检索结果-内蒙古大学图书馆

International Conference on Actual Problems of Electronic Instrument Engineering (APEIE)

作者： P.V. Mishenko N.S. Tkachev Novosibirsk State Technical University Russia

The paper considers actual questions of organization of computing in distributed computing systems (DCS) which components are exposed to breakdowns. The consideration to terminology in the sphere of computing in DCS is given. The existing and expanding methods of computing process recovery after one of several nodes breakdown are discussing. The special attention is payed to the local checkpoints method and its realization in module of fault tolerance providing of NSTU computing Science department distributed computing system.

关键词： distributed computing systems parallel computing fault tolerance checkpoints

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Distributing Incoming Messages Among Handlers 2nd

Algorithm for Distributing Incoming Messages Among Handlers

引用

2nd International Conference on Information Technologies and Their Applications

作者： Zverev, Ivan Zykina, Anna Omsk State Tech Univ 11 Mira Prospect Omsk Russia

ISBN: (纸本)9783031734199;9783031734205

In modern digital world, the amount of information is increasing dramatically. All this information requires immediate processing which can be done by automated systems. To accelerate processing in automated systems, new models, methods and efficient algorithms for their implementation are needed. The article considers the problem of distributing incoming messages to handlers in an automated system of an organization. The classical assignment problem and known methods of its solution are the mathematical basis for solving the problem. A generalization of the assignment problem with invalid combinations of assignments is considered as a model. A solution algorithm is developed and a software product for solving the described problem in the Python language is implemented. Moreover, numerical experiments are carried out to verify the quality of the developed algorithm and check its feasibility. The applied problem posed in this paper is relevant as in terms of its practical application and as the study of the mathematical model of the assignment problem and methods of its solution. The developed algorithm allows us to calculate the system load and regulate the number of handlers in operation. The obtained results can serve as input parameters for the simulation model of the incoming message processing system which will allow experimenting with the load of such a system.

关键词： Assignment Problem Mathematical Modeling distributed computing systems Equivalent Transformations Simulation Modeling Python

来源：评论

学校读者我要写书评

暂无评论

An approach to the development of programming software for distributed computing and information processing systems

An approach to the development of programming software for d...

引用

3rd International Conference on Software and Data Technologies

作者： Kutepov, V. P. Malanin, V. N. Pankov, N. A. Tech Univ Moscow Power Res Inst Moscow Russia

The problem of software development for distributed and parallel computing systems is considered in the paper. Its original issue is in extending our projecting work on parallel programming languages and operational t... 详细信息

ISBN: (纸本)9789898111517

关键词： flow-graph stream parallel programming language distributed computing systems data-flow programming scheduling

来源：评论

学校读者我要写书评

暂无评论

Model of distributed computing system operation with time

引用

PROGRAMMING AND COMPUTER SOFTWARE 2013年第5期39卷 233-241页

作者： Smelyansky, R. L. Moscow MV Lomonosov State Univ Dept Computat Math & Cybernet Moscow 119899 Russia

A mathematical model of the operation dynamics of distributed computing systems is presented. This model covers operation of both hardware and software components. The model provides a theoretical basis for performance, reliability, and consistency analysis, checking the correctness of operation, designing computing system architecture.

关键词： distributed computing systems formal models of behavior performance analysis simulation

来源：评论

学校读者我要写书评

暂无评论

Reliability of a distributed computing System With Performance Sharing

引用

IEEE TRANSACTIONS ON RELIABILITY 2022年第4期71卷 1555-1566页

作者： Xiao, Hui Yi, Kunxiang Peng, Rui Kou, Gang Southwestern Univ Finance & Econ Sch Stat Dept Management Sci & Engn Chengdu 611130 Peoples R China Hunan Univ Technol & Business Sch Management Changsha 410205 Peoples R China Beijing Univ Technol Sch Econ & Management Beijing 100124 Peoples R China Southwestern Univ Finance & Econ Sch Business Adm Fac Business Adm Chengdu 611130 Peoples R China

Existing research has been concentrated on improving the reliability of a distributed computing system through optimizing tasks allocation, providing software redundancy and providing hardware redundancy. None of these works considered the performance sharing mechanism in a distributed computing system. Different from other performance sharing systems whose reliability can be calculated directly, the reliability evaluation of a distributed computing system with performance sharing is more challenging since the reliability depends on the task execution time of each processor after performance sharing. This research considers a distributed computing system with performance sharing mechanism such that the computing power can be redistributed among different processors in the system. A reliability model is proposed to evaluate the distributed computing system with performance sharing. An optimization model is formulated to derive the optimal performance sharing policy such that the system reliability can be maximized. Both analytic examples and numerical examples are carried out to illustrate the proposed model and algorithm.

关键词： Reliability Task analysis distributed computing Computational modeling Optimization Resource management Computers Common bus performance sharing distributed computing systems optimization system reliability universal generating function (UGF)

来源：评论

学校读者我要写书评

暂无评论

MonALISA: An agent based, dynamic service system to monitor, control and optimize distributed systems

引用

COMPUTER PHYSICS COMMUNICATIONS 2009年第12期180卷 2472-2498页

作者： Legrand, I. Newman, H. Voicu, R. Cirstoiu, C. Grigoras, C. Dobre, C. Muraru, A. Costan, A. Dediu, M. Stratan, C. CALTECH Pasadena CA 91125 USA Univ Politehn Bucuresti Bucharest Romania CERN European Ctr Nucl Res Geneva Switzerland

The MonALISA (Monitoring Agents in a Large Integrated Services Architecture) framework provides a set of distributed services for monitoring, control, management and global optimization for large scale distributed systems. It is based on an ensemble of autonomous, multi-threaded, agent-based subsystems which are registered as dynamic services. They can be automatically discovered and used by other services or clients. The distributed agents can collaborate and cooperate in performing a wide range of management, control and global optimization tasks using real time monitoring information. Program summary Program title: MonALISA Catalogue identifier: AEEZ_v1_0 Program summary URL: http://***/summaries/*** Program obtainablefrom: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: Caltech License - free for all non-commercial activities No. of lines in distributed program, including test data, etc.: 147802 No. of bytes in distributed program, including test data, etc.: 25913689 Distribution format: *** Programming language: Java, additional APIs available in Java, C, C++, Perl and python Computer: computing Clusters, Network Devices, Storage systems, Large scale data intensive applications Operating system: The MonALISA service is mainly used in Linux, the MonALISA client runs on all major platforms (Windows, LmLIX, Solaris, MacOS). Has the code been vectorized orparallelized?: It is a multithreaded application. It will efficiently use all the available processors. RAM: for the MonALISA service the minimum required memory is 64 MB: if the JVM is started allocating more memory this will be used for internal caching. The MonALISA client requires typically 256-512 MB of memory. Classification: 6.5 External routines: Requires Java: JRE or JDK to run. These external packages are used (they are included in the distribution): JINI, JFreeChart. PostgreSQL (optional). Nature of problem: To monitor and control distributed

关键词： distributed computing systems Monitoring Control Optimized dynamic routing High performance data transfers

来源：评论

学校读者我要写书评

暂无评论

distributed SPOT PRICING IN RADIAL-DISTRIBUTION systems

引用

IEEE TRANSACTIONS ON POWER systems 1994年第1期9卷 311-317页

作者： MURPHY, L KAYE, RJ WU, FF UNIV NEW S WALES SCH ELECT ENGNKENSINGTONNSW 2033AUSTRALIA

Spot pricing is a method for pricing electricity that maximizes the economic efficiency of the power system. We derive an expression for the spot prices in a radial distribution system, in terms of system quantities such as power line flows. The system's radial structure leads to simplified spot price expressions. We do not assume that all the problem data is available at one location (ie. to the utility). The proposed pricing algorithm addresses the issue of decentralized knowledge by using a distributed processing scheme, which emphasizes local computations. We also show how line flow constraints can be implemented as an integral part of the proposed spot pricing algorithm.

关键词： SPOT PRICING distributed PROCESSING distributed computing systems DISTRIBUTION AUTOMATION PARALLEL PROCESSING

来源：评论

学校读者我要写书评

暂无评论

Schedule length and reliability-oriented multi-objective scheduling for distributed computing

引用

SOFT computing 2015年第6期19卷 1727-1737页

作者： Liu, Guoquan Zeng, Yifeng Li, Dong Chen, Yingke Xian Jiaotong Liverpool Univ Int Business Sch Suzhou Suzhou Peoples R China Xiamen Univ Dept Automat Xiamen Peoples R China Univ Teesside Sch Comp Middlesbrough Cleveland England Univ York York Management Sch York YO10 5DD N Yorkshire England Sichuan Univ Coll Comp Sci Chengdu 610064 Peoples R China

Maximizing system reliability and minimizing schedule length are the two major objectives in scheduling a distributed computing system. These two objectives have been considered separately by most researchers, although more realistically they should be considered simultaneously. This paper addresses the problem by taking a multi-objective approach in scheduling. A Tabu search algorithm is proposed and two lateral interference schemes are used to distribute the Pareto optimal solutions along the Pareto front uniformly. Randomly generated directed acyclic graphs and a real application task graph are used to study the performance of the proposed algorithms. Experimental results show that for this problem lateral interference has no influence on the non-dominated solution number, but does benefit the uniform distribution of non-dominated solutions, irrespective of the computation method used to determine distances between the solutions.

关键词： Multi-objective optimization Tabu search distributed computing systems

来源：评论

学校读者我要写书评

暂无评论

Task allocation for maximizing reliability of a distributed system using hybrid particle swarm optimization

引用

JOURNAL OF systems AND SOFTWARE 2007年第5期80卷 724-735页

作者： Yin, Peng-Yeng Yu, Shiuh-Sheng Wang, Pei-Pei Wang, Yi-Te Natl Chi Nan Univ Dept Informat Management Puli 545 Nantou Taiwan

In a distributed computing system, a number of program modules may need to be allocated to different processors such that the reliability of executing successfully these modules is maximized and the constraints with limited resources are satisfied. The problem of finding an optimal task allocation with maximum system reliability has been shown to be NP-hard;thus, existing approaches to finding exact solutions are limited to the use in problems of small size. This paper presents a hybrid particle swarm optimization (HPSO) algorithm for finding the near-optimal task allocation within reasonable time. The experimental results show that the HPSO is robust against different problem size, task interaction density, and network topology. The proposed method is also more effective and efficient than a genetic algorithm for the test-cases studied. The convergence and the worst-case characteristics of the HPSO are addressed using both theoretical and empirical analysis. (c) 2006 Elsevier Inc. All rights reserved.

关键词： task allocation problem distributed computing systems distributed system reliability hybrid strategy particle swarm optimization genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Survey on Performance Modeling and Prediction for distributed DNN Training

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed systems 2024年第12期35卷 2463-2478页

作者： Guo, Zhenhua Tang, Yinan Zhai, Jidong Yuan, Tongtong Jin, Jian Wang, Li Zhao, Yaqian Li, Rengang IEIT Syst Co Ltd Jinan 250101 Peoples R China Tsinghua Univ Beijing 100084 Peoples R China Beijing Univ Technol Beijing 100124 Peoples R China CAICT Beijing 100191 Peoples R China

The recent breakthroughs in large-scale DNN attract significant attention from both academia and industry toward distributed DNN training techniques. Due to the time-consuming and expensive execution process of large-scale distributed DNN training, it is crucial to model and predict the performance of distributed DNN training before its actual deployment, in order to optimize the design of distributed DNN training at low cost. This paper analyzes and emphasizes the importance of modeling and predicting the performance of distributed DNN training, categorizes and analyses the related state-of-the-art works, and discusses future challenges and opportunities for this research field. The objectives of this paper are twofold: first, to assist researchers in understanding and choosing suitable modeling and prediction tools for large-scale distributed DNN training, and second, to encourage researchers to propose more valuable research about performance modeling and prediction for distributed DNN training in the future.

关键词： Training Predictive models Computational modeling Optimization Costs Tensors Servers Pipelines Software Parallel processing distributed DNN training distributed computing systems large-scale machine learning performance modeling

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：