scholarly journals RGCA: A Reliable GPU Cluster Architecture for Large-Scale Internet of Things Computing Based on Effective Performance-Energy Optimization

Sensors ◽  
2017 ◽  
Vol 17 (8) ◽  
pp. 1799 ◽  
Author(s):  
Yuling Fang ◽  
Qingkui Chen ◽  
Neal N. Xiong ◽  
Deyu Zhao ◽  
Jingjuan Wang
Author(s):  
Yuling Fang ◽  
Qingkui Chen ◽  
Neal N. Xiong ◽  
Deyu Zhao ◽  
Jingjuan Wang

This paper aims to develop a low-cost, high-performance and high-reliability computing system to process large-scale data using common data mining algorithms in the Internet of Things computing. Considering the characteristics of IoT data processing, similar to mainstream high performance computing, we use a GPU cluster to achieve better IoT services. Firstly, we present an energy consumption calculation method (ECCM) based on WSN. Then, using the CUDA Programming model, we propose a Two-level Parallel Optimization Model (TLPOM) which exploits reasonable resource planning and common compiler optimization techniques to obtain the best blocks and threads configuration considering the resource constraints of each node. The key to this part is dynamic coupling Thread-Level Parallelism (TLP) and Instruction-Level Parallelism (ILP) to improve the performance of the algorithms without additional energy consumption. Finally, combining the ECCM and the TLPOM, we use the Reliable GPU Cluster Architecture (RGCA) to obtain a high-reliability computing system considering the nodes’ diversity, algorithm characteristics, etc. The results show that the performance of the algorithms significantly increased by 34.1%, 33.96% and 24.07% for Fermi, Kepler and Maxwell on average with TLPOM and the RGCA ensures that our IoT computing system provides low-cost and high-reliability services.


2018 ◽  
Vol 7 (3.12) ◽  
pp. 545
Author(s):  
Risabh Mishra ◽  
M Safa ◽  
Aditya Anand

Recent advances in wireless communication technologies and automobile industry have triggered a significant research interest in the field of Internet of Vehicles over the past few years.The advanced period of the Internet of Things is guiding the development of conventional Vehicular Networks to the Internet of Vehicles.In the days of Internet connectivity there is need to be in safe and problem-free environment.The Internet of Vehicles (IoV) is normally a mixing of three networks: an inter-vehicleNetwork, an intra-vehicle network, and a vehicle to vehicle network.Based on  idea of three networks combining into one, we define  Internet of Vehicles as a large-scale distributed system to wireless communication and information exchange between vehicle2X (X: vehicle, road, human and internet).It is a combined   network for supporting intelligent traffic management, intelligent dynamic information service, and intelligent vehicle control, representation of an application of the Internet of Things (IoT) technology for intelligent transportation system (ITS).  


2014 ◽  
Vol 2014 ◽  
pp. 1-15 ◽  
Author(s):  
Kwang-il Hwang ◽  
Sung-wook Nam

In order to construct a successful Internet of things (IoT), reliable network construction and maintenance in a sensor domain should be supported. However, IEEE 802.15.4, which is the most representative wireless standard for IoT, still has problems in constructing a large-scale sensor network, such as beacon collision. To overcome some problems in IEEE 802.15.4, the 15.4e task group proposed various different modes of operation. Particularly, the IEEE 802.15.4e deterministic and synchronous multichannel extension (DSME) mode presents a novel scheduling model to solve beacon collision problems. However, the DSME model specified in the 15.4e draft does not present a concrete design model but a conceptual abstract model. Therefore, in this paper we introduce a DSME beacon scheduling model and present a concrete design model. Furthermore, validity and performance of DSME are evaluated through experiments. Based on experiment results, we analyze the problems and limitations of DSME, present solutions step by step, and finally propose an enhanced DSME beacon scheduling model. Through additional experiments, we prove the performance superiority of enhanced DSME.


2012 ◽  
Vol 2012 ◽  
pp. 1-11 ◽  
Author(s):  
Federica Paganelli ◽  
David Parlanti

Current trends towards the Future Internet are envisaging the conception of novel services endowed with context-aware and autonomic capabilities to improve end users’ quality of life. The Internet of Things paradigm is expected to contribute towards this ambitious vision by proposing models and mechanisms enabling the creation of networks of “smart things” on a large scale. It is widely recognized that efficient mechanisms for discovering available resources and capabilities are required to realize such vision. The contribution of this work consists in a novel discovery service for the Internet of Things. The proposed solution adopts a peer-to-peer approach for guaranteeing scalability, robustness, and easy maintenance of the overall system. While most existing peer-to-peer discovery services proposed for the IoT support solely exact match queries on a single attribute (i.e., the object identifier), our solution can handle multiattribute and range queries. We defined a layered approach by distinguishing three main aspects: multiattribute indexing, range query support, peer-to-peer routing. We chose to adopt an over-DHT indexing scheme to guarantee ease of design and implementation principles. We report on the implementation of a Proof of Concept in a dangerous goods monitoring scenario, and, finally, we discuss test results for structural properties and query performance evaluation.


Author(s):  
Bin Cao ◽  
Yatian Zhang ◽  
Jianwei Zhao ◽  
Xin Liu ◽  
Lukasz Skonieczny ◽  
...  

2018 ◽  
Vol 33 (6) ◽  
pp. 749-767 ◽  
Author(s):  
Seppo Leminen ◽  
Mervi Rajahonka ◽  
Mika Westerlund ◽  
Robert Wendelin

Purpose This study aims to understand their emergence and types of business models in the Internet of Things (IoT) ecosystems. Design/methodology/approach The paper builds upon a systematic literature review of IoT ecosystems and business models to construct a conceptual framework on IoT business models, and uses qualitative research methods to analyze seven industry cases. Findings The study identifies four types of IoT business models: value chain efficiency, industry collaboration, horizontal market and platform. Moreover, it discusses three evolutionary paths of new business model emergence: opening up the ecosystem for industry collaboration, replicating the solution in multiple services and return to closed ecosystem as technology matures. Research limitations/implications Identifying business models in rapidly evolving fields such as the IoT based on a small number of case studies may result in biased findings compared to large-scale surveys and globally distributed samples. However, it provides more thorough interpretations. Practical implications The study provides a framework for analyzing the types and emergence of IoT business models, and forwards the concept of “value design” as an ecosystem business model. Originality/value This paper identifies four archetypical IoT business models based on a novel framework that is independent of any specific industry, and argues that IoT business models follow an evolutionary path from closed to open, and reversely to closed ecosystems, and the value created in the networks of organizations and things will be shareable value rather than exchange value.


2019 ◽  
Vol 6 (3) ◽  
pp. 4176-4187 ◽  
Author(s):  
Guorui Li ◽  
Jingsha He ◽  
Sancheng Peng ◽  
Weijia Jia ◽  
Cong Wang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document