Advancements in smart devices, wearable gadgets, sensors, and communication paradigm have enabled the vision of smart cities, pervasive healthcare, augmented reality and interactive multimedia, Internet of Every Thing (IoE), and cognitive assistance, to name a few. All of these visions have one thing in common, i.e., delay sensitivity and instant response. Various new technologies designed to work at the edge of the network, such as fog computing, cloudlets, mobile edge computing, and micro data centers have emerged in the near past. We use the name "edge computing" for this set of emerging technologies. Edge computing is a promising paradigm to offer the required computation and storage resources with minimal delays because of "being near" to the users or terminal devices. Edge computing aims to bring cloud resources and services at the edge of the network, as a middle layer between end user and cloud data centers, to offer prompt service response with minimal delay. Two major aims of edge computing can be denoted as: (a) minimize response delay by servicing the users' request at the network edge instead of servicing it at far located cloud data centers, and (b) minimize downward and upward traffic volumes in the network core. Minimization of network core traffic inherently brings energy efficiency and data cost reductions. Downward network traffic can be minimized by servicing set of users at network edge instead of service provider's data centers (e.g., multimedia and shared data) Content Delivery Networks (CDNs), and upward traffic can be minimized by processing and filtering raw data (e.g., sensors monitored data) and uploading the processed information to cloud. This survey presents a detailed overview of potentials, trends, and challenges of edge computing. The survey illustrates a list of most significant applications and potentials in the area of edge computing. State of the art literature on edge computing domain is included in the survey to guide readers towards the current trends and future opportunities in the area of edge computing.

With the emergence of the big data age, the issue of how to obtain valuable knowledge from a dataset efficiently and accurately has attracted increasingly attention from both academia and industry. This paper presents a Parallel Random Forest (PRF) algorithm for big data on the Apache Spark platform. The PRF algorithm is optimized based on a hybrid approach combining data-parallel and task-parallel optimization. From the perspective of data-parallel optimization, a vertical data-partitioning method is performed to reduce the data communication cost effectively, and a data-multiplexing method is performed is performed to allow the training dataset to be reused and diminish the volume of data. From the perspective of task-parallel optimization, a dual parallel approach is carried out in the training process of RF, and a task Directed Acyclic Graph (DAG) is created according to the parallel training process of PRF and the dependence of the Resilient Distributed Datasets (RDD) objects. Then, different task schedulers are invoked for the tasks in the DAG. Moreover, to improve the algorithm's accuracy for large, high-dimensional, and noisy data, we perform a dimension-reduction approach in the training process and a weighted voting approach in the prediction process prior to parallelization. Extensive experimental results indicate the superiority and notable advantages of the PRF algorithm over the relevant algorithms implemented by Spark MLlib and other studies in terms of the classification accuracy, performance, and scalability.

Cloud computing has emerged as the leading paradigm for information technology businesses. Cloud computing provides a platform to manage and deliver computing services around the world over the Internet. Cloud services have helped businesses utilize computing services on demand with no upfront investments. The cloud computing paradigm has sustained its growth, which has led to increase in size and number of data centers. Data centers with thousands of computing devices are deployed as back end to provide cloud services. Computing devices are deployed redundantly in data centers to ensure 24/7 availability. However, many studies have pointed out that data centers consume large amount of electricity, thus calling for energy-efficiency measures. In this survey, we discuss research issues related to conflicting requirements of maximizing quality of services (QoSs) (availability, reliability, etc.) delivered by the cloud services while minimizing energy consumption of the data center resources. In this paper, we present the concept of inception of data center energy-efficiency controller that can consolidate data center resources with minimal effect on QoS requirements. We discuss software-and hardware-based techniques and architectures for data center resources such as server, memory, and network devices that can be manipulated by the data center controller to achieve energy efficiency.Index Terms-Controller design, data centers, energy efficiency.

No abstract

No abstract

Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming, where large amounts of training samples and iterative operations are required to obtain high-quality weight parameters. In this paper, we focus on the time-consuming training process of large-scale CNNs and propose a Bi-layered Parallel Training (BPT-CNN) architecture in distributed computing environments. BPT-CNN consists of two main components: (a) an outer-layer parallel training for multiple CNN subnetworks on separate data subsets, and (b) an inner-layer parallel training for each subnetwork. In the outer-layer parallelism, we address critical issues of distributed and parallel computing, including data communication, synchronization, and workload balance. A heterogeneousaware Incremental Data Partitioning and Allocation (IDPA) strategy is proposed, where large-scale training datasets are partitioned and allocated to the computing nodes in batches according to their computing power. To minimize the synchronization waiting during the global weight update process, an Asynchronous Global Weight Update (AGWU) strategy is proposed. In the inner-layer parallelism, we further accelerate the training process for each CNN subnetwork on each computer, where computation steps of convolutional layer and the local weight training are parallelized based on task-parallelism. We introduce task decomposition and scheduling strategies with the objectives of thread-level load balancing and minimum waiting time for critical paths. Extensive experimental results indicate that the proposed BPT-CNN effectively improves the training performance of CNNs while maintaining the accuracy.

SUMMARY Data centers are experiencing a remarkable growth in the number of interconnected servers. Being one of the foremost data center design concerns, network infrastructure plays a pivotal role in the initial capital investment and ascertaining the performance parameters for the data center. Legacy data center network (DCN) infrastructure lacks the inherent capability to meet the data centers growth trend and aggregate bandwidth demands. Deployment of even the highest‐end enterprise network equipment only delivers around 50% of the aggregate bandwidth at the edge of network. The vital challenges faced by the legacy DCN architecture trigger the need for new DCN architectures, to accommodate the growing demands of the ‘cloud computing’ paradigm. We have implemented and simulated the state of the art DCN models in this paper, namely: (a) legacy DCN architecture, (b) switch‐based, and (c) hybrid models, and compared their effectiveness by monitoring the network: (a) throughput and (b) average packet delay. The presented analysis may be perceived as a background benchmarking study for the further research on the simulation and implementation of the DCN‐customized topologies and customized addressing protocols in the large‐scale data centers. We have performed extensive simulations under various network traffic patterns to ascertain the strengths and inadequacies of the different DCN architectures. Moreover, we provide a firm foundation for further research and enhancement in DCN architectures. Copyright © 2012 John Wiley & Sons, Ltd.

No abstract