检索结果-内蒙古大学图书馆

Serial failure diagnosis of a distributed processing system by Petri nets

COMPUTERS & MATHEMATICS WITH APPLICATIONS 1996年第9期31卷 57-62页

作者： Katsumata, M Kurihara, M Ohuchi, A Sugasawa, Y NIHON UNIV FAC IND TECHNOLDEPT ENGN MATHNARASHINOCHIBA 275JAPAN

Recently network technologies have rapidly developed, and distributed processing systems which are of asynchronous and parallel characteristics are very useful in various fields. However, it is very difficult to figure out the factors of failure of such systems. In this paper, we make a Petri net model of a simple distributed processing system consisting of a main system and a subsystem, and show how to diagnose serial failure of the system by analyzing invariant sets of the model.

关键词： Petri net T-invariant distributed processing system failure diagnosis

来源：评论

学校读者我要写书评

暂无评论

Data Sampling methods in the ALICE O² distributed processing system

引用

COMPUTER PHYSICS COMMUNICATIONS 2021年 258卷 107581-107581页

作者： Konopka, Piotr von Haller, Barthelemy AGH Univ Sci & Technol Fac Elect Engn Automat Comp Sci & Biomed Engn Al Mickiewicza 30 PL-30059 Krakow Poland European Org Nucl Res CERN CH-1211 Geneva 23 Switzerland

The ALICE experiment at the CERN LHC focuses on studying the quark-gluon plasma produced by heavy-ion collisions. Starting from 2021, it will see its input data throughput increase a hundredfold, up to 3.5 TB/s. To cope with such a large amount of data, a new online-offline computing system, called O-2, will be deployed. It will synchronously compress the data stream by a factor of 35 down to 100 GB/s before storing it permanently. One of the key software components of the system will be the data Quality Control (QC). This framework and infrastructure is responsible for all aspects related to the analysis software aimed at identifying possible issues with the data itself, and indirectly with the underlying processing done both synchronously and asynchronously. Since analyzing the full stream of data online would exceed the available computational resources, a reliable and efficient sampling will be needed. It should provide a few percent of data selected randomly in a statistically sound manner with a minimal impact on the main dataflow. Extra requirements include e.g. the option to choose data corresponding to the same collisions over a group of computing nodes. In this paper the design of the O-2 Data Sampling software is presented. In particular, the requirements for pseudo-random number generators to be used for sampling decisions are highlighted, as well as the results of the benchmarks performed to evaluate different possibilities. Finally, a large scale test of the O-2 Data Sampling is reported. (C) 2020 The Author(s). Published by Elsevier B.V.

关键词： CERN ALICE O-2 Data Sampling Message-based system distributed processing system Data quality control Pseudo-random number generators

来源：评论

学校读者我要写书评

暂无评论

OPERATIONAL SURVIVABILITY IN GRACEFULLY DEGRADING distributed-processing systemS

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 1986年第6期12卷 693-704页

作者： MARTIN, EW DEMILLO, RA GEORGIA INST TECHNOL DEPT INFORMAT & COMP SCIATLANTAGA 30332

The use of experimental methods and statistical analysis techniques to study factors influencing operational survivability in gracefully degrading systems is considered. Survivability data are created using a statistically designed experiment in conjunction with a simulation model of network survivability. Thirty-two factors having stable regression coefficients are employed to identify 10 regression models explaining survivability. Influential characteristics include the distributed system network, the application system, and the distribution policy. Nine factors are discovered in all models: 1. the number of nodes in the distributed system, 2. distributed system connectivity, 3. module memory requirements, 4. module-to-module interaction frequency, 5. distribution policy, 6. percent of nodes lost, 7. initial assignment results, 8. available processing capacity at the end of the subcase, and 9. the interaction of all application related variables.

关键词： Topology Network Topology Degradation Memory Management distributed processing Analytical Models Computational Modeling Operational Survivability distributed processing system Graceful Degradation

来源：评论

学校读者我要写书评

暂无评论

Architectural styles for distributed processing systems and practical selection method

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2002年第8期44卷 459-472页

作者： Morisawa, Y Inoue, K Torii, K Nihon Unisys Ltd Koto Ku Tokyo 1358560 Japan Nara Inst Sci & Technol Grad Sch Informat Sci Ikoma Nara 6300101 Japan Osaka Univ Grad Sch Engn & Sci Toyonaka Osaka 5608531 Japan

The software architecture of a system has influences against various software characteristics of the system such as efficiency, reliability, maintainability, etc. For supporting to design the software architecture, we have developed architectural styles for distributed processing systems. The styles classify the architecture for distributed processing systems into nine categories based on the location of data storage and the type of processing between a client and a server. This paper describes our architectural styles and proposes a simple but practical method to select an appropriate architectural style for developing an application system. The selection method introduces the characterization of architectural styles and the characteristic charts to visualize their characteristics of architectural styles. Next, we propose a method to select an appropriate architectural style using the conformity between characteristic charts of a system and architectural styles. We have verified the applicability of this selection method using our customers' real application systems. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： architectural style distributed computing model distributed processing system software architecture

来源：评论

学校读者我要写书评

暂无评论

Access Control for distributed processing systems: Use Cases and General Considerations 3

Access Control for Distributed Processing Systems: Use Cases...

引用

3rd IEEE International Conference on Collaboration and Internet Computing (CIC)

作者： Li, Ang Li, Qinghua Hu, Vincent C. Univ Arkansas Dept Comp Sci & Comp Engn Fayetteville AR 72701 USA Natl Inst Stand & Technol Comp Secur Div Gaithersburg MD 20899 USA

ISBN: (纸本)9781538625651

Access control (AC) is critical for preventing sensitive information from unauthorized access. Various AC systems have been proposed and enforced in different types of information systems (e.g., bank and military). However, existing AC systems cannot thoroughly address the challenges in emerging distributed processing systems (DPS), such as Big Data (BD) and Cloud, due to their dynamic and complex architecture. Generally, AC for DPS needs to consider the protection for collaboration among distributed processing domains. Even though some DPS architectures were proposed to address DPS challenges, most of them only focus on processing capabilities without consideration of AC. Even with some inclusion of security in recent DPS, they are mostly ad hoc and patch efforts. In this paper, we analyze the general features and use cases of BD and Cloud, which are two of most widely applied DPS applications, and propose a set of general and comprehensive considerations for AC in DPS, which can provide a guideline for designing AC systems for DPS.

关键词： Access Control distributed processing system Design Considerations

来源：评论

学校读者我要写书评

暂无评论

Batrun: Utilizing idle workstations for Large-Scale computing

引用

IEEE PARALLEL & distributed TECHNOLOGY 1996年第2期4卷 41-48页

作者： Tandiary, F Kothari, SC Dixit, A Anderson, EW IOWA STATE UNIV SCI & TECHNOL DEPT COMP SCI AMES IA 50011 USA IOWA STATE UNIV SCI & TECHNOL DEPT PHYS AMES IA 50011 USA

The Batrun distributed processing system locates idle workstations in a cluster and uses them as one virtual computer for batch processing. To guarantee that local users have top priority for their machines Batrun pre... 详细信息

关键词： Batch processing Cluster Of Workstations distributed processing system

来源：评论

学校读者我要写书评

暂无评论

AN LC BRANCH-AND-BOUND ALGORITHM FOR THE MODULE ASSIGNMENT PROBLEM

引用

INFORMATION processing LETTERS 1989年第2期32卷 61-71页

作者： CHERN, MS CHEN, GH LIU, P NATL TAIWAN UNIV DEPT COMP SCI & INFORMAT ENGNTAIPEITAIWAN

distributed processing has been a subject of recent interest due to the availability of computer networks. Over the past few years it has led to the identification of several challenging problems. One of these is the problem of optimally distributing program modules over a distributed processing system. This paper presents an LC (Least Cost) branch-and-bound algorithm to find an optimal assignment that minimizes the sum of execution costs and communication costs. Experimental results show that, for over half of the randomly generated instances, the saving rates exceed 99%.

关键词： Branch-and-bound algorithms module assignment problem distributed processing system

来源：评论

学校读者我要写书评

暂无评论

An architectural style of product lines for distributed processing systems, and practical selection method 9

An architectural style of product lines for distributed proc...

引用

Proceedings of the 8th European software engineering conference held jointly with 9th ACM SIGSOFT international symposium on Foundations of software engineering

作者： Yoshitomi Morisawa Koji Torii Nihon Unisys Ltd. 1-1-1 Toyosu Koto-ku Tokyo 135-8560 Japan and Graduate School of Information Science Nara Institute of Science and Technology 8916-5 Takayama Ikoma-shi nara 630-0101 Janan Graduate School of Information Science Nara Institute of Science and Technology 8916-5 Takayama Ikoma-shi nara 630-0101 Janan

ISBN: (纸本)9781581133905

When implementing an application system in a distributed computing environment, several architectural questions arise, such as how and where computing resources are arranged, and how the communication among computing resources are implemented. To simplify the process of making these choices, we have developed an architectural style for distributed processing system. The style classifies product lines for distributed processing systems into nine categories based on the location of data storage and the style of processing between client and server. This paper describes our architectural style and proposes a simple but practical method to select an appropriate architectural style for developing an application system. We apply this selection method in concrete real application systems.

关键词： software architecture distributed computing model distributed processing system product lines architectural style

来源：评论

学校读者我要写书评

暂无评论

A novel framework to enhance the performance of training distributed deep neural networks

引用

INTELLIGENT DATA ANALYSIS 2023年第3期27卷 753-768页

作者： Phan, Trung Do, Phuc Univ Informat Technol Vietnam Natl Univ Fac Informat Sci & Engn Ho Chi Minh City Vietnam Hoa Sen Univ Fac Informat Technol Ho Chi Minh City Vietnam

There are many attempts to implement deep neural network (DNN) distributed training frameworks. In these attempts, Apache Spark was used to develop the frameworks. Each framework has its advantages and disadvantages and needs further improvements. In the process of using Apache Spark to implement distributed training systems, we ran into some obstacles that significantly affect the performance of the systems and programming thinking. This is the reason why we developed our own distributed training framework, called distributed Deep Learning Framework (DDLF), which is completely independent of Apache Spark. Our proposed framework can overcome the obstacles and is highly scalable. DDLF helps to develop applications that train DNN in a distributed environment (referred to as distributed training) in a simple, natural, and flexible way. In this paper, we will analyze the obstacles when implementing a distributed training system on Apache Spark and present solutions to overcome them in DDLF. We also present the features of DDLF and how to implement a distributed DNN training application on this framework. In addition, we conduct experiments by training a Convolutional Neural Network (CNN) model with datasets MNIST and CIFAR-10 in Apache Spark cluster and DDLF cluster to demonstrate the flexibility and effectiveness of DDLF.

关键词： distributed deep learning framework distributed neural network distributed processing system distributed training Apache Spark

来源：评论

学校读者我要写书评

暂无评论

A Study of Disaster Preparedness systems Operations Analysis and Financial Security Measures of Large Banking Network

A Study of Disaster Preparedness Systems Operations Analysis...

引用

5th International Conference on Convergence and Hybrid Information Technology (ICHIT)

作者： Baek, Jong-Il Park, Dea-Woo Dept. of IT Application Technology Hoseo Graduate School of Venture South Korea

ISBN: (纸本)9783642241055

The recent server system failure, which happened in April 2011, of Nonghyup bank left it in disgrace that the overall management of server system in the banking network has been in insolvent operation. It is one of the most urgent issues that the computer system administration and security should be properly managed as IT technology develops at speed of lightning. In this thesis, it will be comprehensively investigated how the financial institutions deal with the management system against the computer failure and the optimum solution to take care of their financial computer systems and information protection policies. For the optimized operation of banking network system, it is necessary to come up with the improvement plan through the quantitative evaluation of centralized and distributed processing system. The stability in the information protection system needs to deal with the role-based access control and distributed security management system against the access of internal & external users or illegal intruders. In this survey, it will be highlighted that the next generation of banking network infrastructure, which has been reinforced in terms of its stability.

关键词： RBAC (Role Based Access Control) Centralized system distributed processing system Financial Security Banking network

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：