检索结果-内蒙古大学图书馆

Network Cost-Aware Geo-Distributed data analytics system

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED systemS 2022年第6期33卷 1407-1420页

作者： Oh, Kwangsung Zhang, Minmin Chandra, Abhishek Weissman, Jon Univ Nebraska Dept Comp Sci Omaha NE 68182 USA Univ Minnesota Twin Cities Dept Comp Sci Minneapolis MN 55455 USA

Many geo-distributed data analytics (GDA) systems have focused on the network performance-bottleneck: inter-data center network bandwidth to improve performance. Unfortunately, these systems may encounter a cost-bottleneck ($) because they have not considered data transfer cost ($), one of the most expensive and heterogeneous resources in a multi-cloud environment. In this article, we present Kimchi, a network cost-aware GDA system to meet the cost-performance tradeoff by exploiting data transfer cost heterogeneity to avoid the cost-bottleneck. Kimchi determines cost-aware task placement decisions for scheduling tasks given inputs including data transfer cost, network bandwidth, input data size and locations, and desired cost-performance tradeoff preference. In addition, Kimchi is also mindful of data transfer cost in the presence of dynamics. Kimchi has been applied to two common GDA MapReduce models: synchronous barrier and asynchronous push-based shuffle. A Kimchi prototype has been implemented on Spark, and experiments show that it reduces cost by 5% similar to 24% without impacting performance and reduces query execution time by 45% similar to 70% without impacting cost compared to other baseline approaches centralized, vanilla Spark, and bandwidth-aware (e.g., Iridium). More importantly, Kimchi allows applications to explore a much richer cost-performance tradeoff space in a multi-cloud environment.

关键词： Task analysis data transfer Bandwidth Wide area networks Sparks Iridium Distributed databases Geo-distributed data multi-DCs multi cloud providers data analytics system

来源：评论

学校读者我要写书评

暂无评论

FPGA-Assisted Real-Time RF Wireless data analytics system: Design, Implementation, and Statistical Analyses

引用

IEEE ACCESS 2020年 8卷 4383-4396页

作者： Khan, Zaheer Lehtomaki, Janne J. Univ Oulu Ctr Wireless Commun Oulu 90014 Finland

A wide range of new ultra reliable low latency communication (URLLC) applications in next generation (NG) wireless systems demand real-time radio frequency (RF) data analytics of channel utilization (CU) that can help in making proactive resource allocation decisions. However, such real-time RF data analytics require processing of tens of millions of in-phase and quadrature (IQ) samples per second and sending huge quantities of samples to a resource allocating entity is not practical. We present design and implementation of an RF data analytics system which utilizes field-programmable gate arrays (FPGAs) at the network edge to process real-time streaming IQ samples from RF transceiver. FPGAs process millions of samples per second and output low-overhead descriptive statistics of wireless CU, such as mean CU values, maximum CU values, and entire histograms to obtain probability distribution of CU values, to a resource controller server where a quantile estimation based technique is used to detect congestion in CU in real-time. The FPGA-based modules are implemented on Xilinx's Zynq-7000 devices mounted with RF transceivers. We evaluate the performance of the implemented analytics system using extensive measurements, testing, and statistical analyses that are performed in both laboratory and over-the-air environments.

关键词： ARM channel utilization data analytics system FPGA histogram measurements prototyping quantile radio frequency wireless systems Xilinx

来源：评论

学校读者我要写书评

暂无评论

Server-Edge dualized closed-loop data analytics system for cyber-physical system application

引用

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING 2021年 67卷 102040-102040页

作者： Kim, Jun Lee, Ju Yeon Korea Inst Ind Technol 143 Hangaul Ro Ansan 34141 South Korea

In this research, we propose a system architecture of the server-edge dualized closed-loop data analytics system for cyber-physical system (CPS) application. We define six essential components for the data analytics system for CPS application: (1) the cyber model, (2) the data analytics module, (3) the data analysis model execution module, (4) the decision making module, (5) the system control module, and (6) the visualization module. We then propose an architecture of dualized closed-loop data analytics with server and edge-computing devices. The proposed dualized architecture of the data analytics system has advantages in handling the three issues of applying data analytics systems to the manufacturing context: (1) the system overload issue of the data analytics module due to large volumes of data, (2) the automation issue in the sequences of data analysis model generation, data analysis module execution, and system control, and (3) the real-time issue of data analysis model execution. In particular, a PMML-based data analysis model information parsing structure is proposed to deal with the automation issue. A case study that applies the proposed server-edge dualized closed-loop data analytics system for CPS application to the die-casting factory in Korea is introduced.

关键词： Cyber-physical system Edge-computing Server-edge dualized system data analytics system Closed-loop data analytics system

来源：评论

学校读者我要写书评

暂无评论

Differentially Oblivious data Analysis With Intel SGX: Design, Optimization, and Evaluation

引用

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2022年第6期19卷 3741-3758页

作者： Wu, Pengfei Li, Qi Ning, Jianting Huang, Xinyi Wu, Wei Natl Univ Singapore Sch Comp Singapore 119077 Singapore Tsinghua Univ Inst Network Sci & Cyberspace Beijing 100084 Peoples R China Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China Fujian Normal Univ Coll Comp & Cyber Secur Fujian Prov Key Lab Network Secur & Cryptol Fuzhou 350007 Fujian Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Security Beijing 100093 Peoples R China Fujian Normal Univ Coll Math & Stat Fujian Prov Key Lab Network Secur & Cryptol Fuzhou 350007 Fujian Peoples R China

A privacy-preserving data analytics system enables a cloud user to perform the distributed job in a secure manner such that the data privacy can be guaranteed during the cloud-outsourced computation. However, many SGX-based solutions are vulnerable to some side-channel attacks, including the access pattern leakage from both network and memory. Several data-oblivious algorithms with full obliviousness have been proposed in the literature, but they are impractical to be used in the cloud due to the expensive computational overhead. In this article, we propose a DPSpark system with the security defined in a notion of (epsilon, delta)-differentially private obliviousness ((epsilon, delta)-DPO), which relaxes full obliviousness to enable an efficiency improvement. Based on this definition, we present a perturbation-shuffle-analysis (PSA) computing architecture and design several typical differentially oblivious operators. In further, we optimize the system efficiency by reducing the number of oblivious shuffles and choosing an appropriate privacy budget. Finally, we benchmark the system in different parameters. The experimental results show that DPSpark significantly outperforms two state-of-the-art solutions, only with 10.1-85.4 percent additional overhead performing an SGX-based data analysis application.

关键词： data analytics system Intel SGX access pattern privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

Towards Dependency-Aware Cache Management for data analytics Applications

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2022年第1期10卷 706-723页

作者： Yu, Yinghao Zhang, Chengliang Wang, Wei Zhang, Jun Ben Letaief, Khaled Hong Kong Univ Sci & Technol Kowloon Dept Elect & Comp Engn Clear Water Bay Hong Kong Peoples R China Hong Kong Univ Sci & Technol Kowloon Dept Comp Sci & Engn Clear Water Bay Hong Kong Peoples R China Hong Kong Polytech Univ Kowloon Dept Elect & Informat Engn Hung Hom Hong Kong Peoples R China

Memory caches are being used aggressively in today's data analytics systems such as Spark, Tez, and Piccolo. The significant performance impact of caches and their limited sizes call for efficient cache management in data analytics clusters. However, prevalent data analytics systems employ rather simple cache management policies-notably Least Recently Used (LRU) and Least Frequently Used (LFU)-that are oblivious to the application semantics of data dependency, expressed as directed acyclic graphs (DAGs). Without this knowledge, cache management can, at best, be performed by "guessing" the future data access patterns based on history, which frequently results in inefficient, erroneous caching with a low hit rate and a long response time. Worse still, the lack of data dependency knowledge makes it impossible to retain the all-or-nothing cache property of cluster applications, in that a compute task cannot be sped up unless all the dependent data has been kept in the main memory. In this paper, we propose a novel cache replacement policy, named Least Reference Count (LRC), which exploits the application's data dependency information to optimize the cache management. LRC keeps track of the reference count of each data block, defined as the number of dependent child blocks that have not been computed yet, and always evicts the block with the smallest reference count. Furthermore, we incorporate the all-or-nothing requirement into LRC by coordinately managing the reference counts of all the input data blocks for the same computation. We demonstrate the efficacy of LRC through both empirical analysis and cluster deployments against popular benchmarking workloads. Our Spark implementation shows that, the proposed policies well address the all-or-nothing requirement and significantly improve the cache performance. Compared with LRU and a recently proposed caching policy called MEMTUNE, LRC improves the caching performance of typical workloads in production clusters by 22 and

关键词： Cloud computing data analytics system cache management dependency-awareness all-or-nothing caching

来源：评论

学校读者我要写书评

暂无评论

data analytics systems and SME type - a Design Science Approach 22

Data Analytics Systems and SME type - a Design Science Appro...

引用

22nd International Conference on Knowledge-Based and Intelligent Information and Engineering systems (KES)

作者： Ulrich, Patrick Becker, Wolfgang Fibitz, Alexandra Reitelshofer, Eva Schuhknecht, Felix Aalen Univ Beethovenstr 1 D-73430 Aalen Germany Univ Bamberg Feldkirchenstr 21 D-96045 Bamberg Germany

Although the current literature on large amounts of data and data analysis is growing rapidly, profound assumptions and practical tasks are still missing in some areas. This paper focuses on SMEs and their approach to data analysis issues and their implementation. With the methodology of design research we use characteristics of SME types and link them with the corresponding requirements of the compatible data analysis system to increase performance. We derive a framework that serves as a starting point for further research The results indicate that there are several requirements that companies need to consider when realigning or restructuring their internal database. Depending on the type of SME, we choose a performance grid analysis based on the characteristics and requirements of data analysis systems. (C) 2018 The Authors. Published by Elsevier Ltd.

关键词： Design Science Research data analytics system SME Cycle Big data Decision Making

来源：评论

学校读者我要写书评

暂无评论

Framing a Sustainable Architecture for data analytics systems: An Exploratory Study

引用

IEEE ACCESS 2018年 6卷 61600-61613页

作者： Zhao, Jitong Liu, Yan Zhou, Peng Tongji Univ Sch Software Engn Shanghai 201804 Peoples R China

data analytics systems (DASs) with big data capabilities have started playing a promising role in online service ecosystems and large-scaled interconnected systems of many enterprises. The rapid development of analytics models and technologies, along with affordable infrastructures and accumulated data repositories, leads to encouraging expectations on DAS, while also bringing challenges in terms of how to deal with the increased development complexity. However, systematic methodologies for designing a sustainable DAS are still missing. To harness the dynamics raised by technology evolution, ambiguous requirements, under-explored data environments, and so on, framing a sustainable software architecture turns out to be a critical task. By exploring the complex nature of DAS, we propose a novel approach, sustainable architecture development for DAS (SstAD-DAS), to provide practical guidelines for architecture development. A shock absorber mechanism is presented to harness the dynamics of DAS and facilitate the development of a sustainable architecture, the "long decision chain" challenges are handled with a generic process model, and collaborations and responsibilities of participants are suggested to enable better model implementation. SstAD-DAS allows architects to accommodate the long decision chain, leverage skill sets from multiple contributors, and evaluate architectural decisions continuously. Finally, this paper demonstrates the capability and usability of SstAD-DAS by sharing experiences and observations from the continuous development of an intelligence analysis system.

关键词： Architecture sustainability BPMN data analytics system architecture development method

来源：评论

学校读者我要写书评

暂无评论

Maxson: Reduce Duplicate Parsing Overhead on Raw data 36

Maxson: Reduce Duplicate Parsing Overhead on Raw Data

引用

IEEE 36th International Conference on data Engineering (ICDE)

作者： Shi, Xuanhua Zhang, Yipeng Huang, Hong Hu, Zhenyu Jin, Hai Shen, Huan Zhou, Yongluan He, Bingsheng Li, Ruibo Zhou, Keyong Huazhong Univ Sci & Technol Natl Engn Res Ctr Big Data Technol & Syst Serv Comp Technol & Syst Lab Wuhan Hubei Peoples R China Univ Copenhagen Dept Comp Sci Copenhagen Denmark Natl Univ Singapore Singapore Singapore Alibaba Grp Hangzhou Peoples R China

ISBN: (数字)9781728129037

ISBN: (纸本)9781728129037

JSON is a very popular data format in many applications in Web and enterprise. Recently, many data analytical systems support the loading and querying JSON data. However, JSON parsing can be costly, which dominates the execution time of querying JSON data. Many previous studies focus on building efficient parsers to reduce this parsing cost, and little work has been done on how to reduce the occurrences of parsing. In this paper, we start with a study with a real production workload in Alibaba, which consists of over 3 million queries on JSON. Our study reveals significant temporal and spatial correlations among those queries, which result in massive redundant parsing operations among queries. Instead of repetitively parsing the JSON data, we propose to develop a cache system named Maxson for caching the JSON query results (the values evaluated from JSONPath) for reuse. Specifically, we develop effective machine learning-based predictor with combining LSTM (long short-term memory) and CRF (conditional random field) to determine the JSONPaths to cache given the space budget. We have implemented Maxson on top of SparkSQL. We experimentally evaluate Maxson and show that 1) Maxson is able to eliminate the most of duplicate JSON parsing overhead, 2) Maxson improves end-to-end workload performance by 1.5-6.5x.

关键词： JSON parsing semi-structured format data analytics system

来源：评论

学校读者我要写书评

暂无评论

data analytics systems and SME type – a Design Science Approach

引用

Procedia Computer Science 2018年 126卷 1162-1170页

作者： Patrick Ulrich Wolfgang Becker Alexandra Fibitz Eva Reitelshöfer Felix Schuhknecht Aalen University Beethovenstr. 1 73430 Aalen Germany University of Bamberg Feldkirchenstr. 21 96045 Bamberg Germany

Although the current literature on large amounts of data and data analysis is growing rapidly, profound assumptions and practical tasks are still missing in some areas. This paper focuses on SMEs and their approach to data analysis issues and their implementation. With the methodology of design research we use characteristics of SME types and link them with the corresponding requirements of the compatible data analysis system to increase performance. We derive a framework that serves as a starting point for further research. The results indicate that there are several requirements that companies need to consider when realigning or restructuring their internal database. Depending on the type of SME, we choose a performance grid analysis based on the characteristics and requirements of data analysis systems.

关键词： Design Science Research data analytics system SME Cycle Big data Decision Making

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：