Cloud computing with its three key facets (i.e., IaaS, PaaS, and SaaS) and its inherent advantages (e.g., elasticity and scalability) still faces several challenges. The distance between the cloud and the end devices might be an issue for latencysensitive applications such as disaster management and content delivery applications. Service Level Agreements (SLAs) may also impose processing at locations where the cloud provider does not have data centers. Fog computing is a novel paradigm to address such issues. It enables provisioning resources and services outside the cloud, at the edge of the network, closer to end devices or eventually, at locations stipulated by SLAs. Fog computing is not a substitute for cloud computing but a powerful complement. It enables processing at the edge while still offering the possibility to interact with the cloud. This article presents a comprehensive survey on fog computing. It critically reviews the state of the art in the light of a concise set of evaluation criteria. We cover both the architectures and the algorithms that make fog systems. Challenges and research directions are also introduced. In addition, the lessons learned are reviewed and the prospects are discussed in terms of the key role fog is likely to play in emerging technologies such as Tactile Internet.

Abstract-Wireless Sensor Networks (WSNs) are the key components of the emerging Internet-of-Things (IoT) paradigm. They are now ubiquitous and used in a plurality of application domains. WSNs are still domain specific and usually deployed to support a specific application. However, as WSNs' nodes are becoming more and more powerful, it is getting more and more pertinent to research how multiple applications could share a very same WSN infrastructure. Virtualization is a technology that can potentially enable this sharing. This paper is a survey on WSN virtualization. It provides a comprehensive review of the state-of-the-art and an in-depth discussion of the research issues. We introduce the basics of WSN virtualization and motivate its pertinence with carefully selected scenarios. Existing works are presented in detail and critically evaluated using a set of requirements derived from the scenarios. The pertinent research projects are also reviewed. Several research issues are also discussed with hints on how they could be tackled. perform computations and communicate [2]. The most obvious drawback of the current WSNs is that they are domain-specific and task-oriented, tailored for particular applications with little or no possibility of reusing them for newer applications. This strategy is inefficient and leads to redundant deployments when new applications are contemplated. With the introduction of the IoT, it is not unrealistic to envision that future WSN deployments will have to support multiple applications simultaneously. Index Terms-Virtualization is a well-established concept that allows the abstraction of actual physical computing resources into logical units, enabling their efficient usage by multiple independent users [3]. It is a promising technique that can allow the efficient utilization of WSN deployments, as multiple applications will be able to co-exist on the same virtualized WSN. Virtualization is a key technique for the realization of the Future Internet [4] and it is indeed quite pertinent to explore it in the context of WSNs.Virtualizing WSNs brings with it many benefits; for example, even applications that were not envisioned a priori may be able to utilize existing WSN deployments. A second, related benefit is the elimination of tight coupling between WSN services/applications and WSN deployments. This allows experienced as well as novice application developers to develop innovative WSN applications without needing to know the technical details of the WSNs involved. Another benefit is that WSN applications and services can utilize as well as be utilized by third-party applications. It can also help to define a business model, with roles such as physical WSN provider, virtual WSN provider and WSN service provider.The WSN virtualization concept can be applied to several interesting application areas. Recent advances in smart phones and autonomous vehicles [5] have made it possible to have multiple on-board sensors on them. Mobile crowd sensing is one area that can take advantage of virtuali...

No abstract

n the last few years, wireless sensor networks (WSNs) have become ubiquitous and are being used in a broad array of application domains, including healthcare, agriculture, surveillance, and security. These WSNs are composed of small-scale nodes that have the ability to sense, compute, and communicate [1]. While early sensor nodes were resource-constrained with limited capabilities, recent advances in sensor hardware technology have made it possible to produce sensor nodes that have more processing power and memory, and prolonged battery life.Virtualization is a key technique for the realization of the future Internet, and it is indeed quite pertinent to explore it in the context of WSNs. Virtualization makes it possible to present physical computing resources by abstracting them into logical units, enabling their efficient usage by multiple independent users, including multiple concurrent applications [2]. Furthermore, it allows for the deployment of applications that were not even envisioned during an infrastructure's initial deployment.To date, realizations of WSNs have been domain-specific and task-oriented. Applications are bundled with a WSN at the time of deployment, and it is next to impossible to use the same WSN for another application. This leads to redundant deployments and underutilization of these resources. There are two approaches to allow multiple applications to access deployed WSN resources. One is to allow multiple applications to share the data gathered from a WSN. In this approach, a sink/gateway node collects all the data from the WSN and shares it among multiple users. For example, in [3], WSNs are merged into the cloud by sending observed sensor data through a host manager that lies outside the WSN. The host manager simply collects the sensor data, profiles/aggregates it, and then allows multiple applications to use it for their own purposes.The second approach is to use the capabilities of the individual sensor nodes to execute multiple application tasks concurrently, and allow applications to group these sensor nodes together according to their requirements. The key difference between the two approaches is that the former approach allows the sharing of WSN data among multiple applications, while the latter allows sharing of WSN nodes by multiple applications. This article is focused on the second approach because it makes it possible to provision more innovative applications over the deployed WSNs, even applications that were not envisioned a priori. This will greatly improve the efficiency of deployed WSNs and will also encourage new business models.This article introduces the WSN virtualization concept, critically reviews the state of the art in WSN virtualization, and proposes a new early architecture that focuses on fixed WSNs. We illustrate the potential of the architecture by instantiating it for a fire monitoring scenario [4] in which multiple applications share the same WSN. We have built a prototype to demonstrate its feasibility and to measure its performance. We also identify ...

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.

Next Generation Networks (NGNs), as envisioned by ITU-T, are packet-based networks, capable of provisioning consistent and ubiquitous services to end-users, independently of the network, the access technology and the devices used. RESTful Web services are now being contemplated as a technology for service provisioning in NGNs. They are emerging as an alternative, which may be more adequate than SOAPbased Web services in some cases. SOAP-based Web services are modular applications that can be discovered and invoked over a network. RESTful Web services, on the other hand, are defined as a network architectural style for distributed hypermedia systems. This paper presents a survey on RESTful Web services for service provisioning in NGNs. It introduces the concept of RESTful Web services and reviews the state-of-the-art of RESTful-based-service provisioning in NGNs. It also provides an evaluation of the overall suitability of RESTful Web services for service provisioning in NGNs, and discusses research directions. RESTful Web services do show significant potential for service provisioning in NGNs. However, open issues such as publication/discovery and mechanisms for the development of complex session-based services need to be solved before its full potential can be realized.

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 (NFV) 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 (ILP) and propose a cost efficient Proactive VNF placement and chaining (CPVNF) 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.

This paper has been accepted for publication in IEEE Communications Surveys and Tutorials. The copyrights are with IEEE. Abstract: Content Delivery Networks (CDNs) have gained immense popularity over the years. Replica server placement is a key design issue in CDNs. It entails placing replica servers at meticulous locations, such that cost is minimized and Quality of Service (QoS) of end-users is satisfied. Many replica server placement models have been proposed in the literature of traditional CDN. As the CDN architecture is evolving through the adoption of emerging paradigms, such as, cloud computing and Network Functions Virtualization (NFV), new algorithms are being proposed. In this paper, we present a comprehensive survey of replica server placement algorithms in traditional and emerging paradigm based CDNs. We categorize the algorithms and provide a summary of their characteristics. Besides, we identify requirements for an efficient replica server placement algorithm and perform a comparison in the light of the requirements. Finally, we discuss potential avenues for further research in replica server placement in CDNs.