检索结果-内蒙古大学图书馆

19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014

作者： Berekmeri, M. Serrano, D. Bouchenak, S. Marchand, N. Robu, B. GIPSA-Lab. BP 46 Grenoble38402 France Distributed Computer Systems Group LIG BP 53 Grenoble38402 France CNRS France Univ. Grenoble Alpes GrenobleF-38402 France

ISBN: (纸本)9783902823625

We are at the dawn of a huge data explosion therefore companies have fast growing amounts of data to process. For this purpose Google developed MapReduce, a parallel programming paradigm which is slowly becoming the de facto tool for Big Data analytics. Although to some extent its use is already wide-spread in the industry, ensuring performance constraints for such a complex system poses great challenges and its management requires a high level of expertise. This paper answers these challenges by providing the first autonomous controller that ensures service time constraints of a concurrent MapReduce workload. We develop the first dynamic model of a MapReduce cluster. Furthermore, PI feedback control is developed and implemented to ensure service time constraints. A feedforward controller is added to improve control response in the presence of disturbances, namely changes in the number of clients. The approach is validated online on a real 40 node MapReduce cluster, running a data intensive Business Intelligence workload. Our experiments demonstrate that the designed control is successful in assuring service time constraints. © IFAC.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Computational Offloading or Data Binding? Bridging the Cloud Infrastructure to the Proximity of the Mobile User

Computational Offloading or Data Binding? Bridging the Cloud...

引用

IEEE International Conference on Mobile Cloud Computing, Services, and Engineering

作者： Huber Flores Satish Narayana Srirama Rajkumar Buyya University of Tartu Institute of Computer Science Mobile Cloud Lab University of Melbourne Department of Computing and Information Systems Cloud Computing and Distributed Systems Laboratory (CLOUDS)

ISBN: (纸本)9781479944248

Mobile and cloud computing are converging as the prominent technologies that are leading the change to the post personal computing (PC) era. Computational offloading and data binding are the core techniques that foster to elastically augment the capabilities of low-power devices, such as smartphones. Mobile applications may be bonded to cloud resources by following a task delegation or code offloading criteria. In a delegation model, a handset can utilize the cloud in a service-oriented manner to delegate asynchronously a resource-intensive mobile task by direct invocation of the service. In contrast, in an offloading model, a mobile application is partitioned and analyzed so that the most computational expensive operations at code level can be identified and offloaded to a remote cloud-based surrogate. We compared in this paper, the mobile cloud computing models for offloading and delegation. We utilized our own frameworks for computational offloading and data binding in the analysis. While in principle, offloading and delegation are viable methods to augment the capabilities of the mobile devices with cloud power, they enrich the mobile applications from different perspectives at diverse computational scales.

关键词： Mobile Cloud Computing Access Models Code Offloading Task Delegation Middleware Mobile Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Computing infrastructure for big data processing

引用

Frontiers of computer Science 2013年第2期7卷 165-170页

作者： Ling LIU Distributed Data Intensive Systems Lab School of Computer Science Georgia Institute of TechnologyUSA Atlanta 30332

With computing systems undergone a fundamen- tal transformation from single-processor devices at the turn of the century to the ubiquitous and networked devices and the warehouse-scale computing via the cloud, the parallelism has become ubiquitous at many levels. At micro level, par- allelisms are being explored from the underlying circuits, to pipelining and instruction level parallelism on multi-cores or many cores on a chip as well as in a machine. From macro level, parallelisms are being promoted from multiple ma- chines on a rack, many racks in a data center, to the glob- ally shared infrastructure of the Internet. With the push of big data, we are entering a new era of parallel computing driven by novel and ground breaking research innovation on elas- tic parallelism and scalability. In this paper, we will give an overview of computing infrastructure for big data processing, focusing on architectural, storage and networking challenges of supporting big data paper. We will briefly discuss emerging computing infrastructure and technologies that are promising for improving data parallelism, task parallelism and encour- aging vertical and horizontal computation parallelism.

关键词： big data cloud computing data analytics elas-tic scalability heterogeneous computing GPU PCM bigdata processing

来源：评论

学校读者我要写书评

暂无评论

A Control Approach for Performance of Big Data systems

引用

IFAC Proceedings Volumes 2014年第3期47卷 152-157页

作者： M. Berekmeri D. Serrano S. Bouchenak N. Marchand B. Robu GIPSA-lab BP46 38402 Grenoble France Distributed Computer Systems Group LIG BP53 38402 Grenoble France CNRS France Univ. Grenoble Alpes F-38402 Grenoble France

关键词： disturbance rejection linear control systems control for computers cloud computing Big Data

来源：评论

学校读者我要写书评

暂无评论

Towards measurement-based self-management of performance properties in wireless sensor networks

Towards measurement-based self-management of performance pro...

引用

10th ACM International Symposium on Performance Evaluation of Wireless Ad Hoc, Sensor, and Ubiquitous Networks, PE-WASUN 2013 - Co-located with ACM MSWiM 2013

作者： Bachorek, Adam Palanisamy, Bagavathiannan Schmitt, Jens B. Disco / Distributed Computer Systems Lab. University of Kaiserslautern Kaiserslautern Germany

ISBN: (纸本)9781450323604

Ensuring the aspired outcome quality of network-based applications has ever implied an appropriate prognosis of the performance behavior the underlying communication structures will exhibit prior to potential optimization steps. However, the reliable forecast of correlative metrics is still a challenging task, especially in terms of wireless network systems that reject centralized or manual administration. In the context of our prospective self-management concept for autonomous analysis and control of volatile performance characteristics in Wireless Sensor Networks (WSNs), we relate a common network property known as packet transfer delay to various adjustable parameters peculiar to such radio network technologies. Our hands-on experiments reveal the reproducible influence of packet size, backoff period, and number of active neighbor nodes on the medium access procedure and involved performance indicators. By means of a closed formulation of permutable weighted drivers, we investigate the average-case predictability of inter-node end-to-end delays for arbitrary configurations of given network parameters. We validate our prediction method against basic multi-hop networking scenarios while verifying its practicability on a typical resource-scarce WSN platform. Leveraging measurement-driven inspection and conditional modeling of network attributes based on regression analysis, yield field test results substantiate the high precision of our approach to the estimation of performance-related WSN properties as the basis for application-aware performance optimization subject to projected complements. © 2013 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Democratic elections in faulty distributed systems

Democratic elections in faulty distributed systems

引用

14th International Conference on distributed Computing and Networking, ICDCN 2013

作者： Himanshu, Chauhan Garg, Vijay K. Parallel and Distributed Systems Lab. Department of Electrical and Computer Engineering University of Texas Austin TX United States

ISBN: (纸本)9783642356674

In this paper, we show that for elections in distributed systems the conversion from non-binary choices to binary choices does not always provide optimal results when the preferences of nodes are not identical. With this observation, we study the problem of conducting democratic elections in distributed systems in the form of social choice and social welfare functions with three or more candidates. We present some impossibility and possibility results for distributed democratic elections in presence of Byzantine behavior. We also discuss some existing election schemes, and present a new approach that attempts to mitigate the effects of Byzantine *** analyze the performance of these schemes through simulations to compare their efficacy in producing the most desirable social welfare rankings. © Springer-Verlag 2013.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Maximal antichain lattice algorithms for distributed computations

Maximal antichain lattice algorithms for distributed computa...

引用

14th International Conference on distributed Computing and Networking, ICDCN 2013

作者： Garg, Vijay K. Parallel and Distributed Systems Lab. Department of Electrical and Computer Engineering University of Texas at Austin Austin TX 78712 United States

ISBN: (纸本)9783642356674

The lattice of maximal antichains of a distributed computation is generally much smaller than its lattice of consistent global states. We show that a useful class of predicates can be detected on the lattice of maximal antichains instead of the lattice of consistent cuts obtaining significant (exponential for many cases) savings. We then propose new online and offline algorithms to construct and enumerate the lattice of maximal antichains. Previously known algorithm by Nourine and Raynoud [NR99, NR02] to construct the lattice takes O (n2m) time where n is the number of events in the computation, and m is the size of the lattice of maximal antichains. The algorithm by Jourdan, Rampon and Jard [JRJ94] takes O ((n + w2)wm) time where w is the width of the computation. All these algorithms assume as input the lattice of maximal antichains prior to the arrival of a new event. We present a new online incremental algorithm, OLMA, that computes the newly added elements to the lattice without requiring the prior lattice. Since the lattice may be exponential in the size of the computation, we get a significant reduction in the space complexity. The OLMA algorithm takes O (mw2 log w L) time and O (wL w log n) space where wL is the width of the lattice of maximal antichains. The lower space complexity makes our algorithm applicable for online global predicate detection in a distributed system. For the purposes of analyzing offline traces, we also propose new enumeration algorithms to traverse the lattice. © Springer-Verlag 2013.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Big data analytics as a service: Exploring reuse opportunities

Big data analytics as a service: Exploring reuse opportuniti...

引用

IEEE International Conference on Information Reuse and Integration (IRI)

作者： Ling Liu Distributed Data Intensive Systems Lab School of Computer Science College of Computing Georgia Institute of Technology USA

Summary form only given. As data scientists, we live in interesting times. Data has been the No. 1 fast growing phenomenon on the Internet for the last decade. Big data analytics have the potential to reveal deep insights hidden by big data that exceeds the processing capacity of existing systems, such as peer influence among customers, revealed by analyzing shoppers' transactions, social and geographical data. In the past 40 years, data was primarily used to record and report business activities and scientific events, and in the next 40 years data will be used also to derive new insights, to influence business decisions and to accelerate scientific discovery. The key challenge is to provide the right platforms and tools to make reasoning of big data easy and simple. In this keynote talk, I will explore reuse opportunities and challenges from multiple dimensions towards delivering big data analytics as a service. I will illustrate by example the importance and challenges of utilizing programmable algorithm abstractions for many seemingly domain-dependent data analytics tasks. Another reuse opportunity is to exploit unconventional data structures and big data processing constructs to simplify and speed up the big data processing.

关键词： Internet data analysis data structures

来源：评论

学校读者我要写书评

暂无评论

Neighborhood watch: On network coding throughput and key sharing

Neighborhood watch: On network coding throughput and key sha...

引用

2013 IEEE Global Communications Conference (GLOBECOM)

作者： Martin Strohmeier Ivan Martinovic Utz Roedig Karim El Defrawy Jens Schmitt University of Oxford UK InfoLab21 Lancaster University UK University of California Irvine USA Distributed Computer Systems Lab University of Kaiserslautern Germany

ISBN: (纸本)9781479913510

Network coding (NC) has frequently been promoted as an approach for improving throughput in wireless networks. Existing work has mostly focused on the fundamental aspects of NC, while constraints arising in real-world network deployments have not received much attention. In particular, NC requires network nodes to overhear each other's packets, which oftentimes contradicts many security standards that attempt to provide link-layer confidentiality, e.g., by utilizing pairwise encryption keys as is the case IEEE 802.11i and ZigBee. There is an inherent trade-off between gains from NC and link-layer security: if many nodes share the secret link-layer key, NC will improve throughput, yet a leakage of the key will affect many nodes. On the other hand, having distinct secret keys will increase resilience against key compromise, but will also minimize the coding gain. We formulate this security vs. performance trade-off as an optimization problem and evaluate the effectiveness of NC under different sizes of key-sharing groups and network topologies. Our results show that increasing the key-sharing group by a single node can result in a maximum coding gain between 1.3% and 13.7%.

关键词： Throughput Security Encoding Routing Peer-to-peer computing Wireless sensor networks Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Multi-agent multi-issue negotiations with incomplete information: A Genetic Algorithm based on discrete surrogate approach

Multi-agent multi-issue negotiations with incomplete informa...

引用

Congress on Evolutionary Computation

作者： Ahmed Kattan Yew-Soon Ong Edgar Galván-López AI Real-World Applications Lab Computer Science Department UQU Saudi Arabia School of Computer Engineering Nanyang Technological University Singapore Distributed Systems Group School of Computer Science and Statistics Trinity College Dublin Ireland

ISBN: (纸本)9781479904532

In this paper we present a negotiation agent based on Genetic Algorithm (GA) and Surrogate Modelling for a multi-player multi-issue negotiation model under incomplete information scenarios to solve a resource-allocation problem. We consider a multi-lateral negotiation protocol by which agents make offers sequentially in consecutive rounds until the deadline is reached. Agents' offers represent suggestions about how to divide the available resources among all agents participating in the negotiation. Each agent may “Accept” or “Reject” the offers made by its opponents through selecting the “Accept” or “Reject” option. The GA is used to explore the space of offers and surrogates used to model the behaviours of individual opponent agents for enhanced genetic evolution of offers that is agreeable upon all agents. The GA population comprises of solution individuals that are formulated as matrices where a specialised three different search operators that take the matrix representation into considerations are considered. Experimental studies of the proposed negotiation agent under different scenarios demonstrated that the negotiations by the agents completed in agreement before the deadline is reached, while at the same time, maximising profits.

关键词： Space exploration Mathematical model Approximation methods Genetic algorithms Computational modeling Equations Sociology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：