No abstract

No abstract

With the rapid development of Internet of Things (IoT) technologies, fog computing has emerged as an extension to the cloud computing that relies on fog nodes with distributed resources at the edge of network. Fog nodes offer computing and storage resources opportunities to resource-less IoT devices which are not capable to support IoT applications with computation-intensive requirements. Furthermore, the closeness of fog nodes to IoT devices satisfies the low-latency requirements of IoT applications. However, due to the high IoT task offloading requests and fog resource limitations, providing an optimal task scheduling solution that considers a number of quality metrics is essential. In this paper, we address the task scheduling problem with the aim of optimizing the time and energy consumption as two QoS parameters in the fog context. First, we present a fog-based architecture for handling the task scheduling requests to provide the optimal solutions. Second, we formulate the task scheduling problem as an Integer Linear Programming (ILP) optimization model considering both time and fog energy consumption. Finally, we propose an advanced approach called Opposition-based Chaotic Whale Optimization Algorithm (OppoCWOA) to enhance the performance of the original WOA for solving the modelled task scheduling problem in a timely manner. The efficiency of the proposed OppoCWOA is shown by providing extensive simulations and comparisons with the original WOA and some existing meta-heuristic algorithms such as Artificial Bee Colony (ABC), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA).

In service-oriented computing, a user usually needs to locate a desired service for: (i) fulfilling her requirements or (ii) replacing a service, which disappears or is unavailable for some reasons, to perform an interaction. With the increasing number of services available within an enterprise and over the Internet, locating a service online may not be appropriate from the performance perspective, especially in large Internet-based service repositories. Instead, services usually need to be clustered according to their similarity. Thereafter, services in one or several clusters are necessary to be examined online during dynamic service discovery. In this paper, we propose to cluster data providing (DP) services using a refined fuzzy -means algorithm. We consider the composite relation between DP service elements (i.e., input, output, and semantic relation between them) when representing DP services in terms of vectors. A DP service vector is assigned to one or multiple clusters with certain degrees. In addition, we introduce some operations for managing service clusters, when new services emerge or existing services disappear or become unavailable. When grouping similar services into one cluster, while partitioning different services into different clusters, the capability of service search engine is improved significantly. We have prototyped our approach and the source code is freely available on the web. We have evaluated our clustering approach in different settings and the results are very promising.Note to Practitioners-DP services are common nowadays, and there are a huge number of DP services in the Internet-scale environment. Locating an appropriate DP service accurately and efficiently with respect to the requirements of a certain requestor is a challenging task. This work presents a novel clustering-oriented approach, which aims to group DP services into clusters offline leveraging the semantic description of these DP services, and provides operations for managing these clusters. The clustering procedure is conducted by means of a machine learning technique which is a refined fuzzy -means method. A DP service can be assigned to one or several clusters with certain degrees. DP service clusters constitute a cluster network. Operations are provided for facilitating the evolution of cluster network, when a DP service emerges or disappears sometime for some reason. A prototype has been implemented and the approach has been evaluated on two test collections of DP services considering factors impacting the efficiency. Our method can be readily used in industrial DP service repository for supporting DP service discovery and replacement.