Abstract

SUMMARYReducing power consumption has been an essential requirement for Cloud resource providers not only to decrease operating costs, but also to improve the system reliability. As Cloud computing becomes emergent for the Anything as a Service (XaaS) paradigm, modern real-time services also become available through Cloud computing. In this work, we investigate power-aware provisioning of virtual machines for real-time services. Our approach is (i) to model a real-time service as a real-time virtual machine request; and (ii) to provision virtual machines in Cloud data centers using Dynamic Voltage Frequency Scaling (DVFS) schemes. We propose several schemes to reduce power consumption by hard real-time services and power-aware profitable provisioning of soft real-time services.

No abstract

No abstract

Before discovering meaningful knowledge from big data systems, it is first necessary to build a data-gathering infrastructure. Among many feasible data sources, wireless sensor networks (WSNs) are rich big data sources: a large amount of data is generated by various sensor nodes in large-scale networks. However, unlike typical wireless networks, WSNs have serious deficiencies in terms of data reliability and communication owing to the limited capabilities of the nodes. Moreover, a considerable amount of sensed data are of no interest, meaningless, and redundant when a large number of sensor nodes is densely deployed. Many studies address the existing problems and propose methods to overcome the limitations when constructing big data systems with WSN. However, a published paper that provides deep insight into this research area remains lacking. To address this gap in the literature, we present a comprehensive survey that investigates state-of-the-art research work on introducing WSN in big data systems. Potential applications and technical challenges of networks and infrastructure are presented and explained in accordance with the research areas and objectives. Finally, open issues are presented to discuss promising directions for further research.

Generally, various traffic requirements in wireless sensor network are mostly dependent on specific application types, that is, eventdriven, continuous, and query-driven types. In these applications, real-time delivery is one of the important research challenges. However, due to harsh networking environment around a node, many researchers usually take different approach from conventional networks. In order to discuss and analyze the advantage or disadvantage of these approaches, some comprehensive survey literatures were published; however they are either out of date or compiled for communication protocols on single layer. Based on this deficiency, in this paper, we present the up-to-date research approaches and discuss the important features related to real-time communications in wireless sensor networks. As for grouping, we categorize the approaches into hard, soft, and firm real-time model. Furthermore, in all these categories, research has been focused on MAC and scheduling and routing according to research area or objective in second level. Finally, the article also suggests potential directions for future research in the field.

No abstract

Cloud computing has received a lot of attention from both researcher and developer in last decade due to its unique structure of providing services to the user. As the digitalization of world, heterogeneous devices, and with the emergence of Internet of Things (IoT), these IoT devices produce different type of data with distinct frequency, which require real‐time and latency sensitive services. This provides great challenge to cloud computing framework. Fog computing is a new framework to accompaniment cloud platform and is proposed to extend services to the edge of the network. In fog computing, the entire user's tasks are offloaded to distributed fog nodes to the edge of network to avoid delay sensitivity. We select fog computing network dwell different set of fog nodes to provide required services to the users. Allocation of defined resource to the users in order to achieve optimal result is a big challenge. Therefore, we propose dynamic resource allocation strategy for cloud, fog node, and users. In the framework, we first formulate the ranks of fog node using TOPSIS to identify most suitable fog node for the incoming request. Simultaneously logistic regression calculates the load of individual fog node and updates the result to send back to the broker for next decision. Simulation results demonstrate that the proposed scheme undoubtedly improves the performance and give accuracy of 98.25%.