer Linear Program (MILP) and its solution, as well as that of a faster heuristic algorithm, is extensively tested in a series of ns-3 simulations with different network topologies and flow configurations. We differentiate from existing work by estimating flow rates and dynamic network conditions using real-time monitoring information, taking into account the shared medium of wireless networks and the specific fairness behaviour of TCP. Results show an increase in throughput up to 70% in heterogeneous LANs under dynamic network conditions.

IEEE 802.11 (Wi-Fi) networks' popularity has boomed in recent years and their presence is continuously increasing. More and more large-scale networks are being deployed, consisting of a large number of access points. In these networks, the handover process has proven to be very challenging. In standard Wi-Fi, the client is responsible for making the handover decision and the access point plays no role in it. This can lead to several issues such as short stays, oscillating behaviour and poor overall connectivity. In this paper, we propose a way to shift the handover process from client to access point, without requiring any modification to the client itself. By using network virtualization, we are able to perform proactive and transparent handovers, steered by a centralized controller. This allows us to exploit valuable information such as the clients' distance from all available access points, leading to a better handover process. In this paper, we present several distance aware handover algorithms. The results show that we are able to improve the handover algorithm using this information by reducing the number of handovers and avoiding unnecessary ones. We were able to reduce the throughput penalty during a handover by 50% which leads to a more seamless handover process.

Network function virtualization (NFV) and software defined networking (SDN) have been proposed to increase the cost-efficiency, flexibility, and innovation in network service provisioning. This is achieved by leveraging IT virtualization techniques and combining them with programmable networks. By doing so, NFV and SDN are able to decouple the network functionality from the physical devices on which they are deployed. Service function chains (SFCs) composed out of virtual network functions (VNFs) can now be deployed on top of the virtualized infrastructure to create new value-added services. Current NFV approaches are limited to mapping the different VNF to the physical substrate subject to resource capacity constraints. They do not provide the possibility to define location requirements with a certain granularity and constraints on the colocation of VNF and virtual edges. Nevertheless, many scenarios can be envisioned in which a service provider (SP) would like to attach placement constraints for efficiency, resilience, legislative, privacy, and economic reasons. Therefore, we propose a set of affinity and anti-affinity constraints, which can be used by SP to define such placement restrictions. Furthermore, a semantic SFC validation framework is proposed that allows the virtual network function infrastructure provider (VNFInP) to check the validity of a set of constraints and provide feedback to the SPs. This allows the VNFInP to filter out any non-valid SFC requests before sending them to the mapping algorithm, significantly reducing the mapping time.

HTTP Adaptive Streaming (HAS) has become the de facto standard technology for the delivery of video streaming services. Current adaptation heuristics for HAS focus on the selection of the optimal quality representation to be delivered from a single server. However, many content providers use multiple content servers storing replicas of the segmented video or are deployed over Content Delivery Networks (CDNs). Hence, the problem is not limited to selecting the optimal quality but also consists in requesting the segments from the best performing video server. In this paper a dynamic server selection strategy is proposed that enables the streaming client to select the optimal video delivery server. The proposed mechanism allows any quality adaptation algorithm to be plugged into it. The selection algorithm uses probability-based search strategies to explore the search space of available servers and to gain insights in their characteristics. This prevents the selection strategy to end up in a local optimum. To avoid buffer starvations, the exploration behavior is dependent on the current buffer filling. The proposed approach allows to achieve a Quality of Experience (QoE) that is within 25% of the optimum for which the client has a priori knowledge of the server characteristics.

Video streaming services have continuously gained popularity over the last decades, accounting for about 70% of all consumer Internet traffic in 2016. All of these video streaming sessions have strict delivery deadlines in order to avoid playout interruptions, detrimentally impacting the Quality of Experience (QoE). However, the vast majority of this traffic uses TCP at the transport layer, which is known to be far from minimizing the number of deadline-missing streams. By introducing deadline-awareness at the transport layer, video delivery can be optimized by prioritizing specific flows. This paper proposes a deadline-aware congestion control mechanism, based on a parametrization of the traditional TCP New Reno congestion control strategy. By taking into account the available deadline information, the modulation of the congestion window is dynamically adapted to steer the aggressiveness of a considered stream. The proposed approach has been thoroughly evaluated in both a video-on-demand (VoD)-only scenario and a scenario where VoD streams co-exist with live streaming sessions and non-deadline-aware traffic. It was shown that in a video streaming scenario the minimal bottleneck bandwidth can be reduced by 16% on average when using deadline-aware congestion control. In coexistence with other TCP traffic, a bottleneck reduction of 11% could be achieved.

Network Function Virtualization (NFV) is set to disrupt the current networking ecosystem by turning vertically-integrated middleboxes into software modules running on general purpose virtualized platforms. NFV will play a key role in future wireless and mobile networks where significant cost reductions can be obtained by virtualizing different layers and functions of the radio access and core network. Such goal raises several challenges in terms of both functional decomposition of the radio nodes and for the management and orchestration of the resulting network. In this work we present Scylla a high-level declarative language for programming network functions that allows programmers to implement per-flow custom packet processing. We also introduce a set of programming abstractions modeling the fundamental aspects of VNF orchestration. Finally, we present a proof-of-concept Controller and an SDK implementing the proposed abstractions.

IEEE 802.11ah is a new Wi-Fi draft for sub-1Ghz communications, aiming to address the major challenges of the Internet of Things (IoT): connectivity among a large number of power-constrained stations deployed over a wide area. The new Restricted Access Window (RAW) mechanism promises to increase throughput and energy efficiency by dividing stations into different RAW groups. Only the stations in the same group can access the channel simultaneously, which reduces collision probability in dense scenarios. However, the draft does not specify any RAW grouping algorithms, while the grouping strategy is expected to severely impact RAW performance. To study the impact of parameters such as traffic load, number of stations and RAW group duration on optimal number of RAW groups, we implemented a sub-1Ghz PHY model and the 802.11ah MAC protocol in ns-3 to evaluate its transmission range, throughput, latency and energy efficiency in dense IoT network scenarios. The simulation shows that, with appropriate grouping, the RAW mechanism substantially improves throughput, latency and energy efficiency. Furthermore, the results suggest that the optimal grouping strategy depends on many parameters, and intelligent RAW group adaptation is necessary to maximize performance under dynamic conditions. This paper provides a major leap towards such a strategy.

Recently, video-on-demand (VoD) streaming services like Netflix and Hulu have gained a lot of popularity. This has led to a strong increase in bandwidth capacity requirements in the network. To reduce this network load, the design of appropriate caching strategies is of utmost importance. Based on the fact that, typically, a video stream is temporally segmented into smaller chunks that can be accessed and decoded independently, cache replacement strategies have been developed that take advantage of this temporal structure in the video. In this paper, two caching strategies are proposed that additionally take advantage of the phenomenon of binge watching, where users stream multiple consecutive episodes of the same series, reported by recent user behavior studies to become the everyday behavior. Taking into account this information allows us to predict future segment requests, even before the video playout has started. Two strategies are proposed, both with a different level of coordination between the caches in the network. Using a VoD request trace based on binge watching user characteristics, the presented algorithms have been thoroughly evaluated in multiple network topologies with different characteristics, showing their general applicability. It was shown that in a realistic scenario, the proposed election-based caching strategy can outperform the state-of-the-art by 20% in terms of cache hit ratio while using 4% less network bandwidth.

HTTP Adaptive Streaming (HAS) is quickly becoming the de facto standard for video streaming services. In HAS, each video is temporally segmented and stored in different quality levels. Rate adaptation heuristics, deployed at the video player, allow the most appropriate level to be dynamically requested, based on the current network conditions. It has been shown that today’s heuristics underperform when multiple clients consume video at the same time, due to fairness issues among clients. Concretely, this means that different clients negatively influence each other as they compete for shared network resources. In this article, we propose a novel rate adaptation algorithm called FINEAS (Fair In-Network Enhanced Adaptive Streaming), capable of increasing clients’ Quality of Experience (QoE) and achieving fairness in a multiclient setting. A key element of this approach is an in-network system of coordination proxies in charge of facilitating fair resource sharing among clients. The strength of this approach is threefold. First, fairness is achieved without explicit communication among clients and thus no significant overhead is introduced into the network. Second, the system of coordination proxies is transparent to the clients, that is, the clients do not need to be aware of its presence. Third, the HAS principle is maintained, as the in-network components only provide the clients with new information and suggestions, while the rate adaptation decision remains the sole responsibility of the clients themselves. We evaluate this novel approach through simulations, under highly variable bandwidth conditions and in several multiclient scenarios. We show how the proposed approach can improve fairness up to 80% compared to state-of-the-art HAS heuristics in a scenario with three networks, each containing 30 clients streaming video at the same time.

The growing popularity of over the top (OTT) video streaming services has led to a strong increase in bandwidth capacity requirements in the network. By deploying intermediary caches, closer to the end-users, popular content can be served faster and without increasing backbone traffic. Designing an appropriate replacement strategy for such caching networks is of utmost importance to achieve high caching efficiency and reduce the network load. Typically, a video stream is temporally segmented into smaller chunks that can be accessed and decoded independently. This temporal segmentation leads to a strong relationship between consecutive segments of the same video. Therefore, caching strategies have been developed, taking into account the temporal structure of the video. In this paper, we propose a novel caching strategy that takes advantage of clients announcing which videos will be watched in the near future, e.g., based on predicted requests for subsequent episodes of the same TV show. Based on a Video-on-Demand (VoD) production request trace, the presented algorithm is evaluated for a wide range of user behavior and request announcement models. In a realistic scenario, a performance increase of 11% can be achieved in terms of hit ratio, compared to the state-of-the-art.

In recent years a lot of new consumer devices have been introduced to the home network. Modern home networks usually consists of multiple heterogeneous communication technologies such as Ethernet, Wi-Fi and power-line communications. Today, the user has to manually decide which transmission technology to use as there is no automated optimization across technologies. Load balancing algorithms can improve overall throughput while redundant links also provide the opportunity to switch flows in case of link failures. Current standards either lack real implementation in consumer devices or do not have the flexibility to support all necessary functionality towards creating a convergent hybrid home network. Therefore, we propose an alternative way by using Software-Defined Networking techniques to manage a heterogeneous home network. In this paper we specifically evaluate the ability of OpenFlow-enabled switches to perform link switching both under normal conditions and in case of link failures. Our results show that SDN-based management can be used to improve heterogeneous home networks by utilising redundant links for flow rerouting. However, they also show that improvements are still needed to reduce downtime during link failure or rerouting in case of TCP traffic.

The Internet of Things (IoT) has inspired a myriad of real-time applications, such as robotics and human-machine interaction. Many IoT applications have significant computational requirements, while at the same time they demand very low latencies. The cloud can provide the needed resources on-demand, however often fails to meet these timing requirements. Low response time can only be realized by having computational infrastructure in close vicinity. Therefore we investigate to what extent the cloud can be extended in the direct wireless surroundings of the IoT devices. This environment is highly heterogeneous as it comprises a wide variety of devices, connected using a plethora of technologies (both wired and wireless). A direct implication is that, compared to traditional cloud infrastructure, many of those nodes and links are likely to fail. We propose an application placement that can overcome failure-related challenges. We demonstrate that availability-awareness can increase the number of applications that can be hosted simultaneously by 132%. Furthermore we find that an additional increase of 54% can be realized through redundant provisioning of resources.

The popularity of multimedia services offered over the Internet have increased tremendously during the last decade. The technologies that are used to deliver these services are evolving at a rapidly increasing pace. However, new technologies often demand updating the dedicated hardware (e.g., transcoders) that is required to deliver the services. Currently, these updates require installing the physical building blocks at different locations across the network. These manual interventions are time-consuming and extend the Time to Market of new and improved services, reducing their monetary benefits. To alleviate the aforementioned issues, Network Function Virtualization (NFV) was introduced by decoupling the network functions from the physical hardware and by leveraging IT virtualization technology to allow running Virtual Network Functions (VNFs) on commodity hardware at datacenters across the network. In this paper, we investigate how existing service chains can be mapped onto NFV-based Service Function Chains (SFCs). Furthermore, the different alternative SFCs are explored and their impact on network and datacenter resources (e.g., bandwidth, storage) are quantified. We propose to use these findings to cost-optimally distribute datacenters across an Internet Service Provider (ISP) network.

Development and continuous operation of network management systems is a major challenge to future networks, where a large number of semi-independent devices jointly try to realize a working network. This work considers network testbed management, and more specifically on testbed management software for community networks. Because of the inherently unstructured and chaotic nature of community networks, managing components inside a community network with a frequently varying and unpredictable performance is particularly challenging. This paper focuses on the verification of community network testbed control software which has to cope with these challenges. We show how the application of a container-based unit testing approach has a positive impact on development efforts and testbed stability.

Community Wireless Networks are an emerging networking model, offering people the opportunity to build and manage their own network without being dependent on telecom operators. The strength of this type of networks lies in the involvement of the whole community, as each person benefitting from the community wireless network somehow contributes to the design, deployment and maintenance of the network. This model has resulted in large community wireless networks growing all over the world, connecting people in the local communities to each other and the Internet. Because of the rising popularity and demonstrated success, researchers are also becoming more interested in community networks. This paper presents guidelines and experiences from creating an outdoor testbed targeted at community wireless networks, based on experience and feedback from community network members.

Cloud environments face a growing demand for application hosting, and applications consisting of multiple data-sources and storage components. The need to ensure service level agreements for these types of applications creates important challenges for cloud infrastructure providers. The main contribution of this paper is an optimal cost-effective model and two algorithms to map component-based data oriented applications to cloud platforms. The first algorithm is based on an Integer Linear Programming formulation and minimizes an objective function, taking into account the capacities of the available nodes and links, as well as the customer requirements. This algorithm is able to obtain the optimal solution, but shows a limited scalability. For this reason a heuristic algorithm is designed to solve the scalability issue. The experimental results thoroughly compare the execution times and obtained node usage for both algorithms.

Over the past decades, the importance of multimedia services such as video streaming has increased considerably. Since streaming protocols such as Real Time Streaming Protocol (RTSP) and Real Time Transport Protocol (RTP) require server-side bit-rate adaptation schemes, they are not ideally suited to deal with highly heterogeneous and dynamically changing network conditions. Therefore, research shifted towards client-side adaptation schemes, requiring significantly less investments in server-side infrastructure. HTTP Adaptive Streaming (HAS) is now becoming omnipresent in video streaming services due to many advantages offered by HTTP-based streaming: reliable transmission over TCP, reuse of existing caching infrastructure and compatibility with NATs and firewalls. In HAS, the video content is split temporally into segments which are encoded at different quality rates. The client side heuristic decides at which quality rate each segment should be downloaded, based on measured network statistics, buffer filling level and device characteristics. Traditionally, Advanced Video Coding (AVC) is used to encode the different segments, introducing a significant amount of redundancy across quality representations. Scalable Video Coding (SVC) can cope with these issues of content redundancy by creating dependencies between the base and enhancement layers. Adopting SVC in HAS significantly improves caching and bandwidth efficiency at the server side. Another advantage of SVC, is the ability to gradually upgrade the quality of the video by downloading additional video layers.

HTTP Adaptive Streaming (HAS) has several advantages compared to traditional streaming protocols, such as easy traversal of firewalls and reuse of widely deployed HTTP infrastructure. HAS content is temporally segmented, and encoded at different quality representations, allowing the video player to autonomously adapt to network conditions by adapting play-out quality between subsequent segment downloads. However, to guarantee continuous playback, current-generation HAS protocols require a large play-out buffer. This makes them ill-suited for live television, as it significantly increases the live signal delay. This paper proposes a novel HAS solution for live streaming services. A HAS video player was designed that can cope with buffers as small as 2 seconds. This obviously requires the player to more rapidly react to bandwidth changes, which was achieved by using the Scalable Video Coding (SVC) extension of the H.264 Advanced Video Coding (AVC) video codec. Moreover, an intelligent network proxy was developed that guarantees the delivery of the SVC base quality layer using Differentiated Services (DiffServ). Furthermore, a more dynamic deadline-based approach is proposed which allows the client itself to decide which segments should be prioritized based on the risk of running into a buffer starvation. This enables more efficient use of the prioritized channel, leading to less freezes and increased quality and stability. The combination of these technologies allows the video player to align its quality adaptation decisions to the available bandwidth more efficiently and completely avoid buffer starvations. The small buffer size also reduces the total live signal delay from multiple dozens to only a few seconds.

Network virtualisation is considerably gaining attention as a solution to ossification of the Internet. However, the success of network virtualisation will depend in part on how efficiently the virtual networks utilise substrate network resources. In this paper, we propose a machine learning-based approach to virtual network resource management. We propose to model the substrate network as a decentralised system and introduce a learning algorithm in each substrate node and substrate link, providing self-organization capabilities. We propose a multiagent learning algorithm that carries out the substrate network resource management in a coordinated and decentralised way. The task of these agents is to use evaluative feedback to learn an optimal policy so as to dynamically allocate network resources to virtual nodes and links. The agents ensure that while the virtual networks have the resources they need at any given time, only the required resources are reserved for this purpose. Simulations show that our dynamic approach significantly improves the virtual network acceptance ratio and the maximum number of accepted virtual network requests at any time while ensuring that virtual network quality of service requirements such as packet drop rate and virtual link delay are not affected.

HTTP Adaptive Streaming (HAS) is quickly becoming the de facto standard for Over-The-Top video streaming. In HAS, each video is temporally segmented and stored in different quality levels. Quality selection heuristics, deployed at the video player, allow dynamically requesting the most appropriate quality level based on the current network conditions. Today's heuristics are deterministic and static, and thus not able to perform well under highly dynamic network conditions. Moreover, in a multi-client scenario, issues concerning fairness among clients arise, meaning that different clients negatively influence each other as they compete for the same bandwidth. In this article, we propose a Reinforcement Learning-based quality selection algorithm able to achieve fairness in a multi-client setting. A key element of this approach is a coordination proxy in charge of facilitating the coordination among clients. The strength of this approach is three-fold. First, the algorithm is able to learn and adapt its policy depending on network conditions, unlike current HAS heuristics. Second, fairness is achieved without explicit communication among agents and thus no significant overhead is introduced into the network. Third, no modifications to the standard HAS architecture are required. By evaluating this novel approach through simulations, under mutable network conditions and in several multi-client scenarios, we are able to show how the proposed approach can improve system fairness up to 60% compared to current HAS heuristics.

In recent years, HTTP (Hypertext Transfer Protocol) adaptive streaming (HAS) has become the de facto standard for adaptive video streaming services. A HAS video consists of multiple segments, encoded at multiple quality levels. State-of-the-art HAS clients employ deterministic heuristics to dynamically adapt the requested quality level based on the perceived network conditions. Current HAS client heuristics are, however, hardwired to fit specific network configurations, making them less flexible to fit a vast range of settings. In this article, a (frequency adjusted) Q-learning HAS client is proposed. In contrast to existing heuristics, the proposed HAS client dynamically learns the optimal behaviour corresponding to the current network environment in order to optimise the quality of experience. Furthermore, the client has been optimised both in terms of global performance and convergence speed. Thorough evaluations show that the proposed client can outperform deterministic algorithms by 11–18% in terms of mean opinion score in a wide range of network configurations.

HTTP adaptive streaming (HAS) services allow the quality of streaming video to be automatically adapted by the client application in face of network and device dynamics. Due to their advantages compared to traditional techniques, HAS-based protocols are widely used for over-the-top (OTT) video streaming. However, they are yet to be adopted in managed environments, such as ISP networks. A major obstacle is the purely client-driven design of current HAS approaches, which leads to excessive quality oscillations, suboptimal behavior, and the inability to enforce management policies. Moreover, the provider has no control over the quality that is provided, which is essential when offering a managed service. This article tackles these challenges and facilitates the adoption of HAS in managed networks. Specifically, several centralized and distributed algorithms and heuristics are proposed that allow nodes inside the network to steer the HAS client's quality selection process. The algorithms are able to enforce management policies by limiting the set of available qualities for specific clients. Additionally, simulation results show that by coordinating the quality selection process across multiple clients, the proposed algorithms significantly reduce quality oscillations by a factor of five and increase the average delivered video quality by at least 14%.

The consumption of multimedia services over HTTP-based delivery mechanisms has recently gained popularity due to their increased flexibility and reliability. Traditional broadcast TV channels are now offered over the Internet, in order to support Live TV for a broad range of consumer devices. Moreover, service providers can greatly benefit from offering external live content (e.g., YouTube, Hulu) in a managed way. Recently, HTTP Adaptive Streaming (HAS) techniques have been proposed in which video clients dynamically adapt their requested video quality level based on the current network and device state. Unlike linear TV, traditional HTTP- and HAS-based video streaming services depend on unicast sessions, leading to a network traffic load proportional to the number of multimedia consumers. In this paper we propose a novel HAS-based video delivery architecture, which features intelligent multicasting and caching in order to decrease the required bandwidth considerably in a Live TV scenario. Furthermore we discuss the autonomic selection of multicasted content to support Video on Demand (VoD) sessions. Experiments were conducted on a large scale and realistic emulation environment and compared with a traditional HAS-based media delivery setup using only unicast connections.

The Internet is rapidly evolving towards a multimedia service delivery platform. However, existing Internet-based content delivery approaches have several disadvantages, such as the lack of Quality of Service (QoS) guarantees. Future Internet research has presented several promising ideas to solve the issues related to the current Internet, such as federations across network domains and end-to-end QoS reservations. This paper presents an architecture for the delivery of multimedia content across the Internet, based on these novel principles. It facilitates the collaboration between the stakeholders involved in the content delivery process, allowing them to set up loosely-coupled federations. More specifically, the Federated Resource Reservation (FedRR) algorithm is proposed. It identifies suitable federation partners, selects end-to-end paths between content providers and their customers, and optimally configures intermediary network and infrastructure resources in order to satisfy the requested QoS requirements and minimize delivery costs.

Recently, the Internet has become a popular platform for the delivery of multimedia content. However, its best effort delivery approach is ill-suited to guarantee the stringent Quality of Service (QoS) requirements of many existing multimedia services, which results in a significant reduction of the Quality of Experience. This paper presents a solution to these problems, in the form of a framework for dynamically setting up federations between the stakeholders involved in the content delivery chain. More specifically, the framework provides an automated mechanism to set up end-to-end delivery paths from the content provider to the access Internet Service Providers (ISPs), which act as its direct customers and represent a group of end-users. Driven by Service Level Agreements (SLAs), QoS contracts are automatically negotiated between the content provider, the access ISPs, and the intermediary network domains along the delivery paths. These contracts capture the delivered QoS and resource reservation costs, which are subsequently used in the price negotiations between content provider and access ISPs. Additionally, it supports the inclusion of cloud providers within the federations, supporting on-the-fly allocation of computational and storage resources. This allows the automatic deployment and configuration of proxy caches along the delivery paths, which potentially reduce delivery costs and increase delivered quality.

The proliferation of multimedia services over access networks (e.g., IPTV or network-based Personal Video Recording) has introduced important new revenue potential for network and service providers but has also complicated the management burden. As a result, today's management of multimedia networks is often too static to cope with the increasing quality requirements of multimedia services. A key point in these quality requirements is the quality as perceived by the end users, denoted as the Quality of Experience (QoE). In the thesis, we have introduced an auto-nomic management layer that optimizes the QoE of multimedia networks. We have studied several QoE optimizing techniques with respect to traffic adaptation, admission control and video rate adaptation. All these QoE optimizing techniques exhibit autonomic behavior as they continuously monitor the network to optimize their configuration and consequently optimize the QoE. Furthermore, we have investigated the coordinated deployment of these QoE optimizing techniques by focusing on the exchange of context between entities in the distributed autonomic management layer. Through extensive evaluation using both simulation and emulation on a large-scale testbed, we have shown that the proposed QoE optimizing techniques can successfully optimize the QoE of multimedia services. This QoE optimization was characterized in terms of metrics such as the number of admitted sessions and video quality.

As the requirements and scale of cloud environments increase, scalable management of the cloud is needed. Centralized solutions lack scalability and fully distributed management systems only have a limited overview of the system. One of the often-studied problems in cloud environments is the application placement problem, used to decide where application instances are instantiated and how many resources to allocate to the instances. In this paper a general approach is introduced for using centralized cloud resource management algorithms in a hierarchical context, increasing the scalability of the management system while maintaining a high placement quality. The management system itself is executed on the cloud, further increasing scalability and robustness. The proposed method uses aggregation techniques to generate input values for a centralized application placement algorithm which is run in all management nodes. Decoupling ensures management nodes can function independently. Subsequently, we compare the performance of hierarchical application placement method with that of a fully centralized algorithm. The results show that a solution, within 5% of the optimum placement when using the centralized algorithm, can be achieved hierarchically in less than 25% of the time needed for execution of the centralized algorithm.

With the advent of novel services such as IPTV and videoconferencing broadband DSL networks are facing enormous challenges. These services have strict QoS demands in terms of packet loss, jitter and delay. In an effort to meet these demands, operators introduced centralized admission control mechanisms to avoid congestion when too many session were allowed. These centralized approaches often fail to effectively manage the available resources mainly because of the bursty nature of multimedia traffic. When transmitting variable bit rate videos resources are reserved based on the peak rate of the video. This leads to under-utilisation of the network. Measurement based admission control mechanism have been proposed such as the IETF Pre-Congestion Notification (PCN) to allow better network utilisation. Each node in the PCN domain measures the network load and admits or blocks accordingly sessions at the edges of the network. Previous research proposed bandwidth metering and an autonomic rate adaptation algorithm which led to a better utilisation of the network but still introduced unnecessary bandwidth headroom caused by the variable bit rate of videos. In this paper, we propose an additional buffering step before traffic enters the PCN domain and determine configuration guidelines for the parameters. The performance of this buffering step has been evaluated in an NS-2 based simulator environment. The conducted tests show a 26.5% increase of network utilisation.

A large number of intelligent components for managing the Future Internet have been proposed recently or are currently being investigated. However, before these network components can be deployed in real-life networks, they need to be thoroughly validated through realistic and large scale experiments. Testbed facilities provide a means to set up large scale network topologies but offer only a limited functionality in managing the deployment of the experiment itself. In this paper, we propose a management framework which automates the configuration and management of network experiments. The framework focuses on the emulation of user behaviour, to obtain realistic network conditions, and features several mechanisms that allow to reduce the experiments' size both temporally (in shorter simulation time) as spatially (with fewer physical nodes).

The popularity of streaming multimedia services has greatly increased in recent years. Telco- and cable-providers have started offering a plethora of multimedia services in the access and aggregation network, including video on demand, interactive digital television, and time-shifted TV. However, these services introduce additional challenges, such as stringent time constraints, and high bandwidth requirements. To overcome these problems, we explore the advantages of delivering such multimedia content using deadline-aware scheduling and caching algorithms. These algorithms decide when to send and store which content. This enables the network to optimize bandwidth consumption and satisfy deadline constraints. The designed algorithm was evaluated and compared to classical deadline-unaware delivery protocols. This allows us to study the efficiency of the new algorithm, and identify the scenarios in which deadline-aware scheduling improves delivery of multimedia content.

Network management has suffered from increases in business, system, and operational complexity. This has been exacerbated by the heterogeneity in management data as well as the high quality requirements of multimedia services. Autonomic networking manages this growing complexity by adding intelligence inside network nodes and network management applications. While most autonomic applications simply use a control loop to monitor and configure entities, our work is aimed at building a self-governing network that is able to fulfill the requirements of current and future services. This means that management applications need a detailed and dynamic view of the contextual status of the network nodes as a whole in order to adapt their behaviour to changing context. In this paper, we propose an algorithm to semi-automatically generate filter rules based on existing information in a network management information model. These filter rules are used to determine the set of contextual data that needs to be exchanged with other nodes. The algorithm exploits the reasoning capabilities of ontologies and relies on the introduction of additional semantic relationships to achieve a fine-grained context exchange model. Large scale evaluations were conducted to characterise the performance of this ontological approach.

DSL aggregation networks are evolving to the standard platform for the delivery of multimedia services such as television and network based personal video recording. These multimedia services introduce large challenges for network operators as they are sensitive to packet loss. Therefore, admission control mechanisms are required to avoid congestion caused by allowing too many sessions. However, as multimedia services are often bursty it is not possible to reserve a fixed amount of bandwidth in the network since this policy will lead to either over-admittance or under-admittance. Recently, the IETF Pre-Congestion Notification (PCN) Working Group, proposed a measurement based admission control mechanism, where the network load is measured at each node and sessions are allowed or blocked at the edge of the network. In this paper, we extend and evaluate the PCN mechanism: we propose a new measurement algorithm for PCN, based on bandwidth metering, and determine the configuration guidelines for the parameters of both the original token bucket based approach and the novel algorithm for different network conditions and traffic types. More specifically, we study PCN's applicability on protecting VBR video services, which is currently not studied in the PCN Working Group. Furthermore, we characterise the gain of PCN in comparison to a centralised admission control mechanism.