The growing demand for computational power in cloud computing has made Graphics Processing Units (GPUs) essential for providing substantial computational capacity. Efficiently allocating GPU resources is crucial due to their high cost. Additionally, it’s necessary to considercloud environment characteristics, such as dynamic workloads, multi-tenancy, and requirements like isolation. One key challenge is efficiently allocating GPU resources while maintaining isolation and adapting to dynamic workload fluctuations. Another challenge is ensuring scheduling maintains fairness between tenants while meeting task requirements (e.g., completion deadlines). While existing approaches have addressed each challenge individually, none have tackled both challenges simultaneously. This is especially important in dynamic environments where applications continuously request and release GPU resources. This paper introduces a new dynamic GPU resource allocation method, incorporating fair and requirement-aware task scheduling. We present a novel algorithm that leverages the multitasking capabilities of GPUs supported by both hardware and software. The algorithm schedules tasks and continuously reassesses resource allocation as new tasks arrive to ensure fairness. Simultaneously, it adjusts allocations to maintain isolation and satisfy task requirements. Experimental results indicate that our proposed algorithm offers several advantages over existing state-of-the-art solutions. It reduces GPU resource usage by 88% and significantly decreases task completion times.

Programmable data planes facilitate near line-rate network traffic classification by maintaining per-flow statistics directly within the data plane memory. However, this capability introduces a significant vulnerability: spoofing-based attacks can inject substantial volumes of dummy flows, swiftly depleting limited memory resources and overwriting legitimate flow records. Consequently, this degrades the classification performance and disrupts the reliable traffic analysis. In this paper, we address the challenge of legitimate flow overwrites caused by spoofed flow explosions and propose a resilient in-network detection framework that safeguards data-plane resources without compromising inference accuracy. Our approach employs a data-driven method to identify spoofing behavior based on traffic characteristics and dynamically filters spoof-like sources using early-stage flow differentiation parameters. The control plane learns threshold values for these parameters from observed data and deploys them in the data plane to validate suspicious flows before allocating memory, thereby limiting unnecessary register usage by attack-like traffic. We prototype our solution in a P4-enabled software switch and demonstrate its effectiveness in mitigating memory exhaustion attacks, preserving classification reliability, and maintaining in-network inference performance under high-volume spoofing attacks.

Innovative holographic applications such as holographic concerts have recently emerged. They are expected to play an important role in the Metaverse. Hybrid Network Function Virtualization (NFV) / IN-Network Computing (INC) network infrastructures are needed to provision them as recently shown in the literature. INC is an emerging technology that aims to distribute the computational workload across the network by placing computational tasks on programmable devices (e.g., routers or switches). However, the integration of INC in existing infrastructures does face significant management and orchestration challenges. Although the ETSI Management and Orchestration (MANO) architectural framework designed for 5G facilitates application provisioning in networks that are NFV enabled, it lacks support for networks that are INC enabled. Therefore it is necessary to have a new MANO architecture in order to provision applications which have both NFV and INC components. This paper proposes a hybrid NFV-INC MANO architecture for provisioning holographic applications in hybrid NFV/INC environment. The proposed architecture is an extension of the ETSI NFV MANO. It will certainlyplay an important role in 6G since many applications foreseen for 6G will have the same stringent requirements as holographic applications. It is evaluated through a proof of concept prototype. The following tools were used for the prototype: Open Source MANO (OSM) and Mininet emulator.

The advent of microservice architecture enables complex cloud applications to be realized via a set of individually isolated components, increasing their flexibility and performance. As these applications require massive computing resources, graphics processing units (GPUs) are being widely used as high-speed parallel computing devices to meet the stringent demands. Although current GPUs allow application components to be executed concurrently via spatial multitasking, they face several challenges. The first challenge is allocating the computing resources to components dynamically to maximize efficiency. The second challenge is avoiding performance degradation caused by the data transfer overhead between the components. To address these challenges, we propose an efficient GPU resource management technique that dynamically allocates GPU resources to application components. The proposed method allocates resources based on component workloads and uses online performance monitoring to guarantee the application's performance. We also propose a GPU memory manager to reduce the data transfer overhead between components via shared memory. Our evaluation results indicate that the proposed dynamic resource allocation method improves application throughput by up to 134.12% compared to the state-of-the-art spatial multitasking techniques. We also show that using a shared memory results in 6x throughput improvement compared to the baseline User Datagram Protocol (UDP)-based technique.

Applications deployed in clouds are susceptible to performance degradation due to diverse underlying causes such as infrastructure faults. To maintain the expected availability of these applications, Machine Learning (ML) models can be used to predict the impending application performance degradations to take preventive measures. However, the prediction accuracy of these ML models, which is a key indicator of their performance, is influenced by several factors, including training data size, data sampling intervals, input window and prediction horizon. To optimize these data-related parameters, in this paper, we propose a surrogate-assisted multi-objective optimization algorithm with the objective to maximize prediction model accuracy while minimizing the resources consumed for data collection and storage. We evaluated the proposed algorithm through two use cases focusing on the prediction of Key Performance Indicators (KPIs) for a 5 G core network and a web application deployed in two Kubernetes-based cloud testbeds. It is demonstrated that the proposed algorithm can achieve a normalized hypervolume of 99.5% relative to the optimal Pareto front and reduce search time for the optimal solution by 0.6 hours compared to other surrogates and by 3.58 hours compared to using no surrogates.

To implement a Network Service (NS) within a Network Function Virtualization (NFV) environment, it is essential to create a sequence of connected Virtual Network Functions (VNFs), known as a VNF Forwarding Graph (VNF-FG), and then embed it onto the substrate network. The emergence of VNF decomposition as a new functional architecture allows VNFs to be broken down into smaller sub-functions, offering enhanced flexibility, resource sharing, and scalability. VNF decomposition can significantly reduce VNF embedding costs since different sub-functions can be efficiently reused by multiple network requests. However, when VNFs are decomposed into multiple sub-functions, selecting the appropriate decomposition option for each VNF and constructing the VNF-FG to embed onto the substrate network poses a significant challenge in NFV resource allocation (NFV-RA). A key challenge is identifying the optimal decomposition option among all possible choices for VNF embedding. In this paper, we introduce a cost-aware algorithm designed to address the topological decomposition of VNF-FGs, focusing on minimizing embedding costs while meeting specified service requirements. We formulate the VNF topology decomposition problem using Integer Linear Programming (ILP) to select the best decomposition option and minimize the embedding cost. Furthermore, we propose four efficient heuristics for different topologies to identify the optimal decomposition options for network embedding. Simulation results demonstrate that our proposed algorithm outperforms existing benchmarks in terms of embedding costs and achieves execution times that are up to 95% better than the SE approach.

During a Remote Robotic Surgery (RRS) session, multimodal data traffic with different requirements is initiated. In order to achieve a cost-effective deployment of such a system, it is crucial to tailor resource allocation policies based on the different quality of service (QoS) requirements of each data traffic. In this paper, we focus on resource allocation in a 5G-enabled tactile Internet RRS system using network function virtualization (NFV). In particular, we investigate the joint placement and scheduling of Virtualized Network Functions (VNFs) in a RRS system under both deterministic and dynamic settings. An integer linear program (ILP) is used to formulate the problem. Due to its high computational complexity, we first propose an efficient greedy algorithm to solve the ILP under deterministic settings. Simulation results show that our proposed algorithm achieves near-optimal performance and outperforms the benchmark solutions in terms of cost and admission rate. It can reduce cost by up to 37% and improve admission rate by up to 34% while satisfying both latency and reliability constraints. Furthermore, our results show that modeling the multimodal data traffic by multiple VNF Forwarding Graphs (VNF-FGs) with different QoS requirements achieves a significant gain in terms of cost and acceptance rate compared to modeling it by a single VNF-FG with the most stringent requirements. We then considered a dynamic environment where latency variations and traffic arrivals may occur over time. Using the principles of optimal stopping theory, we propose an adaptive dynamic scheduler that is capable of triggering recalculations of the existing optimal solution based on the observed cumulative number of traffic arrivals and latency violations without the need for predictions. Our proposed optimal scheduler minimizes the migration cost compared to other schedulers.

Applications deployed in edge cloud environments can have stringent requirements such as high throughput and high availability. However, these applications may suffer from performance degradation caused by various underlying reasons such as infrastructure-related faults. Handling application performance degradation proactively is thus critical for maintaining the application Quality-of-Service (QoS). This can be achieved through predicting application performance degradation using Machine Learning (ML) models. The performance of these ML models may degrade over time due to changes in the relevancy of features used for training the ML model for application performance degradation, i.e., feature drift. In this paper, we predict application performance degradation in edge clouds and propose a framework for adapting to the feature drifts that may occur in this environment. This framework detects a feature drift using performance of the prediction model as well as feature importance, and updates the features and adapts the prediction model to the drift considering the severity of the feature drift. We have built a proof-of-concept of our proposed framework on a Kubernetes testbed. It is demonstrated that the proposed framework can achieve up to 9.1% higher F1-score compared to Dynamic Correlation-based Feature Selection (DCFS) approach for feature drift adaptation from the literature.

Intent-Based Networking (IBN) has recently gained interest to realize intelligent cloud management systems. IBN makes cloud consumption user-friendly by allowing users to specify “what needs to be done” rather than “how it should be done”. In this paper, we address the problem of service graphs generation in IBN, while considering functional requirements derived from user intent. We propose a solution that uses a domain ontology to translate the intents into their functional requirements which are specified in terms of initial services. Then, we use a service catalog along with the initial services to generate all possible service graphs that can meet the functional requirements of the given intent. Our evaluations show that the proposed solution achieves up to 84% improvement of the execution time compared to the existing benchmarks.

The increasing demand for ultra-low latency and high bandwidth in emerging applications, such as virtual reality gaming and telesurgery, is challenging current network infrastructures. In-Network Computing (INC) has emerged as a promising solution to these challenges by optimizing network performance, reducing congestion, and minimizing both latency and bandwidth usage. As 6G networks strive to deliver unprecedented connectivity and ultra-low latency, INC is poised to become an integral part of future network architectures. However, a significant gap exists in the literature concerning a comprehensive model for describing INC components, which is crucial for effective INC provisioning. To address this gap, we propose the In-Network Computing Ontology (INCO), a domain-independent, ontology-based model designed to describe and discover INC components in a centralized repository. Our model covers both the functional and non-functional specifications of INC components. Furthermore, we introduce a semantic matchmaking algorithm that uses the INCO model to automatically discover and select the most relevant INC components from the repository based on user requests. Experimental simulations validate our approach, demonstrating the effectiveness of the semantic matchmaking algorithm, particularly regarding response time and consistency.

Amidst the emergence of immersive applications, such as, the metaverse, Virtual Reality (VR), Augmented Reality (AR), and Holography, it is clear that substantial enhancements to our existing internet infrastructure are imperative. Fulfilling the stringent Quality of Service (QoS) requirements—which include ultra-low latency, high bandwidth, and optimal frame refresh rates—hinges on the seamless integration of Communication, Caching, and Computing, collectively referred to as the "3C". These elements must be interwoven within the network fabric. Our study presents a novel approach to optimize these 3C resources within a network framework that incorporates Edge and Cloud computing, and In-Network Computing (INC). We propose a resource allocation solution tailored to networks enabled by INC. We aim to efficiently manage the distribution of Service Function Chains and the storage of relevant data for immersive applications. Given the inherent complexity of the tackled problem, we propose two solutions: a Particle Swarm Optimization (PSO)-based meta-heuristic and a simpler, yet effective, greedy heuristic. Our comprehensive simulations, grounded in realistic VR scenarios, validate the effectiveness of the proposed solution, which not only enhances resource efficiency and reduces operational costs but also guarantees high refresh rates and maintains a Motion-To-Photon latency under 22 ms.

Emerging technologies that encompass a multitude of tiny wearable devices are vulnerable to cyberattacks that can turn them into bots for launching Distributed Denial of Service (DDoS) attacks. In-network Machine Learning (ML) has emerged as a prominent solution for detecting and responding to such attacks in the shortest possible time to avoid disrupting user experience. However, the dynamic nature of attack traffic patterns necessitates continuous adaptation of conventional one-size-fits-all ML models. The manual process of identifying novel malicious traffic patterns and updating the ML model from the control plane to the network data plane is time-consuming and labor-intensive. This study aims to automate the identification of unseen malicious traffic patterns and update the ML model in programmable networks using a data-driven approach. Specifically, we determine drift detection thresholds from the baseline performance of historical (i.e., training) data and consider any deviation as anomalies in unseen (i.e., testing) data. These thresholds are continuously updated by considering changes in the data distribution and in-network inference results. We utilize an intrusion detection dataset (CIC-IDS2017) to illustrate the impact of emerging attacks on model performance degradation and the efficacy of our proposed data-driven method in mitigating these attacks. Our approach has proven effective in safeguarding against evolving DDoS attacks.

Cloud and edge computing have proposed different functionalities to enable multiple applications requiring different communication, computing, and caching (3C) resources. The upcoming futuristic applications (e.g., metaverse, holographic, and haptic communication) impose further stringent requirements (e.g., ultra-low latency, ultra-high reliability) on the infrastructure. These requirements call for a paradigm shift in the infrastructure architecture where all resource components and owners collaborate from the cloud up to the edge, creating a cloud-to-edge continuum of integrated resources. Furthermore, we argue that artificial intelligence (AI) and collaborative-based decisions are promising techniques to efficiently manage the highly complex architecture that jointly leverages 3C in the continuum. This article presents a comprehensive survey of existing research, including AI and collaborative-based studies, targeting the effective and seamless provision of 3C resources and services in the cloud-to-edge continuum. Through an extensive analysis of driving use cases, the synergy between these three main services is scrutinized to highlight its crucial role in the next-generation network infrastructures (NGNI). Finally, a discussion on the opportunities and challenges brought by integrating 3C in NGNI from different perspectives, including architectural design as well as the regulatory and business aspects, are presented.

Network Function Virtualization (NFV) is a network architecture that separates network functions from dedicated hardware, implementing them as software modules known as Virtual Network Functions (VNFs), which are executed in virtual machines or containers. NFV increases the deployment flexibility and agility within operator networks and reduces the operating and capital expenditures significantly. In NFV, migration of VNFs can significantly reduce the embedding cost. However, stringent latency requirements between VNFs can make them tightly coupled, thus hindering each VNF from being migrated individually, and resulting in poor performance. One of the main challenges in an NFV environment is therefore to migrate a cluster of VNFs to minimize the embedding cost. In this paper, we aim to solve the problem of cluster VNF migration by considering the given inter-VNF latency requirements. We formulate the VNF migration problem as an Integer Linear Programming (ILP) and present two scalable and efficient algorithms for migrating a cluster of VNFs. Through extensive experiments, we show that our proposed algorithms are highly effective. They reduce the total embedding cost by 14% compared to the existing heuristics, while being much more scalable in terms of execution time compared to the brute-force approach.

Ensuring the quality of service of applications deployed in inherently complex and fault-prone cloud environments is of utmost concern. While machine learning based fault management solutions help attain the desired reliability, they require labeled cloud metrics data for training and evaluation. Furthermore, high dynamicity of cloud environments brings forth emerging data distributions, which necessitate frequent labeling of data for model adaptation. We propose a test suite-based active learning framework for automated labeling of cloud metrics data with the corresponding cloud system state while accounting for emerging fault patterns and data or concept drifts. We have implemented our solution on a cloud testbed and introduced various emerging data distribution scenarios to evaluate the proposed framework’s labeling efficacy over known and emerging data distributions. According to our results, the proposed framework achieves about 41% higher weighted F1-score and 34% higher average Area Under the One-vs-Rest Receiver Operating Characteristic Curve (AUC) score than a system without any adaptation for emerging data distributions.

To ensure reliability and service availability, next-generation networks are expected to rely on automated anomaly detection systems powered by advanced machine learning methods with the capability of handling multi-dimensional data. Such multi-dimensional, heterogeneous data occurs mostly in today’s Industrial Internet of Things (IIoT), where real-time detection of anomalies is critical to prevent impending failures and resolve them in a timely manner. However, existing anomaly detection methods often fall short of effectively coping with the complexity and dynamism of multi-dimensional data streams in IIoT. In this paper, we propose an adaptive method for detecting anomalies in IIoT streaming data utilizing a multi-source prediction model and concept drift adaptation. The proposed anomaly detection algorithm merges a prediction model into a novel drift adaptation method resulting in accurate and efficient anomaly detection that exhibits improved scalability. Our trace-driven evaluations indicate that the proposed method outperforms the state-of-the-art anomaly detection methods by achieving up to an 89.71% accuracy (in terms of Area under the Curve (AUC)) while meeting the given efficiency and scalability requirements.

The growth of streaming data originating from Internet of Things (IoT)-based Industry 4.0 opens doors to real-time analytics of time-sensitive services. However, this ever-increasing amount of data inevitably leads to anomalies, resulting in considerable risks for time-sensitive applications. Thus, real-time detection of anomalies is critical to prevent impending failures and resolve them in time. Given that the problem is to detect application-level anomalies in real time, we develop a deep learning-based technique, which integrates time-series data inference with a Long-Short Term Memory (LSTM)-based prediction model. Our proposed method relies on a novel metric called Sequence Inconsistency Distance (SID), which determines the abnormality likelihood of a target record in real time. Our trace-driven evaluations indicate that the proposed method achieves up to a 92.6% performance gain compared to the current state-of-the-art anomaly detection methods in terms of true positive and false positive rate while meeting the essential efficiency requirements.

Network Function Virtualization (NFV) enables the decoupling of network functions from dedicated hardware to run them as software instances on commodity servers through virtualization, replacing hardware-based network functions with software-based Virtual Network Functions (VNFs). In this paper, we study the joint problem of VNF decomposition and migration to address VNF embedding in NFV resource allocation (NFV-RA). More specifically, we investigate how VNF migration and VNF decomposition can be mutually beneficial to minimize the embedding cost of network services. After presenting a novel formulation of the problem as an integer linear programming (ILP), we validate it by CPLEX and show that our joint VNF decomposition and migration approach can outperform the VNF decomposition-only approach by 20% in terms of embedding cost.

To realize a Network Service (NS) in a Network Function Virtualization (NFV) network, it is needed to form an ordered set of connected Virtual Network Functions (VNFs), commonly referred to as VNF Forwarding Graph (VNF-FG), and then embed it onto the substrate network. Forming a VNF-FG is a challenging step of NFV resource allocation (NFV-RA), especially when the VNFs can be further decomposed into different sub-functions. In this paper, we propose a cost-aware algorithm to solve the problem of topological decomposition of VNF-FGs with the main objective of minimizing the embedding cost while satisfying the given service requirements. The simulation results indicate that our proposed algorithm outperforms the existing benchmark in terms of embedding cost, while being significantly scalable compared to the brute-force approach.

The Internet of Things has become highly popular in the healthcare sector due to its benefits for patients, doctors and health authorities. In particular, the resulting sub-fields, such as medical IoT and mobile health (mHealth), have become essential in pervasive healthcare monitoring and preventing the spread of viruses. However, the massive amount of data generated by millions of IoT devices challenges the current infrastructure of cloud and edge computing, leading to high response times and unreliable results. Security and privacy concerns make these technologies particularly vulnerable to attacks. In this paper, we propose an mHealth solution based on in-network computing paradigm to provide privacy-aware, time-constrained and reliable results for IoT applications in a mobile health context. Our simulation and analytical results show that our solution satisfies mHealth applications requirements and outperforms conventional solution based on edge computing.

In-network traffic classification is a new paradigm in developing accurate and early-stage traffic classification solutions. However, despite having good accuracy, the one-fit machine learning model becomes outdated as the traffic pattern changes over time. This changing traffic pattern leads to misclassification, i.e., incorrect mapping of traffic flows to the Quality of Service (QoS) classes, resulting in a service quality violation and the imposition of a penalty. This paper proposes a profit-aware adaptive traffic classification approach in the data plane. We particularly design an economic model to measure the impact of per-class misclassification rate on the infrastructure provider's profit and use an adaptive method to handle misclassification directly inside a programmable data plane. The evaluation result shows that optimal path allocation for various traffic classes determines the targeted revenue, while improving classifier accuracy reduces penalty and maintains the maximum profit.

Next-generation networks will enable applications that are expected to be highly reliable, always available, with guaranteed Quality-of-Service (QoS). Distributed, heterogeneous edge clouds are key enablers for these applications. However, applications deployed in such networks may suffer from performance degradation caused by various infrastructure-related faults. Preventing performance degradations by predicting them using Machine Learning (ML)-based analytics and handling them proactively is thus critical for maintaining the application QoS. Predicting performance degradations can be challenging due to the diversity of the underlying causes. In this paper, we propose an automated feature selection system that uses causal-temporal analysis to find the infrastructure metrics that have causal relationships with application metrics. The selected features are further used to train ML models for predicting application performance degradation. We have validated a proof-of-concept of our system on a Kubernetes testbed, where it is demonstrated that the proposed feature selection system is up to 17.9 times faster than Recursive Feature Elimination (RFE). Using the features selected by the proposed system, the ML models could predict performance degradation with up to 12.7% higher F1-score compared to using historical values of application Key Performance Indicator (KPI) to forecast its future values.

Ensuring the quality of service of applications deployed in inherently complex and fault-prone cloud environments is of utmost concern. While machine learning based fault management solutions help attain the desired reliability, they require labeled cloud metrics data for training and evaluation. Furthermore, high dynamicity of cloud environments brings forth emerging data distributions, which necessitate frequent labeling of data for model adaptation. We propose a test suite-based active learning framework for automated labeling of cloud metrics data with the corresponding cloud system state while accounting for emerging fault patterns and data or concept drifts. We have implemented our solution on a cloud testbed and introduced various emerging data distribution scenarios to evaluate the proposed framework’s labeling efficacy over known and emerging data distributions. According to our results, the proposed framework achieves a 41% higher weighted Fl-score and a 34% higher average AUC score than a system without any adaptation for emerging data distributions.

The Industrial Internet of Things (IIoT) applications is usually associated with stringent latency requirements. An anomaly in an IIoT edge network deteriorates the performance and thus needs a real-time Root Cause Analysis (RCA) to identify the anomalous node and provide robust network infrastructure. In this paper, we present an automated, real-time RCA technique to identify the network-level root cause nodes. We use a deep learning-based approach, exploiting a Graph Neural Network (GNN) to identify root cause nodes. In GNN-RCA, we used a sampling technique and optimized aggregator function to reduce detection time. We have shown that the proposed GNNRCA method outperforms the existing benchmarks in terms of classification score and execution time.

In natural disasters and unforeseen incidents, such as floods, earthquakes and hurricanes, the traditional communication infrastructure may become unavailable to support the emergency tele-operations. Under such circumstances, deploying unmanned aerial vehicles (UAVs) as small flying base stations is seen as a promising solution to provide real-time data communication between physicians and remote robots in both up-link and down-link directions with strict transmission requirements. This paper studies the joint optimization problem of resource allocation and UAVs positioning in UAV-assisted wireless networks with the goal of minimizing the number of deployed UAVs. Since the formulated problem is a non-convex mixed-integer non-linear programming problem, efficient heuristic and genetic solutions are proposed. Simulation results show that the proposed heuristic algorithm approaches the genetic one with an important reduction in computational complexity.

By decoupling network functions from the underlying hardware, Network Function Virtualization (NFV) allows application components to be implemented as sets of Virtual Network Functions (VNFs) chained in a specific order, represented by VNF-Forwarding Graphs (VNF-FG). Fog computing is instrumental to tap into the full potential of NFV by deploying VNFs in close proximity to end-users, thus decreasing the latency significantly. However, the mobility of end-users and the fog nodes, and the limited fog nodes coverage results in service discontinuity and may increase application delay. Application component migration offers great potential to address this issue. In this paper, we propose a component migration strategy in an NFV-based hybrid cloud/fog system considering the mobility of both end-users and fog nodes. We use the Gauss-Markov mobility model and a random walk mobility model for fog nodes and end-user devices, respectively. We modeled the problem mathematically, which minimizes the aggregated weighted function of application delay and cost. However, considering the mobility of both end-users and fog nodes makes the problem quite complex. Hence, we propose a Deep Reinforcement Learning (DRL) approach to decide where and when to migrate application components and to achieve rapid decision-making. Simulation results demonstrate that the proposed scheme performs well. It offers favorable convergence and outperforms existing algorithms in terms of application delay and migration costs.

Network Function Virtualization (NFV) is a network service deployment technology that reduces capital and operational costs while yielding flexibility and scalability for service operators. As such, an ordered chain of Virtual Network Functions (VNFs), known as a VNF Forwarding Graph (VNF-FG), should be composed and embedded into the underlying substrate network. In the literature, the composition and embedding stages of VNF-FGs are usually targeted separately, which may result in undesired solutions. In this paper, we propose our joint VNF-FG composition and embedding solution, which considers the variations of service demands while also accounting for dynamic network conditions. Specifically, our proposed solution relies on deep reinforcement learning empowered by two components for estimating dynamic parameters: network resource utilization and service demand analyzers. Moreover, to efficiently explore the problem’s large discrete action space, we utilize a specialized branching Q-network and enhance it with an action filtering mechanism. We evaluated our proposed method against joint and disjoint composition and embedding heuristics as well as versus other deep learning-based methods. Our results show that the proposed method can achieve up to a 95% improvement of embedding cost compared to our benchmarks.

Dynamic and zero-touch management is expected to be the key feature of next-generation 6G networks. Network Function Virtualization (NFV) is one of the key technologies for realizing such management through software-based networks. Despite great benefits offered by NFV, deploying network services (NSs) in NFV ecosystems remains a challenge, especially for latency-sensitive NSs, as they demand stringent latency requirements and fast service provisioning. Specifically, service graphs should be embedded into an infrastructure such that these requirements are satisfied while optimizing network operator’s objectives. To cope with the scalability of optimization-based approaches, heuristic methods are known as promising alternatives to find a satisfactory solution within an acceptable execution time. However, existing VNF embedding heuristics still suffer from the so-called causality issue, which may degrade the embedding solution quality. The causality issue means that embedding decisions cannot be optimally determined before all neighboring dependencies are known. To this end, we introduce our${h}$-horizon sequential look-ahead greedy embedding framework, which provides efficient embedding and re-embedding strategies to alleviate the impact of the causality issue. The simulation results indicate that our proposed algorithm significantly improves embedding cost, compared to the existing heuristic algorithms while being much more scalable than an optimization-based approach.

In traditional Wireless Sensor Networks (WSNs) the applications are embedded in sensor nodes, making them application-oriented, domain-specific devices. Virtualization is a promising approach to allow several applications to use the physical resources of the same deployed WSN. Given that WSN sensor nodes hold limited available energy, efficient allocation and utilization of resources become important. In this paper, we study the problem of virtual network embedding in virtualized WSNs in a static setting. Our objective is to minimize the overall energy consumption by embedding the application virtual network requests onto the physical WSN substrate network. We formulate the problem as an Integer Linear Programming (ILP), accounting for latency as the service-level agreement (SLA). We then propose our so-called E2NE heuristic to achieve a near-optimal solution in a computationally efficient manner. Our results show that embedding virtual sensor networks in a virtualized WSN leads to more energy efficiency than embedding the same networks in traditional WSN without any support for virtualization. This is largely due to the fact that more physical sensors need to be activated in traditional WSN because each physical sensor can run one and only one task at a time.

Remote robotic surgery is one of the most interesting Tactile Internet (TI) applications. It has a huge potential to deliver healthcare services to remote locations. Moreover, it provides better precision and accuracy to diagnose and operate on patients. Remote robotic surgery requires ultra-low latency and ultra-high reliability. The aforementioned stringent requirements do not apply for all the multimodal data traffic (i.e., audio, video, and haptic) triggered during a surgery session. Hence, customizing resource allocation policies according to the different quality-of-service (QoS) requirements is crucial in order to achieve a cost-effective deployment of such system. In this paper, we focus on resource allocation in a softwarized 5G-enabled TI remote robotic surgery system through the use of Network Functions Virtualization (NFV). Specifically, this work is devoted to the joint placement and scheduling of application components in an NFV-based remote robotic surgery system, while considering haptic and video data. The problem is formulated as an integer linear program (ILP). Due to its complexity, we propose a greedy algorithm to solve the developed ILP in a computationally efficient manner. The simulation results show that our proposed algorithm is close to optimal and outperforms the benchmark solutions in terms of cost and admission rate. Furthermore, our results demonstrate that splitting application traffic to multiple VNF-forwarding graphs (VNF-FGs) with different QoS requirements achieves a significant gain in terms of cost and admission rate compared to modeling the whole application traffic with one VNF-FG having the most stringent requirements.

This paper investigates the use of cell-free unmanned aerial vehicles (UAVs)-assisted wireless networks and optimizes the number of deployed UAVs under quality of service and coverage constraints. The formulated problem tackles the user-UAVs association, UAVs placement, channel assignment and transmit power allocation while considering both access and backhaul networks. Since the problem is a non-convex and non-linear mixed-integer programming, low-complexity efficient greedy-based algorithmic solutions are proposed. The first one finds the UAVs' best positions and allocates resource whereas the second one guarantees the problem feasibility (i.e., all users can be satisfied) by removing the worst users. For comparison purposes, a meta-heuristic solution based on the Particle Swarm Optimization technique is proposed. Simulation results illustrate the efficiency of the proposed algorithms in terms of the number of deployed UAVs in cell-free wireless networks.

Microservices are a promising technology for future networks, and many research efforts have been devoted to optimally placing microservices in cloud data centers. However, microservices deployment in edge and in-network devices is more expensive than the cloud. Additionally, several works do not consider the main requirements of microservice architecture, such as service registry, failure detection, and each microservice's specific database. This paper investigates the problem of placing components (i.e. microservices and their corresponding databases) while considering physical nodes' failure and the distance to service registries. We propose a Components-aware Microservices Placement for In-Network Computing Cloud-Edge Continuum (CaMP-INC). We formulate an Integer Linear Programming (ILP) problem with the objective of cost minimization. Due to the problem's$\mathcal{NP}$-hardness, we propose a heuristic solution. Numerical results demonstrate that our proposed solution CaMP-INC reduces the total cost by 15.8% on average and has a superior performance in terms of latency minimization compared to benchmarks.

In-network traffic classification is a class of in-network computing that brings significant benefits to the network, i.e., the first line of defence, classification at line rate and fast reaction time. However, it is still challenging to accurately and efficiently classify Internet traffic at an early stage due to a clear trade-off between flow identification time and classification accuracy - both are competing objectives. To this end,$w$e introduce a framework that focuses on deploying an accurate network traffic classifier inside a programmable data plane that can classify the traffic at maximal speed while considering the underlying constraints of the device. Notably,$w$e move from statistical feature-based traffic analysis and argue that traffic flow can be classified using a single feature called sequential packet size information as input. We evaluate our approach by identifying different types of IoT traffic inside a programmable data plane. Our findings demonstrate that accurate and early-stage network traffic classification is achievable with minor use of networking device resources.

In edge and cloud environments, using graphics processing units (GPUs) as a high-speed parallel computing device increases the performance of compute-intensive applications. Nowadays, due to the increase in the volume and complexity of data to be processed, GPUs are more actively used in component-based applications. As a result, the sequence of multiple interdependent components is co-located on the GPU and shares GPU resources. The overall application performance in this kind of application depends on the data transfer overhead and the performance of each component in the sequence. Managing the components' competitive use of shared GPU resources faces various challenges. The lack of a low-overhead and online technique for dynamic GPU resource allocation leads to imbalanced GPU usage and penalizes the overall performance. In this paper, we present efficient GPU memory and resource managers that improve overall system performance by using shared memory and dynamically assigning portions of shared GPU resources. The portions are based on the components' workload and throughput-based performance analyzer while guaranteeing the application's progress. The evaluation results show that our dynamic resource allocation method is able to improve the average performance of the applications with the various number of concurrent components by up to 29.81% over the default GPU concurrent multitasking. We also show that using shared memory results in 2x performance improvements.

The unprecedented increase of heterogeneous devices connected to the Internet, along with tight requirements of future networks, including 5G and beyond, poses new design challenges to network infrastructures. Collaborative computing, caching and communication paradigm together with artificial intelligence have the potential to enable the Next-Generation Networking Infrastructure (NGNI) that is needed to fulfill the stringent requirements of emerging applications. In this paper, we propose the SCORING project vision for reshaping the current network infrastructure towards an NGNI acting as a truly distributed, collaborative, and pervasive system that enables the execution of application-specific tasks and the storage of the related data contents in the Cloud-Edge-Mist continuum with high QoS/QoE guarantees.

Internet of Things (IoT) applications are becoming more and more pervasive. However, they are usually embedded in the actual IoT devices. This precludes the efficient usage of IoT capabilities, particularly, sensing and actuation capabilities. Cloud computing enables the efficient usage of resources through the Infrastructure as a Service (IaaS) service model. Unfortunately, an IoT IaaS faces many challenges that the research community has not yet solved. Some examples are the heterogeneity of the devices, their orchestration, and the provision of bare-metal access. This paper proposes an architecture for a cloud IaaS in IoT settings. Modules, interfaces, and procedures are proposed. The validation is done by a proof of concept, with concrete measurements on the prototype and simulations. The prototype relies on real-life sensors (i.e., Virtenio and Advanticsys) and robots (i.e., EV3 LEGO Mindstorms).

Fault management systems that use real-time analytics based on Machine Learning (ML) help provide the reliability required in edge clouds, though they suffer from frequent changes in data distribution (concept drift) caused by highly dynamic traffic in edge clouds, requiring frequent adaptations of the ML model. We propose an automated concept drift handling framework for fault prediction in edge clouds using Reinforcement Learning (RL) to select the most appropriate drift adaptation method as well as the amount of data needed for adaptation, while considering edge cloud operator’s requirements. We implemented an edge cloud testbed and introduced infrastructure and network faults to it in the presence of abrupt and incremental concept drift. According to the obtained results, our proposed framework achieves up to 40% higher accuracy compared to a system without drift handling, and up to$13\times $and$30\times $less regret for selecting adaptation methods and amount of data, respectively, compared to other approaches.

6G networks are envisioned to be trustworthy systems that can self-maintain their reliability and service availability. The ability to automatically recognize and predict any faults or failures that occur while delivering services is a step towards realizing such systems. Real-time analytics based on Artificial Intelligence (AI)/Machine Learning (ML) techniques provides the required functionality. However, in the highly dynamic and complex environment of 6G services, the distribution of data feeding to the ML models is subject to change over time (i.e., concept drift), which makes persistent model accuracy challenging without any frequent model retraining. To address this issue, in this paper, we propose a system that predicts the faults in an edge cloud environment, where the prediction models are trained and automatically adapted to the concept drifts via Transfer Learning (TL). To present the effectiveness of our system, we implemented an edge cloud testbed and introduced CPU over-utilization and network congestion fault to it in the presence of concept drift. We used Convolutional Neural Network (CNN), Long-Short Term Memory (LSTM), and a combination of them as fault prediction models. For detecting the drifts, we have implemented and compared four drift detection methods, and we utilized three TL scenarios for adapting the model to the drift. Our results indicate the superiority of our system in maintaining a persistent accuracy in the presence of concept drift compared to a prediction system without a drift handling entity.

With the wide adoption of large-scale internet services and big data, the cloud has become the ideal environment to satisfy the ever-growing storage demand. In this context, data replication has been touted as the ultimate solution to improve data availability and reduce access time. However, replica management systems usually need to migrate and create a large number of data replicas over time between and within data centers, incurring a large overhead in terms of network load and availability. In this paper, we propose CRANE, an effiCient Replica migrAtion scheme for distributed cloud Storage systEms. CRANE complements any replica placement algorithm by efficiently managing replica creation in geo-distributed infrastructures in order to (1) minimize the time needed to copy the data to the new replica location, (2) avoid network congestion, and (3) ensure the minimum desired availability for the data. Through simulation and experimental results, we show that CRANE provides a sub-optimal solution for the replica migration problem with lower computational complexity than its integer linear program formulation. We also show that, compared to OpenStack Swift, CRANE is able to reduce by up to 60 percent the replica creation and migration time and by up to 50 percent the inter-data center network traffic while ensuring the minimum required data availability.

Remote robotic surgery, one of the most interesting 5G-enabled Tactile Internet applications, requires an ultra-low latency of 1 ms and high reliability of 99.999%. Communication disruptions such as packet loss and delay in remote robotic surgery can prevent messages between the surgeon and patient from arriving within the required deadline. In this paper, we advocate for scalable Gaussian process regression (GPR) to predict the contents of delayed and/or lost messages. Specifically, two kernel versions of the sequential randomized low-rank and sparse matrix factorization method ($\ell _{1}$-SRLSMF and SRLSMF) are proposed to scale GPR and address the issue of delayed and/or lost data in the training dataset. Given that the standard eigen decomposition for online GPR covariance update is cost-prohibitive, we employ incremental eigen decomposition in$\ell _{1}$-SRLSMF and SRLSMF GPR methods. Simulations were conducted to evaluate the performance of our proposed$\ell _{1}$-SRLSMF and SRLSMF GPR methods to compensate for the detrimental impacts of excessive delay and packet loss associated with 5G-enabled Tactile Internet remote robotic surgery. The results demonstrate that our proposed framework can outperform state-of-the-art approaches in terms of haptic data generalization performance. Finally, we assess the proposed framework’s ability to meet the Tactile Internet requirement for remote robotic surgery and discuss future research directions.

With the explosive demands for data, content delivery networks are facing ever-increasing challenges to meet end-users' quality-of-experience requirements, especially in terms of delay. Content can be migrated from surrogate servers to local caches closer to end-users to address delay challenges. Unfortunately, these local caches have limited capacities, and when they are fully occupied, it may sometimes be necessary to remove their lower-priority content to accommodate higher-priority content. At other times, it may be necessary to return previously removed content to local caches. Downloading this content from surrogate servers is costly from the perspective of network usage, and potentially detrimental to the end-user QoE in terms of delay. In this paper, we consider an edge content delivery network with vehicular nodes and propose a content migration strategy in which local caches offload their contents to neighboring edge caches whenever feasible, instead of removing their contents when they are fully occupied. This process ensures that more contents remain in the vicinity of end-users. However, selecting which contents to migrate and to which neighboring cache to migrate is a complicated problem. This paper proposes a deep reinforcement learning approach to minimize the cost. Our simulation scenarios realized up to a 70% reduction of content access delay cost compared to conventional strategies with and without content migration.

Robots are being used more and more in surgery due to the many benefits they bring (e.g. reduction of patient discomfort, precision, reliability). Remote robotic surgery is now expected to become a reality due to the emergence of 5G. Needle insertion is a crucial element of many robotic surgical procedures such as biopsies, injections, neurosurgery, and brachytherapy cancer treatment. During needle insertion in remote robotic surgery, there is still no guarantee that the surgeon will obtain the haptic feedback from the patient side within the stringent deadlines, even in 5G settings. This paper proposes a framework for learning by imitation as a way to predict the messages that will eventually fail to reach their destination within the required deadlines. By leveraging expert demonstrations, the Hidden Markov Model is used to encapsulate a set of expert force/torque profiles and corresponding parameters during the off-line training process. A Gaussian mixture regression is then used to reproduce a generalized version of the force/torque profile and corresponding parameters during the prediction. Simulations are conducted to evaluate the performance of the proposed method. They show that our proposed framework is able to execute predictions in much less than the 1ms end-to-end latency requirement of remote robotic surgery.

Using Information Centric Networks (ICNs) instead of IP networks will improve Quality of Experience (QoE) by enabling efficient and scalable Content Delivery Networks (CDNs). However, Information Centric based CDNs still face many challenges. The rate adaptation algorithms used in IP based CDNs can for instance lead to inaccurate estimations of Round-Trip Times (RTTs) in ICN settings. Furthermore, the network storage feature of ICN can introduce major oscillations in adaptive streaming. In this paper, we use the ETSI Multi Access Edge Computing (MEC) to tackle these issues. An overall system view (which includes the MEC server) and a novel rate adaptation algorithm are proposed. The proposed rate adaptation algorithm is validated with simulations and the results show that it significantly improves users' QoE due to higher accuracy and stability in rate estimation.

Cloud computing, despite its inherent advantages (e.g., resource efficiency), still faces several challenges. The wide area network used to connect the cloud to end users could cause high latency, which may not be tolerable for some applications, especially Internet-of-Things (IoT) applications. Fog computing can reduce this latency by extending the traditional cloud architecture to the edge of the network and by enabling the deployment of some application components on fog nodes. Application providers use Platform-as-a-Service (PaaS) to provision (i.e., develop, deploy, manage, and orchestrate) applications in cloud. However, existing PaaS solutions (including IoT PaaS) usually focus on cloud and do not enable provisioning of applications with components spanning cloud and fog. Provisioning such applications requires novel functions, such as application graph generation, that are absent from existing PaaS. Furthermore, several functions offered by existing PaaS (e.g., publication/discovery) need to be significantly extended in order to fit in a hybrid cloud/fog environment. In this article, we propose a novel architecture for PaaS for hybrid cloud/fog system. It is IoT use case driven, and its applications' components are implemented as virtual network functions (VNFs) with execution sequences modeled as graphs with substructures, such as selection and loops. It automates the provisioning of applications with components spanning cloud and fog. In addition, it enables the discovery of existing cloud and fog nodes and generates application graphs. A proof of concept is built based on Cloudify open source. Feasibility is demonstrated by evaluating its performance when the PaaS modules and application components are placed in clouds and fogs in different geographical locations.

The advent of a new breed of enhanced multimedia services has put network operators into a position where they must support innovative services while ensuring both end-to-end Quality of Service requirements and profitability. Recently, Network Function Virtualization (NFV) has been touted as a cost-effective underlying technology in 5G networks to efficiently provision novel services. These NFV-based services have been increasingly associated with multi-domain networks. However, several orchestration issues, linked to cross-domain interactions and emphasized by the heterogeneity of underlying technologies and administrative authorities, present an important challenge. In this paper, we tackle the cross-domain interaction issue by proposing an intelligent and profitable auction-based approach to allow inter-domains resource allocation.

Slices were introduced in 5G to enable the co-existence of applications with different requirements on a single infrastructure. Slices may be delay-constrained for mission-critical applications such as Tactile Internet applications. When delay-constrained slices are implemented as collections of virtual network function (VNF) chains, a key challenge is to place the VNFs and route the traffic through the chains to meet a strict delay constraint. Parallel VNF processing has been proposed as a promising approach. However, this approach increases the number of physical nodes in the chains, and thus decreases the reliability, which is also critical for Tactile Internet applications. Furthermore, the cost depends upon the specific VNF placement and traffic routing, as nodes and links are heterogeneous. This article tackles the issues of reliability and cost when embedding delay-constrained slices. We model the problem as an optimization problem that minimizes reliability degradation and cost while ensuring the strict delay constraint when a parallel VNF processing approach is used. Due to the complexity of the formulated problem, we also propose a Tabu search-based algorithm to find sub-optimal solutions. The results indicate that our proposed algorithm can significantly improve cost and reliability while meeting a strict delay constraint.

Fog-based Content Delivery Networks (CDNs) distribute contents from origin servers to cloud replica servers and to fog caches. Some of these fog caches may be located on Set-top Boxes (STBs) close to end users, assuming that the STBs can host micro-caches. This can greatly reduce Latency. Network function virtualization (NFV) is a technology that can be used in fog systems. NFV-enabled STBs can therefore host micro-caches implemented as virtual network functions (VNFs). Appropriate placement mechanisms are needed to place these micro-caches to improve end-users' QoS in terms of Latency while still minimizing cost. In this paper, this placement problem is modeled as an optimization problem. A bee colony-based algorithm is suggested to find the placement that minimizes an aggregation of Latency and micro-cache storage cost. The simulation results show an improvement in the aggregated Latency and cost when the proposed algorithm is deployed.

The fifth generation (5G) utilizes Network Functions Virtualization (NFV) and Software Defined Network (SDN) to provide applications. Among them, there are deadline constrained applications. When the traffic generated by applications traverses Virtual Network Functions (VNFs) chains, it may not be possible to meet the deadlines when the traffic is processed sequentially; even if very fast servers are provisioned to host the VNFs. We propose a parallel VNF processing approach for the traffic. This is done through pools of candidate servers that host VNFs which process the traffic. Considering the routing policy provided by the SDN routing application, the server selection problem with the aim of deadline satisfaction and cost minimization is modeled as a non-linear binary optimization problem. An iterative search algorithm is proposed to solve this problem. Simulations show enhancement in deadline satisfaction as well as cost reduction.

Users' viewing experience in the video delivery process is of paramount importance for Content Delivery Networks (CDNs). Throughout their operations, CDN providers target the satisfaction of users' expectations in terms of Quality of Experience (QoE). In this context, CDN providers need to acquire knowledge on users' QoE and correlate observations through different video sessions in order to identify QoE degradations and investigate their potential root cause. In the absence of users' feedback on their QoE, CDN providers can monitor and analyze Key Performance Indicators (KPIs) throughout video sessions. This allows to assess the Quality of Service (QoS) offered to users, influencing their QoE. However, due to the large number of sessions handled by CDN operators, it is not possible to conduct such an analysis manually. In this work, we introduce a framework that allows to automatically group a large set of video sessions into a small number of representative clusters, with each cluster containing video sessions with similar patterns of KPIs. The framework builds upon a set of features representing the evolution of KPIs over a session. It relies on an unsupervised machine learning algorithm to form the clusters. We evaluate the framework over a real-world dataset with traffic logs relating to thousands of sessions. The obtained results underline the capabilities of the proposed framework.

Tactile Internet is a next generation Internet. It allows the exchange of haptic sensations in addition to audio and video content. It is a key enabler of several emerging applications as remote robotic surgery and autonomous driving, when combined with 5G and Edge Computing. Because Tactile Internet will enable mission critical applications, it has to adhere to strict requirements, mainly in terms of ultra-responsiveness, ultra-reliability and security. In this paper, we propose a fog-based architecture for remote phobia treatment, a Tactile Internet application. The proposed architecture offers a set of software modules that allow a phobia patient to have a therapy session, under the guidance of an expert therapist located remotely, with the patient and the therapist sharing the same virtual reality environment. We use the fog paradigm to meet the stringent Tactile Internet requirements, namely the round trip latency of 1ms. The components of the architecture offer high level interfaces to simplify interaction with external software components as well as with a wide range of hardware devices. A prototype is also implemented and the performance is discussed.

Multi-stream transport protocols, such as SCTP and QUIC, tackle challenges such as Head of Line (HoL) faced by TCP. They are getting more and more deployed and currently carry more than 7% of the global Internet traffic. However, since these protocols have limited control over the actual routes the streams will take in the network, the streams are generally forwarded through a single and same path, even though there are generally multiple paths available in the network. Consequently, the traffic streams do not fully benefit from the available bandwidth and performance improvement remains limited. Software Defined Networks (SDN) separate control planes and data planes. It offers a complete view of the network to applications and enables network programmability through flexible rules. These rules may be used to ensure that the different streams generated by multi-stream transport protocols follow multiple paths in the network. In this paper, we propose an SDN-based framework for multi-stream transport protocols in multipath networks. The proposed framework provides an interface for applications to specify multi-stream rules. Based on these rules, the framework uses the services offered by the SDN Controller to ensure that the multiple streams go over multiple paths in the network. Experiments performed show that our proposal improves the QoS offered to the end users.

Fog computing extends the cloud to the edge of the network, close to the end-users enabling the deployment of some application component in the fog while others in the cloud. Network Functions Virtualization (NFV) decouples the network functions from the underlying hardware. In NFV settings, application components can be implemented as sets of Virtual Network Functions (VNFs) chained in specific order representing VNF-Forwarding Graphs (VNF-FG). Many studies have been carried out to map the VNF-FGs to cloud systems. However, in hybrid cloud/fog systems, an additional challenge arises. The mobility of fog nodes may cause high latency as the distance between the end-users and the nodes hosting the components increases. This may not be tolerable for some applications. In such cases, a prominent solution is to migrate application components to a closer fog node. This paper focuses on application component migration in NFV-based hybrid cloud/fog systems. The objective is to minimize the aggregated makespan of the applications. The problem is modeled mathematically, and a heuristic is proposed to find the sub-optimal solution in an acceptable time. The heuristic aims at finding the optimal fog node in each time-slot considering a pre-knowledge of the mobility models of the fog nodes. The experiment's results show that our proposed solution improves the makespan and the number of migrations compared to random migration and No-migration.

Fog computing reduces the latency induced by distant clouds by enabling the deployment of some application components at the edge of the network, on fog nodes, while keeping others in the cloud. Application components can be implemented as Virtual Network Functions (VNFs) and their execution sequences can be modeled by a combination of sub-structures like sequence, parallel, selection, and loops. Efficient placement algorithms are required to map the application components onto the infrastructure nodes. Current solutions do not consider the mobility of fog nodes, a phenomenon which may happen in real systems. In this paper, we use the random waypoint mobility model for fog nodes to calculate the expected makespan and application execution cost. We then model the problem as an Integer Linear Programming (ILP) formulation which minimizes an aggregated weighted function of the makespan and cost. We propose a Tabu Search-based Component Placement (TSCP) algorithm to find sub-optimal placements. The results show that the proposed algorithm improves the makespan and the application execution cost.

Multimedia conferencing is the conversational exchange of multimedia content between multiple parties. It has a wide range of applications (e.g., massively multiplayer online games (MMOGs) and distance learning). Media handling services (e.g., video mixing, transcoding, and compressing) are critical to multimedia conferencing. However, efficient resource usage and scalability still remain important challenges. Unfortunately, the cloud-based approaches proposed so far have several deficiencies in terms of efficiency in resource usage and scaling, while meeting quality of service (QoS) requirements. This paper proposes a solution which optimizes resource allocation and scales in terms of the number of participants while guaranteeing QoS. Moreover, our solution composes different media handling services to support the participants' demands. We formulate the resource allocation problem mathematically as an integer linear programming (ILP) problem and design a heuristic for it. We evaluate our proposed solution for different numbers of participants and different participants' geographical distributions. Simulation results show that our resource allocation mechanism can compose the media handling services and allocate the required resources in an optimal manner while honoring the QoS in terms of end-to-end delay.

User Generated Videos (UGV) are the dominating content stored in scattered caches to meet end-user Content Delivery Networks (CDN) requests with quality of service. End-User behaviour leads to a highly variable UGV popularity. This aspect can be exploited to efficiently utilize the limited storage of the caches, and improve the hit ratio of UGVs. In this paper, we propose a new architecture for Data Analytics in Cloud-based CDN to derive UGVs popularity online. This architecture uses RESTful web services to gather CDN logs, store them through generic collections in a NoSQL database, and calculate related popular UGVs in a real time fashion. It uses a dynamic model training and prediction services to provide each CDN with related popular videos to be cached based on the latest trained model. The proposed architecture is implemented with k-means clustering prediction model and the obtained results are 99.8% accurate.

Content Delivery Networks (CDNs) deliver content (e.g. Web pages, videos) to geographically distributed end-users over the Internet. Some contents do sometimes attract the attention of a large group of end-users. This often leads to flash crowds which can cause major issues such as outage in the CDN. Microservice architectural style aims at decomposing monolithic systems into smaller components which can be independently deployed, upgraded and disposed. Network Function Virtualization (NFV) is an emerging technology that aims to reduce costs and bring agility by decoupling network functions from the underlying hardware. This paper leverages the NFV and microservice architectural style to propose an architecture for on-the-fly CDN component provisioning to tackle issues such as flash crowds. In the proposed architecture, CDN components are designed as sets of microservices which interact via RESTFul Web services and are provisioned as Virtual Network Functions (VNFs), which are deployed and orchestrated on-the-fly. We have built a prototype in which a CDN surrogate server, designed as a set of microservices, is deployed on-the-fly. The prototype is deployed on SAVI, a Canadian distributed test bed for future Internet applications. The performance is also evaluated.

Internet of Things (IoT) is expected to enable a myriad of applications by interconnecting objects - such as sensors and robots - over the Internet. IoT applications range from healthcare to autonomous vehicles and include disaster management. Enabling these applications in cloud environments requires the design of appropriate IoT Infrastructure-as-a-Service (IoT IaaS) to ease the provisioning of the IoT objects as cloud services. This paper discusses a case study on search and rescue IoT applications in large-scale disaster scenarios. It proposes an IoT IaaS architecture that virtualizes robots (IaaS for robots) and provides them to the upstream applications as-a-Service. Node- and Network-level robots virtualization are supported. The proposed architecture meets a set of identified requirements, such as the need for a unified description model for heterogeneous robots, publication/discovery mechanism, and federation with other IaaS for robots when needed. A validating proof of concept is built and experiments are made to evaluate its performance. Lessons learned and prospective research directions are discussed.

Multimedia conferencing is used extensively in a wide range of applications, such as online games and distance learning. These applications need to efficiently scale the conference size as the number of participants fluctuates. Cloud is a technology that addresses the scalability issue. However, the proposed cloud-based solutions have several shortcomings in considering the future demand of applications while meeting both Quality of Service (QoS) requirements and efficiency in resource usage. In this paper, we propose an Adaptive and Dynamic Scaling mechanism (ADS) for multimedia conferencing services in the cloud. This mechanism enables scalable and elastic resource allocation with respect to the number of participants. ADS produces a cost efficient scaling schedule while considering the QoS requirements and the future demand of the conferencing service. We formulate the problem using Integer Linear Programming (ILP) and design a heuristic for it. Simulation results show that ADS mechanism elastically scales conferencing services. Moreover, the ADS heuristic is shown to outperform a greedy algorithm from a resource-efficiency perspective.

Wireless Sensor Networks (WSNs) are being used extensively today in various domains. However, they are traditionally deployed with applications embedded in them which precludes their re-use for new applications. Nowadays, virtualization enables several applications on a same WSN by abstracting the physical resources (i.e. sensing capabilities) into logical ones. However, this comes at a cost, including an energy cost. It is therefore critical to ensure the efficient allocation of these resources. In this paper, we study the problem of assigning application sensing tasks to sensor devices, in virtualized WSNs. Our goal is to minimize the overall energy consumption resulting from the assignment. We focus on the static version of the problem and formulate it using Integer Linear Programming (ILP), while accounting for sensor nodes' available energy and virtualization overhead. We solve the problem over different scenarios and compare the obtained solution to the case of a traditional WSN, i.e. one with no support for virtualization. Our results show that significant energy can be saved when tasks are appropriately assigned in a WSN that supports virtualization.

Traditional Content Delivery Networks (CDNs) built with traditional Internet technology are less and less able to cope with today's tremendous growth of content. Information Centric Networks (ICN), a proposed future Internet technology, may aid in remedying the situation. Unlike the current Internet, it decouples information from its sources and provides in- network storage. We expect traditional CDN and ICN-based CDN to co-exist in the foreseeable future, especially as it is now known that it might be possible to evolve traditional CDNs to gain the benefits promised by ICN. 5G providers must therefore aim to offer core network slices on which both ICN-based CDNs and traditional CDNs can be built. These slices could of course also be offered to providers of other applications with requirements similar to those of content delivery. This paper tackles the problem of slicing 5G for content delivery over ICN- based CDNs and traditional CDNs. Only virtualized Evolved Packet Core (EPC)-based 5G is considered. The problem is defined as a resource allocation problem which aims at minimizing the cost of slice assignment, while meeting QoS requirements. An Integer linear programming (ILP) formulation is provided and evaluated in a small-scale scenario.

Value-added Services (VASs) (e.g. dynamic site acceleration, media management) play a critical role in Content Delivery Networks (CDNs). Network Functions Virtualization (NFV) enables the agile provisioning of VASs. In NFV settings, VASs are provisioned as ordered sets of Virtual Network Functions (VNFs), forming VNF-Forwarding Graphs (VNF-FG) which are deployed in the CDN infrastructure. The CDN VAS VNF-FGs have a specific characteristic: they have one end-point (corresponding to the content server) that is unknown, prior to their placement. The proposals for CDN VAS VNF-FG placement, so far, have only considered offline placement, where the VNF-FGs are placed before end-user traffic steers into the network. However, in concrete cases, a change in service usage patterns might occur, a situation that could require a VNF-FG placement in an online manner. This paper tackles the problem of online VNF-FG placement for VASs in CDNs, taking into account the eventual reuses and migrations of already-deployed VNFs. A cost model is considered, including multiple costs; i.e. new VNF instantiations, migration, hosting and routing costs. The objective is to optimally place the VNF-FGs such that total reconfiguration costs are minimized while QoS is satisfied. An Integer Linear Programming (ILP) formulation is provided and evaluated in a small-scale scenario.

Applications are sets of interacting components that can be executed in sequence, in parallel, or by using more complex constructs such as selections and loops. They can, therefore, be modeled as structured graphs with sub-structures consisting of these constructs. Fog computing can reduce the latency induced by distant clouds by enabling the deployment of some components at the edge of the network (i.e., closer to end-devices) while keeping others in the cloud. Network Functions Virtualization (NFV) decouples software from hardware and enables an agile deployment of network services and applications as Virtual Network Functions (VNFs). In NFV settings, efficient placement algorithms are required to map the structured graphs representing the VNF Forwarding Graphs (VNF-FGs) onto the infrastructure of the hybrid cloud/fog system. Only deterministic graphs with sequence and parallel sub-structures have been considered thus to date. However, several real-life applications do require non-deterministic graphs with sub-structures as selections and loops. This paper focuses on application component placement in NFV-based hybrid cloud/fog systems, with the assumption that the graph representing the application is non-deterministic. The objective is to minimize an aggregated weighted function of makespan and cost. The problem is modeled as an Integer Linear Programming (ILP) and evaluated over small-scale scenarios using the CPLEX optimization tool.

Large-scale disaster management applications are among the several realistic applications of the Internet of Things (IoT). Fire detection and earthquake early warning applications are just two examples. Several IoT devices are used in such applications, e.g., sensors and robots. These sensors and robots are usually heterogeneous. Moreover, in disaster scenarios, the existing communication infrastructure may become completely or partially destroyed, leaving mobile ad-hoc networks the only alternative to provide connectivity. Utilizing these applications raises new challenges such as the need for dynamic, flexible, and distributed gateways which can accommodate new applications and new IoT devices. Network functions virtualization (NFV) and software defined networking (SDN) are emerging paradigms that can help to overcome these challenges. This paper leverages NFV and SDN to propose an architecture for on-the-fly distributed gateway provisioning in large-scale disaster management. In the proposed architecture, the gateway functions are provisioned as virtual network functions that are chained on-the-fly in the IoT domain using SDN. A prototype is built and the performance results are presented.

Value-added services (e.g., overlaid video advertisements) have become an integral part of today's content delivery networks (CDNs). To offer cost-efficient, scalable, and more agile provisioning of new value-added services in CDNs, network functions virtualization paradigm may be leveraged to allow implementation of fine-grained services as a chain of virtual network functions (VNFs) to be placed in CDN. The manner in which these chains are placed is critical as it both affects the quality of service (QoS) and provider cost. The problem is however, very challenging due to the specifics of the chains (e.g., one of their end-points is not known prior to the placement). We formulate it as an integer linear program and propose a cost efficient proactive VNF placement and chaining algorithm. The objective is to find the optimal number of VNFs along with their locations in such a manner that the cost is minimized while QoS is met. Apart from cost minimization, the support for large-scale CDNs with a large number of servers and end-users is an important feature of the proposed algorithm. Through simulations, the algorithm's behavior for small-scale to large-scale CDN networks is analyzed.

Due to the recent surge in end-users demands, value-added video services (e.g. in-stream video advertisements) need to be provisioned in a cost-efficient and agile manner in Content Delivery Networks (CDNs). Network Function Virtualization (NFV) is an emerging technology that aims to reduce costs and bring agility by decoupling network functions from the underlying hardware. It is often used in combination with Software Defined Network (SDN), a technology to decouple control and data planes. This paper proposes an NFV and SDN-based architecture for a cost-efficient and agile provisioning of value-added video services in CDNs. In the proposed architecture, the application-level middleboxes that enable value-added video services (e.g. mixer, compressor) are provisioned as Virtual Network Functions (VNFs) and chained using application-level SDN switches. HTTP technology is used as the pillar of the implementation architecture. We have built a prototype and deployed it in an OPNFV test lab and in SAVI, a Canadian distributed test bed for future Internet applications. The performance is also evaluated.

Content Delivery Networks (CDN) interconnect several surrogate a.k.a replica servers that use geographical proximity as a criteria for delivering multimedia content. The delivered content may be enriched by value-added video services (e.g. in-stream video advertisements). The purpose of this demo is to show the prototype we developed in order to enable a cost-efficient and agile provisioning of value-added video services in CDNs. The prototype implements our NFV and SDN-based architecture. The application-level middleboxes that enable value-added video services (e.g. mixer, compressor) are provisioned as Virtual Network Functions (VNFs) and chained using application-level SDN switches. On one hand, we will highlight how value-added video applications can be provisioned in CDN domain. On the other hand, we will show concretely the advantages and overheads of the application-level service function chaining.

Content placement (CP) algorithms are an integral component of Cloud-based Content Delivery Networks (CCDNs) that select a subset of content from the myriad catalogue, to be placed on surrogates to meet end-user requests with quality of service (QoS). It is challenging to conjure popularity of content, due to size of the catalogue, the heavy and long tail nature of the popularity distribution function and complexity arising from Online Social Networking (OSN) relationships. Therefore, we leverage hierarchical organization of surrogates to push and store content that is preemptively and strategically chosen, such that popular and correlated content always remains within QoS distance of each other. We design an Integer Linear Programming (ILP) model and solve it optimally and nearoptimally using CPLEX and Particle Swarm Optimization-based heuristic, respectively. We compare our model with state-of- the-art CP algorithm to show the benefits of popularity and correlation aware CP.

In large-scale natural disasters, humans are likely to fail when they attempt to reach high-risk sites or act in search and rescue operations. Robots, however, outdo their counterparts in surviving the hazards and handling the search and rescue missions due to their multiple and diverse sensing and actuation capabilities. The dynamic formation of optimal coalition of these heterogeneous robots for cost efficiency is very challenging and research in the area is gaining more and more attention. In this paper, we propose a novel heuristic. Since the population of robots in large-scale disaster settings is very large, we rely on Quantum Multi-Objective Particle Swarm Optimization (QMOPSO). The problem is modeled as a multi-objective optimization problem. Simulations with different test cases and metrics, and comparison with other algorithms such as NSGA-II and SPEA-II are carried out. The experimental results show that the proposed algorithm outperforms the existing algorithms not only in terms of convergence but also in terms of diversity and processing time.

The European Telecommunications Standards Institute (ETSI) developed Network Functions Virtualization (NFV) Management and Orchestration (MANO) framework. Within that framework, NFV orchestrator (NFVO) and Virtualized Network Function (VNF) Manager (VNFM) functional blocks are responsible for managing the lifecycle of network services and their associated VNFs. However, they face significant scalability and performance challenges in large-scale and geo-distributed NFV systems. Their number and location have major implications for the number of VNFs that can be accommodated and also for the overall system performance. NFVO and VNFM placement is therefore a key challenge due to its potential impact on the system scalability and performance. In this paper, we address the placement of NFVO and VNFM in large-scale and geo-distributed NFV infrastructure. We provide an integer linear programming formulation of the problem and propose a two-step placement algorithm to solve it. We also conduct a set of experiments to evaluate the proposed algorithm.

Network services have been significantly increased in today's enterprise networks. The time and cost of deploying these services are recently considered as critical challenges for enterprise networks. Network Functions Virtualization (NFV) is a promising solution to offer cost-efficient, scalable and more rapid deployment of such services. It allows the implementation of fine-grained services as a chain of Virtual Network Functions (VNFs). These chains need to be placed in the network. The chain placement is critical since it effects on both quality of service (QoS) and the provider cost. This paper formulates the problem of VNF placement and chaining as an Integer Linear Program (ILP) and proposes a Cost-efficient Centrality-based VNF Placement and chaining algorithm (CCVP). The objective is to find the optimal number of VNFs along with their locations in such a manner that the provider cost is minimized. Apart from cost minimization, the support for large-scale environments with a large number of servers and end-users is an important feature of the proposed algorithm. Finaly, the algorithm behavior is analyzed through simulations.

The European Telecommunications Standards Institute management and orchestration framework is designed to enable automated management of the network services and their corresponding virtualized network functions (VNFs). In that context, the network function virtualization (NFV) orchestrator (NFVO) manages the lifecycle of the network services and coordinates with the VNF managers (VNFMs) which manage the VNFs lifecycle. In large-scale and distributed NFV deployments, these management functions face critical challenges such as delays, and variations in VNFs workload. Placing NFVO and VNFM in a large-scale distributed NFV deployment is therefore a very challenging problem due to the potential negative impact on performance and operational cost. However, to the best of our knowledge, the problem has not yet been addressed in the literature. This paper is a first step toward a solution to the overall problem. It focuses on the VNFM placement and aims at minimizing the operational cost without violating the performance requirements. We call this the VNFM placement problem (MPP). We provide an integer linear programming formulation and propose a tabu search algorithm to solve larger instances of the MPP. We evaluate our algorithm in a real-world large-scale scenario. The results show that it leads to significant reductions in the operational cost of large-scale distributed NFV deployments.

Sharing a deployed Wireless Sensor Network Infrastructure (WSNI), (using virtualization), among multiple, concurrent applications can help realize the true potential of Internet-of-Things (IoT). Virtualized WSNs can be used by multiple applications and services concurrently including semantic applications to help end-users to understand the context of the events and make informed decisions. This paper proposes a heuristic-based genetic algorithm to select capable nodes to perform efficient in-network sensor data annotation in virtualized WSNs. We also present early simulations results.

Fog computing brings cloud closer to end-users and data sources by enabling computation at the edge of the network. Low latency is the main benefit. IoT applications are often latency-sensitive. Such applications may be provisioned as component-based in a hybrid cloud/fog environment with components spanning cloud and fog. This will enable placing some of its components in the fog domain closer to the IoT devices, and consequently reduce the latency. However, provisioning applications in hybrid cloud/fog environment is still manual today. Existing PaaS do not support interacting with fog nodes, at the edge, for applications' components provisioning. This demo shows the key features of the hybrid Platform as-a-Service (PaaS) we have designed for IoT applications provisioning in cloud and fog environments. Three goals are assigned to the demo: (1) How applications can be designed and developed in such environments, (2) how the hybrid PaaS deploys the applications' components across cloud and fog nodes, and (3) how it executes and manages them using appropriate orchestration techniques.

Content Delivery Networks (CDN) and their globally dispersed caches host a myriad of User Generated Videos (UGV) to meet end-user requests with quality of service. To efficiently utilize the limited storage of the caches, it is imperative to improve the hit ratio of UGVs. In contrast to the traditional static content, UGV popularity is highly dynamic and dependent on end-user behavior. Therefore, we devise a novel popularity prediction model for UGV, using a hybrid regression model. Our hybrid regression model dynamically adapts the popularity of UGV that is built from a historical training dataset. We reduce error in predicting popularity by up to 14%, when compared to pure offline and online approaches, with a small increase in the execution time and memory overhead. Our novel popularity prediction model accounts for end- user behavior by considering the end-user video watch time and the number of shares for the UGVs. To improve cache performance in CDN, we employ a cache replacement strategy that leverages our popularity prediction model to efficiently evict the less popular UGVs for more popular content. We compare our novel cache replacement strategy with the traditional and state-of-the-art cache replacement strategies and show an increase in the average hit ratio of up to 74% and 7%, respectively, for UGVs with shortterm popularity.

Internet of Things (IoT) is expected to enable a myriad of end-user applications by interconnecting physical objects. Cloud computing is a promising paradigm for provisioning IoT end-user applications in a cost-efficient manner. IoT end-user applications are provisioned in cloud settings using PaaS and offered as SaaS. This paper focuses on the PaaS aspects of IoT end-user applications provisioning. It critically reviews the state of the art. The critical review discusses the PaaS on the whole spectrum of IoT verticals and also the PaaS dealing with specific IoT verticals.

Multimedia conferencing is the real-time exchange of multimedia content between multiple parties. It is the basis of a wide range of applications (e.g., multimedia multiplayer game). Cloud-based provisioning of the conferencing services on which these applications rely will bring benefits, such as easy service provisioning and elastic scalability. However, it remains a big challenge. This paper proposes a PaaS for conferencing service provisioning. The proposed PaaS is based on a business model from the state of the art. It relies on conferencing IaaSs that, instead of VMs, offer conferencing substrates (e.g., dial-in signaling, video mixer and audio mixer). The PaaS enables composition of new conferences from substrates on the fly. This has been prototyped in this paper and, in order to evaluate it, a conferencing IaaS is also implemented. Performance measurements are also made.

Virtualization in Wireless Sensor Networks (WSN) allows an efficient resource usage through the sharing of the same WSN physical infrastructure by multiple applications. Semantic applications are gaining more and more momentum. However, provisioning them in Virtualized WSNs (vWSNs) remains a big challenge; the data collected by the virtual sensors needs to be annotated in-network and for this annotation, an ontology needs to be provisioned, i.e. developed, deployed and managed. This paper proposes a framework for ontology provisioning in vWSNs. The framework comprises of an ontology provisioning center, an ontology enabled vWSN and an ontology provisioning protocol that enables the interactions between the provisioning center and the ontology enabled vWSN. To the best of our knowledge this is the first effort to provide such support in vWSNs. We have built a prototype to evaluate the performance of the framework and also present simulation results of the ontology provisioning protocol.

Recently, Cloud based Content Delivery Network (CCDN) has emerged as efficient content delivery architecture to provide content delivery services with improved Quality of Service (QoS), scalability and resource efficiency. Replica server placement is a key design issue in CCDNs and involves deciding the placement of replica servers on geographically dispersed cloud sites that minimizes the operational cost and satisfies QoS of the end-users. Since replica server placement problem is NP-hard, it is necessary to design an efficient heuristic for CCDNs. In this paper, we propose an efficient greedy heuristic for the replica server placement problem. The heuristic consists of two main procedures: placement and refinement. The placement procedure obtains an initial placement of replica servers on cloud sites with low operational cost. The refinement procedure removes the redundant cloud sites to reduce the operational cost further. The simulation results demonstrate that the proposed greedy heuristic outperforms the existing greedy heuristics in terms of computation time and the operational cost.

This demo will show the key features of a Platform as-a-Service (PaaS) we have proposed in a research paper accepted for presentation at IEEE LANMAN 2016 conference. The proposed PaaS enables IoT applications provisioning in hybrid cloud/fog environments. Two goals are assigned to the demo. On the one hand, we will highlight how IoT applications can be provisioned in such environments. On the other hand, we will show concretely the advantages these hybrid environments have over traditional cloud environments. The provisioning in these hybrid environments enables latency reduction and processing performance enhancement. Indeed, in order to reduce latency, the applications can have some of its components running in a distant cloud and interacting with the other components running in the fog, closer to IoT devices.

Fog computing brings cloud close to end-users and data sources by enabling computation and storage at the edges of the network. An application can have some of its components running in a “distant” cloud and interacting with the other components running in the fog, closer to end-users and data sources such as wireless sensors. Low latency is the main benefit. Applications spanning cloud and fog, such as Internet of Things (IoT) applications, are still provisioned manually nowadays. This paper proposes an architecture for a Platform as-a-Service (PaaS) to automate applications provisioning in a hybrid cloud/fog environment. Cloud Foundry is used as the basis for its implementation. As a use case, the proposed PaaS was employed to provision a simple component-based IoT application that detects fire and dispatches robots to fight the fire. A prototype is built and measurements are made.

Home Subscriber Server (HSS) is the main database of the current generation's cellular communications systems. It contains subscriber-related information, such as the authentication information and the list of services to which each user is subscribed. The anticipated tremendous increase in the number of subscribers, services and devices (M2M) in 5G networks brings new challenges with regard to HSS provisioning. It calls for more scalability and elasticity regarding information storage, access and management. The current method for increasing the number of HSSs deployed is certainly not the most cost efficient solution. On the other hand, advanced virtualization techniques can aid in tackling the challenges while enabling a smooth migration to 5G. This paper proposes a new architecture for a scalable and elastic HSS using virtualization. The new architecture enables easy and rapid deployment of new HSS instances at a minimal cost, while increasing efficiency of the use of resources. The paper presents the architecture, demonstrates its use via a case scenario, describes the implemented proof of concept prototype and evaluates the performance results.

Multimedia conferencing is the conversational exchange of multimedia content between multiple parties. It has a wide range of applications (e.g. Massively Multiplayer Online Games (MMOGs) and distance learning). Many multimedia conferencing applications use video extensively, thus video mixing in conferencing settings is of critical importance. Cloud computing is a technology that can solve the scalability issue in multimedia conferencing, while bringing other benefits, such as, elasticity, efficient use of resources, rapid development, and introduction of new applications. However, proposed cloud-based multimedia conferencing approaches so far have several deficiencies when it comes to efficient resource usage while meeting Quality of Service (QoS) requirements. We propose a solution to optimize resource allocation for cloud-based video mixing service in multimedia conferencing applications, which can support scalability in terms of number of users, while guaranteeing QoS. We formulate the resource allocation problem mathematically as an Integer Linear Programming (ILP) problem and design a heuristic for it. Simulation results show that our resource allocation model can support more participants compared to the state-of-the-art, while honoring QoS, with respect to end-to-end delay.

With the recent advances in sensor hardware and software, architectures for virtualized Wireless Sensor Networks (vWSNs) are now emerging. Through node- and network-level virtualization, vWSNs can be offered as Infrastructure-as-a-Service (IaaS) which can aid in realizing the true potential of Internet-of-Things (IoT). Cloud computing offers elastic provisioning of large-scale infrastructures to multiple concurrent users where Platform-as-a-Service (PaaS) interacts with IaaS in order to efficiently host and execute applications over these infrastructures. Amalgamating IoT with cloud computing potentially allows rapid application and service provisioning in an efficient, scalable and robust manner. However, interactions between vWSNs and PaaS are largely an unexplored area. Indeed, existing vWSN IaaS are not yet ready for PaaS. This paper proposes a vWSN IaaS architecture which is ready for interactions with PaaS. The proposed architecture is based on our previous works and is rooted in the fundamental differences between traditional IaaS and vWSN IaaS. We built a prototype using Java Sunspot as the WSN tool kit and made early performance measurements.

Content Placement (CP) problem in Cloud based Content Delivery Networks (CCDNs) leverage resource elasticity to build cost effective CDNs that guarantee QoS. In this paper, we present our novel CP model, which optimally places content on surrogates in the cloud, to achieve (a) minimum cost of leasing storage and bandwidth resources for data coming into and going out of the cloud zones and regions, (b) guarantee Service Level Agreement (SLA), and (c) minimize degree of QoS violations. The CP problem is NP Hard, hence we design a unique push based heuristic, called Weighted Social Network Analysis (W SNA) for CCDN providers. W-SNA is based on Betweeness Centrality (BC) from SNA and prioritizes surrogates based on their relationship to the other vertices in the network graph. To achieve our unique objectives, we further prioritize surrogates based on weights derived from storage cost and content requests. We compare our heuristic to current state of the art Greedy Site (GS) and purely Social Network Analysis (SNA) heuristics, which are relevant to our work. We show that W-SNA outperforms GS and SNA in minimizing cost and QoS. Moreover, W-SNA guarantees SLA but also minimizes the degree of QoS violations. To the best of our knowledge, this is the first model and heuristic of its kind, which is timely and gives a fundamental pre allocation scheme for future online and dynamic resource provision for CCDNs.

Wireless Sensor Networks (WSNs) have become very popular and are being used in many application domains (e.g. smart cities, security, gaming and agriculture). Virtualized WSNs allow the same WSN to be shared by multiple applications. Semantic applications are situation-aware and can potentially play a critical role in virtualized WSNs. However, provisioning them in such settings remains a challenge. The key reason is that semantic applications' provisioning mandates data annotation. Unfortunately it is no easy task to annotate data collected in virtualized WSNs. This paper proposes a data annotation architecture for semantic applications in virtualized heterogeneous WSNs. The architecture uses overlays as the cornerstone, and we have built a prototype in the cloud environment using Google App Engine. The early performance measurements are also presented.

In this paper we present the concept of context- aware Emergency Notification and Rescue Service (ENRS) utilizing user information from the 4G EPC network. The 4G EPC is an all IP next generation architecture that makes it easy for various 3GPP and non-3GPP standards to co-exist and provide network access to the end user. The proposed architecture consists of two parts; first part is emergency notification and information gathering to use for the event notification. The second part consists of an intelligent context-aware decision engine that processes the collected information in real time and generates notification messages for the end user. Our proposed service is based on the RESTful concepts and can be used to effectively notify and help users during the emergency. Currently a prototype of the service is being developed to validate the ENRS.

In current practice, the fire-fighters communication system is verbal, using a simplex radio frequency system (walkie-talkie). This system has a flat communication structure, which prevents any private communication among groups of firefighters. In addition, only one fire-fighter is allowed to talk at a time and no other functionalities (e.g. video communications or conferencing) are supported. This paper proposes a new multimedia conferencing system for fire-fighters, which overcomes the current system limitations. The new system is based on Mobile Ad-Hoc Networks, an infrastructure-less and self-organized wireless networks that are suitable for emergency situations. The proposed system has a cluster-based architecture in order to offer more scalability. A proof-of-concept prototype has been implemented and performance have been evaluated and analysed.

Disaster response systems improve the situational awareness of responders and assist them by providing a wide range of services including communications, sensing/actuating and data collection and processing. The services are hosted on various types of devices such as laptops, PDAs, sensors and actuators that usually are interconnected through a mobile ad-hoc network (MANET). Interactions are required between these various services and this makes service discovery a key component of disaster relief systems. In this paper we propose a novel DNS-based service discovery architecture for disaster response systems. Our architecture employs the recent IETF proposal, DNS-based Service Discovery (DNS-SD) for representing service information as DNS records, and uses a cluster-based approach to dynamically form service directories and to enable service discovery.

Open Mobile Alliance (OMA) RESTful location services are standard RESTful Web services for terminal location. They are location technology-independent and enable applications' portability and interoperability. Wireless sensors are electronic devices that can sense context: space, environment and physiology. Location is a key element of space context information. Wireless sensors can sense location with an accuracy that most other technologies cannot provide, which has made them the technology of choice for several applications. This paper proposes a novel architecture for the implementation of OMA RESTful location services in wireless sensor environments. The architectural components and operational procedures are described. The proof of concept prototype is also described, along with the measurements.

The Session Initiation Protocol (SIP) is the de facto standard for multimedia multiparty sessions signalling in Next Generation Networks (NGN). It is the basis of a wide range of IP multimedia services. SIP relies on centralized servers, as per its standard specifications and current usage. However, research has recently begun on the integration of Peer-to-Peer (P2P) principles to SIP to capitalize on the benefits of decentralization. This paper contributes to this research by proposing a novel architecture for P2P SIP. The architecture is an overlay composed of a set of self-organized proxies and distributed registrars. Unlike the architectures proposed to date, it does not extend SIP messages and is P2P middleware independent. This eases implementation, interoperability with legacy, and ensures portability. We have prototyped it using JXTA. JXTA is a P2P middleware that can be deployed on devices ranging from cellular phones to high-end servers and including laptops. Requirements are derived and the related work is discussed. The architecture is presented and the implementation, including the prototype, is described.

Wireless actuators are small scale devices that can receive/accept instructions and act on their environment. The IP Multimedia Subsystem (IMS) is a key component for 3G networks. It aims at seamless provisioning of multimedia services. Combining actuation capabilities with IMS capabilities will certainly enable novel value added services. This paper proposes an architecture for the integration of wireless actuation with IMS. The cornerstone of the architecture is the actuation control function, a new functional entity that we introduce into the IMS architecture. A proof of concept prototype has also been developed along with an application to demonstrate the potential of such an integration.

The IP Multimedia Subsystem (IMS) is a key component of 3G networks aimed at enabling the seamless provisioning of IP multimedia services to end users. Multiparty sessions (or conferences), which enable the conversational exchange of multimedia content between several parties, represent one of the specialized services supported by the IMS. Conferencing is the basis of a wide range of applications such as: debating; multiplayer gaming; and distance learning. In order to offer users a predictable experience and a controlled quality when using such applications, suitable QoS mechanisms must be supported in the IMS. We have previously proposed a two-party call differentiation scheme along with an architectural framework enabling its realization in the IMS. In this work, we apply our call differentiation scheme to the conferencing case, by studying the effects of call differentiation on the operation of the standard IMS conferencing architecture. This is achieved via a case study including the definition of a differentiated IMS conferencing architecture, the elaboration of various differentiated multiparty sessions scenarios, and the implementation of a proof-of-concept prototype.

The IP Multimedia Subsystem (IMS) aims to provide cellular access to all the services that the Internet offers; it is an overlay control layer on top of an IP layer. Wireless Sensor Networks (WSN) with mobile sinks are useful in a wide range of scenarios since they can improve the overall network lifetime and increase data capacity. Combining the capabilities of IMS with the rich set of contextual information captured by mobile sink WSNs will open the door to a wide range of novel multimedia services. This paper proposes an overlay architecture for the integration of IMS with mobile sink-based WSN. The Presence service is used as entry point to the IMS world. The gateway which is the heart of our architecture is an overlay built on top of the very same mobile phones that act as mobile sinks, presence publishers / watchers, and end-user devices. A prototype is built using JXME, an extension of JXTA with P2P middleware.

The IP Multimedia Subsystem (IMS) is becoming the de-facto standard for IP-based multimedia services, while Wireless Sensor Networks (WSNs) are gaining a lot of popularity due to their ability of capturing a rich set of contextual information and their high application potential. Making the rich set of contextual information, captured by WSNs, available to the IMS can greatly enhance its service provisioning capabilities and open the door to a wide range of novel multimedia services. We have previously proposed a solution for WSNs/IMS integration. One of the key components of this solution is a WSN/IMS gateway acting as intermediary between the two networks. This paper focuses on the design and implementation of this gateway. The gateway architecture proposed encompasses the information management and support functions needed to enable IMS interaction with different types of WSNs. A prototype of this architecture is built and tested using Ericsson's IMS simulated environment. Furthermore, two applications (a pervasive game and a personalized call control application) are used to demonstrate the system operation.

The IP Multimedia Subsystem (IMS) is a key component of 3G networks. It enables the seamless provision of multimedia services to end-users. Multimedia conferencing is an important category of multimedia services in IMS. It is the basis of a wide range of multiparty applications including audio/video conferencing, multiparty gaming and distance learning. Floor control is an important feature of multimedia conferencing. It manages the access to shared resources such as audio and video channels. This paper proposes a novel architecture for floor control in IMS. The architecture is an add-on to the IMS conferencing architecture. It includes a comprehensive set of server side and client side API that exposes the floor control capabilities to application developers. It enables the use of emerging industry standards such as SIP MSCML and JSR 309. Furthermore it proposes a novel interface (the SIP Floor Server Control Mark Up (SIP-FSCML) Language) as an alternative to Megaco/H.248 for controlling floor control servers. We successively introduce the overall architecture, the novel APIs, the communication interfaces (including SIP-FSCML) and the proof of concept prototype.

Mobile ad hoc networks (MANETs) are infrastructure-less and can be set up anywhere, anytime. They can host a wide range of applications in rescue operations, military, private, and commercial settings. Multimedia conferencing is the basis of a wealth of "killerrdquo applications that can be deployed in MANETs. Some examples are audio/video conferencing, multiplayer games, and online public debating. Signaling is the nerve center of multimedia conferences-it establishes, modifies, and tears down conferences. This paper focuses on signaling for multimedia conferences in MANETs. We review the state of the art and propose a novel architecture based on application-level clusters. Our validation employed SIP as the implementation technology and OPNET as our simulation tool. Our clusters are constructed dynamically and the nodes that act as cluster heads are elected based on their capabilities. The capabilities are published and discovered using a simple application-level protocol. The architectural principles and the clustering operations are discussed. Our SIP-based implementation is also presented along with the performance evaluation.

Multihop Cellular Networks (MCNs) are an example of the integration of 3G and mobile ad hoc networks (MANETs). In this integration, single-hop cellular networks and MANETs coexist and cooperate. 4G networks are seen as the coexistence and cooperation of legacy (e.g 3G) and new (e.g. MANET) networks. This makes integrated 3G/MANET and particularly multihop cellular networks part of the 4G vision. MCNs have now emerged as a new and promising research area. However, MCNs service provisioning aspects, which are the focus of this paper, have not yet been addressed. This work identifies and analyzes the high level architectural alternatives for service provisioning using the SIP servlets framework. Our choice of the SIP servlet framework is motivated by the fact that SIP is currently being considered for the signaling protocol in integrated 3G/MANETs. We conclude that the most interesting options for the 3G network operator are an architecture that enables the invocation of 3G services by MANET users and an architecture that enables the execution of MANET services in 3G The first alternative has the advantage of extending 3G coverage and speeding up the service execution process while the second one has the benefit of providing to MANET users a reliable environment with powerful resources for service execution. This paper also identifies the research issues related to these two alternatives.

Emergency sessions are the most fundamental and critical services offered by telecommunications networks. They require preferential treatment over regular sessions and this is achieved with QoS and resource management techniques. An IMS emergency service architecture has been proposed by 3GPP. However, this solution only provides preferential treatment to public-initiated emergency communications. It does not offer any special treatment to mission critical calls, PSAP callbacks, and urgent communications among citizens. Furthermore, the preferential treatment offered does not provide public-initiated emergency sessions with a prioritized access to the resources at the transport layer. This may lead to unacceptable emergency sessions' setup delays and even emergency sessions failures when there is a strong contention for transport resources. This paper tackles these issues by extending the existing 3GPP architecture. We introduce new QoS profiles for emergency sessions, and propose mechanisms for supporting them. We have also built a proof of concept prototype. Its main features are presented.

Web services can be reused to create new ones using composition methods. We have proposed a framework for Web services composition previously. In this framework, we describe Web services with functional, semantic, behavioral, and non-functional characteristics. The framework uses different techniques for creating the composite service. We have already proposed a matchmaking technique that enables discovering the primitive Web services that would be used to create the composite service. In this paper, we propose concepts and schemes for categorizing and assembling the matched services. A core concept called categories is used by the proposed techniques, which are basically organizational elements. The categorization technique helps the assembly technique in creating the composite service by categorizing the matched services. The assembly technique manipulates and selects the categorized services from different categories, uses BPEL to orchestrate the selected services, and finally selects the best-assembled service as the composed service. A case study from telecom domain is used to illustrate the proposed techniques.

Emergency services represent one of the fundamental services offered by the IP multimedia subsystem (IMS). Currently, these services rely on a limited range of contextual information (mainly location). A richer set of contextual information could be exploited to provide enhanced emergency services and lead to more efficient emergency operations. In this paper, we propose an extension of the 3GPP IMS emergency service architecture for the provision of enhanced, context-aware emergency services. The 3GPP presence framework is leveraged and extended to realize the information management aspects of the architecture. Furthermore, a proof-of-concept prototype, showcasing an enhanced emergency service scenario, is presented.

Wireless Sensor Networks (WSN) are made up of small devices that can sense context information (e.g. space, physiology, and environment). The IP Multimedia System (IMS) aims at the convergence of Internet and cellular networks. It enables the delivery of multimedia services to end-users. Integrating the sensing capabilities of WSN in the IP multimedia subsystem will open the door to a wide range of novel multimedia services. This paper proposes a presence based architecture for the integration, focusing on how the information is conveyed from the WSN to the presence infrastructure (i.e the inbound interface). Presence is an integral part of IMS. It enables the distribution of end-user presence information (e.g. location, availability), a sub-set of context information, to interested parties, generally applications. We introduce the architecture and elaborate some of the required extensions to the 3GPP presence service. The proof of concept prototype is also described.

Ambient networks is a new networking concept for beyond 3G. An ambient network is defined as one or more network nodes or devices that share a common network control plane. Network composition is a core concept of ambient networks. It requires the composition of the different registries hosted by the composing ambient networks. These registries may be heterogeneous. Entities in a given network may also need to access information hosted by a registry in another network. This makes the problem of information discovery and publication after composition very challenging. This paper proposes a solution based on an overlay architecture. We introduce the functional entities of the overlay architecture; present the procedures and messages related to the publication and discovery of information and describe the implementation of a proof-of-concept prototype based on JXTA, a middleware commonly used in peer-to-peer settings.

Ambient networks refer to a new networking concept for beyond 3G. They use automatic network composition to enable dynamic and instantaneous inter- working between heterogeneous networks on demand. Ambient networks can host several registries (e.g. management information bases, context information bases). When they autonomously compose, the hosted registries have to follow suit and compose. This paper focuses on the issues related to the autonomous composition of registries when ambient networks compose. We identify a set of requirements and propose a general architecture for autonomic composition. We also discuss cursorily information discovery after composition.

Conferencing is an important category of applications that includes very popular applications such as audio/video conferencing, distance learning and multiparty games. It comprises two main components: signaling and media handling. Conferencing in mobile ad hoc networks (MANETs) remains an uphill task due to the special characteristics of these networks. This paper focuses on the media handling aspects of conferencing. It proposes a novel architecture for controlling media mixers. The architecture is based on Megaco, an approach for controlling media mixers in traditional networks. We present it in terms of functional entities, primitives and procedures. Simulation results are also included.

A critical challenge in mobile ad hoc networks is to scale with a flat structure. Clusters are customarily used at the network layer of these networks, especially for the routing schemes required to approach this problem. Recently, their use at the application layer has also been proposed. However, this new usage faces many performance challenges. This paper focuses on how to optimize the performance of cluster-based application layer schemes in mobile ad hoc networks. It proposes an architecture based on cross-layer design, a concept employed more and more in wireless environments, and which violates reference-layered architecture. We illustrate this architecture with a case study on a cluster-based session signaling scheme. We also present a proof-of-concept prototype and our initial measurements.

In conventional wireless sensor networks, sinks collect data from sensors and/or aggregators and interact with end-user applications via centralized gateways. However, there exist application scenarios where this modus operandi may not be suitable. In such cases it is preferable that the applications interact directly with the sensors. This paper proposes a Web- service based architecture with an overlaid UDDI for these cases. It also presents simulation results for these scenarios to demonstrate performance gains.

Service differentiation is an active topic in 3G networks, which aim at supporting a diversity of IP multimedia services (with different QoS requirements) and users (establishing sessions with different levels of importance). In this paper, we propose a network level call differentiation scheme in IMS-based 3G networks. This scheme defines three new classes of calls offering different priorities/guarantees to the user. Service differentiation is achieved at the session signaling level by relying on a context-aware resource allocation strategy. An extension to the 3GPP IMS architecture is proposed to realize the service differentiation scheme and a proof-of-concept prototype is built using SIP and COPS as implementation technologies. Unlike other signaling level schemes, the system proposed here offers flexible QoS negotiation mechanisms to the user, provides preferential treatment at the beginning and during sessions, and takes into consideration the characteristics of the multimedia, multiparty, service environment offered by 3G networks.

Ambient Networks (AN) is a new networking concept for beyond 3G. Network composition is a core concept of AN. It provides dynamic cooperation between heterogeneous networks. Each ambient network can host several registries. When the networks compose, the registries also have to compose. This composition is based on a composition agreement that must be negotiated between the different parties involved. This paper presents a framework for dynamic negotiation of an agreement for the composition of registries. It presents the framework principles and a template for the composition agreement proposals, and describes the main steps of the negotiation. It also describes the negotiation protocol (i.e. entities, messages and state diagrams). We have validated our protocol using SPIN, a software tool for simulating and validating distributed systems behavior. The process and the results are discussed.

It is foreseen that several wireless sensor networks (WSNs) will be deployed in the very near future to provide various sensing services to end user applications. A wide range of novel end-user applications will emerge. In some application scenarios, the sinkless model is appropriate. In this model, the applications interact directly with the sensor nodes, without going through a gateway. However, the current sensor nodes use proprietary protocols and data access frameworks. This propriety will hinder the speed of evolution of applications. There is a need for a framework that is well known to application developers and is based on standard protocols. This paper presents an embedded Web services platform residing on the sensor nodes, allowing direct interaction between applications and individual sensor nodes. The lessons learned indicate that Web service platform on sensor node is feasible, despite the nodes' limited resources and the complexity of the framework.

Wireless sensor networking research has been mainly focused on internal wireless sensor network issues such as MAC and routing protocols, energy saving, HW design and to some extent on the architecture of gateways that connect a wireless sensor network with the rest of the world. Wireless sensor networks have been seen as dedicated to one task by one owner. On the other hand, our research is focused on integration of wireless sensor networks into existing networks, primarily mobile ones, and provision of sensor based and/or enhanced services to remote users. Therefore, we have been working on designing an architecture that utilizes the existing infrastructure to interconnect independent wireless sensor networks and to provide data aggregation and actuator control services. In the proposed architecture, sensor networks (small or large, deployed for any purpose and by anyone) represented by their gateways are treated as leaf nodes hanging off a mobile or fixed network that use these networks to interact with remote and local users. Each gateway exposes the capabilities of its sensors, actuators and the sensor network as a whole. This information is used by sensor services middleware to query/command sensor ecosystems on behalf of applications and remote users interested in sensor measurements or actuator control. The details of the interaction between the gateways and its sensors/actuators are of no interest to the remote users. Further, we consider the whole wireless sensor networking landscape as an open market where the underlying mobile and fixed networks facilitate the interaction between the sensor networks and the consumers of the information they produce. Each sensor network is first of all a sensor information provider that offers specific sensor information defined by the type of available sensors and their spatial and temporal conditions to the interested users. Secondly, each sensor network provides actuation services that may potentially affect the information gathered by its sensors. Obviously, in such an environment, where many mobile users are acting as tiny information providers, service discovery, service composition, service provisioning and service authorization are very challenging problems. These problems are addressed in the proposed architecture by introducing a middle layer that aggregates information from all small information providers and provides higher level services to the end users. This layer provides the means to quickly add or remove sensors, actuators, sensor networks, sensor network providers, to modify and enhance the existing or add completely new services utilizing the underlying infrastructure. It could be thought of as a "plug-and-play" functionality for: (a) interconnecting different existing sensor networks; (b) adding new sensor networks which facilitate the expansion of the entire system; and (c) expanding the capability of individual sensor networks.

Conferencing represents an important category of applications, which includes videoconferences and distance learning. To our knowledge, there is no signaling architecture for conferencing in integrated 3G/mobile ad hoc networks. However, there are architectures for conferencing in stand alone 3G and in stand alone mobile ad hoc networks. Unfortunately, none are suitable when the two networks are integrated. This paper proposes a novel signaling architecture for conferencing in integrated 3G/mobile ad hoc networks. This architecture is based on application-level clusters and conference gateways. The gateways mediate between the 3G and the mobile ad hoc networks. We have implemented a prototype using the Session Initiation Protocol as our technology.

Applications are the ultimate consumers of the information collected by sensors. There exist several frameworks for the interactions between end-user applications and sensors. They range from low-level APIs to databases and include Web Services. This paper is devoted to the use of Web Services for bridging end-user applications and wireless sensors networks. Its first contribution is a systematic evaluation of the current frameworks for the interactions between end-user applications and wireless sensors networks. The evaluation shows the potential of Web Services, compared to the other frameworks and motivates their usage in the case study. The second contribution is the definition of Web Services for the I-centric telecommunication services, and their implementation in a wireless sensor network that does not support Web Services. We demonstrate that Web Services are very promising as "bridges" and share the lessons we have learned.

Presence technology conveys the willingness and ability of an entity to communicate and is very useful in developing innovative applications. Protocols and APIs have been proposed for presence, but these APIs are at a low level of abstraction. Web services provide the flexibility to develop loosely coupled applications with coarse-grained interfaces. This paper proposes a novel Web service for presence application development. This Web service is presence protocol independent and its use is illustrated in the paper by a concrete application. We have implemented it as a gateway towards an IETF SIMPLE based presence server, but other implementations are possible. The mapping is discussed and the prototype described. Performance measurements are also made. The results indicate that the additional overhead introduced because of XML based SOAP messages is not prohibitive, although significant.

In this paper we propose a new architecture for media handling in ad-hoc peer-to-peer networks. The architecture is distributed with two steps in the mixing operation. Our system is composed of two levels of peers. The high level is formed by peers, which do mixing and are called mixers. Each mixer is dedicated to a number of peers belonging to the second level. Synchronization of mixers is important to deliver media streams with proper ordering and timing. We propose a distributed algorithm based on logical clocks to synchronize mixers. The two main advantages of our architecture are scalability and the limited number of mixers in end-to-end path. This second feature guarantees rapid delivery of streams. We have built a proof of concept prototype and compared the performance results with the hierarchical mixing architecture.

Multiparty sessions are the basis of a wealth of applications. Some examples are audio/video conferencing, distance learning and gaming. Peer-to-peer ad hoc networks are now emerging. They are useful in a wide range of application scenarios in personal, commercial, public and military environments. Very little is known today on how to handle multiparty sessions in these new networks. This paper proposes a novel signaling system for multiparty sessions in peer-to-peer ad hoc networks. The architecture relies on clustering. Requirements are derived and new principles are proposed. The principles are implemented as extensions to the session initiation protocol (SIP). Extending SIP enables easy interworking with conventional third generation telecommunication networks. The implementation is presented. We have also built a prototype, using JXTA, a middleware for peer-to-peer. The prototype is described with the measurements we have made.

Internet telephony can be defined as real-time voice or multimedia communications over packet switched networks, including the Internet. The advent of third generation, wireless telecommunications networks will make it much more popular by adding the wireless dimension. Millions of end-users will access Internet telephony services using wireless devices. These end-users will be highly mobile and will change locations very frequently. A key requirement in this environment is universal access. It stipulates that end-users have access to their advanced services from anywhere and from any terminal. Mobile agents can aid in meeting it in an efficient manner. They can carry services and follow roaming end-users. The paper presents the design, the implementation, and the evaluation of a mobile agent-based advanced service architecture for wireless Internet telephony. When a mobile agent carries services, subscription becomes a critical issue. The agent needs to be updated when the end-user subscribes or unsubscribes to services. Our architecture tackles the issue by proposing and evaluating two schemes: agent swapping and on-the-fly updating. Although, wireless Internet telephony is our prime target, the architecture is, to a large extent, independent of the underlying network and therefore applicable to Internet Telephony in general.

Value added services, or more simply - services, are the critical ingredient for the success and the survival of Internet Telephony. Services can be defined as anything that goes beyond two party voice calls. Some examples are multiparty gaming, customized stock quotes and call screening. This paper focuses on service creation in Internet Telephony. Service creation plays a major role in Internet Telephony because it enables openness and programmability by offering frameworks for the development of value added services. Two principal sets of standards have emerged for Internet Telephony: H.323 from the ITU-T and SIP from the IETF. No service creation framework comes with the H.323 set. Two frameworks come with the SIP set: the Call Processing Language (CPL) and the SIP common gateway interface (CGI). Besides the IETF, other forums such as Parlay and JAIN have proposed pertinent frameworks. The first part of the paper provides an overview of the service creation frameworks for Internet Telephony. A common characteristic of these frameworks is that they require knowledge that nonexperts may not have (e.g., scripts, programming languages). High-level service creation environments may help these nonexperts. The second part of the paper presents a case study on a high level service creation environment (SCE) where pre-defined graphical components are combined into services. The environment is discussed in detail along with the service logic execution environment (SLEE) where the services are executed. The SCE and SLEE make no assumption on the service creation framework supported by the network, and any of the standard frameworks could be used provided it offers the functionality abstracted in the graphical components. We have used the Parlay APIs as a framework and the prototype is built for a SIP environment. The prototype is described and the lessons we have learned are presented.

The virtual home environment (VHE) is a concept for service mobility. Several tool kits are under standardization for its realization. Beyond these tool kits, it is worth researching mobile agents. A few mobile agent based architectures have been proposed for VHE. In these architectures, mobile agents carry services and customized data and follow roaming end-users, by relocation or cloning. This paper focuses on how these agents and their clones are updated. It proposes two novel schemes for updating mobile service agents in VHE. The schemes rely on the agent's ability to notify a network entity of the changes made by end users to the customized data, and also on the agent's ability to update itself if requested. In the first scheme, the clones are updated remotely, whereas in the second scheme, an updating mobile agent tours all the clones to update them locally. We have derived requirements, articulated the schemes, built a prototype, and made measurements. The measurements indicate that the scheme where the network entity requests the updates directly performs better in most cases.

APIs, such as Parlay, open up networks to third party developers. They provide new opportunities for rapid and efficient service creation. However, they may be considered too low level by some developers. New service creation environments (SCE) with a higher level of abstraction lead to even faster and more efficient service creation. We report on our experiment in designing and implementing a SCE and a service logic execution environment (SLEE) for Parlay API in a session initiation protocol (SIP) environment. The approach is very promising although the scope of the services that can be created is still limited to services such as wake up call, call centres, where the calls are initiated by the applications.

The intelligent network (IN) represents the world-wide accepted basis for uniform provisioning of advanced telecommunication services. On the other hand IP-based communication is fast becoming a viable alternative for voice communications. Mobile agents offer unique opportunities for structuring and implementing open distributed service architectures, facilitated by the dynamic downloading and movement of service code to specific network nodes. In this paper, a new service architecture for IP telephony, based on the ITU-T standard H.323, is proposed. The implementation uses mobile agents and Jini as enabling technologies and existing architectural concepts taken from IN. This IP service architecture enables telecommunication services deployed through mobile service agents on a per-user basis, which results in several advantages when compared to centralized service architectures. The paper demonstrates that the flexible extensible architecture can accommodate not only existing services but is flexible enough to accommodate a wide variety of future services. In addition we show how the architecture addresses the full management life cycle of advanced services, from open third party creation, to subscription and utilization, and ultimately to maintenance and withdrawal.