检索结果-内蒙古大学图书馆

International Conference for High Performance computing, Networking, Storage and Analysis (SC21)

作者： Costa, Emily Patel, Tirthak Schwaller, Benjamin Brandt, Jim M. Tiwari, Devesh Northeastern Univ Boston MA 02115 USA Sandia Natl Labs Albuquerque NM USA

ISBN: (纸本)9781450384421

Monitoring and analyzing I/O behaviors is critical to the efficient utilization of parallel storage systems. Unfortunately, with increasing I/O requirements and resource contention, I/O performance variability is becoming a significant concern. This paper investigates I/O behavior and performance variability on a large-scale high-performance computing (I IPC) system using a novel methodology that identifies similarity across jobs from the same application leveraging an I/O characterization tool and then, detects potential I/O performance variability across jobs of the same application. We demonstrate and discuss how our unique methodology can be used to perform temporal and feature analyses to detect interesting I/O performance variability patterns in production UPC systems, and their implications for operating/managing large-scale systems.

关键词： Storage systems HPC HPC I/O performance variability machine learning distributed computing systems

来源：评论

学校读者我要写书评

暂无评论

Business Process Engineering for Data Storing and Processing in a Collaborative distributed Environment Based on Provenance Metadata, Smart Contracts and Blockchain Technology

引用

JOURNAL OF GRID computing 2021年第1期19卷 3-3页

作者： Demichev, Andrey Kryukov, Alexander Prikhod'ko, Nikolai Lomonosov Moscow State Univ Skobeltsyn Inst Nucl Phys Moscow Russia

We suggest a novel approach to designing totally decentralized data management systems in distributed environments with administratively unrelated or loosely related user groups and in conditions of partial or complete lack of trust between them. This approach is based on the integration of blockchain technology, smart contracts and provenance metadata driven data management. Provenance metadata (PMD) contain key information that is necessary to determine the origin, authorship and quality of relevant data, their storage and usage consistency, and for interpretation and confirmation of relevant results of data processing. Architecture, operation principles and algorithms have been developed for the system, entitled ProvHL (Provenance HyperLedger), which provides fault-tolerant, safe and reliable management of provenance metadata, control of operations with data files, as well as resource access management in collaborative distributed computing systems (CDCS). CDCS refers to distributed systems formed by combining into a single pool of computer resources of various organizations (institutions) to work together in the framework of a project. The paper also suggests a new blockchain-based method for delegation of rights within distributed computing systems which is free from shortcomings inherent in other solutions. The main goal of the work is to demonstrate the capabilities of the proposed approach and the above technologies to improve the functional properties of CDCSs.

关键词： distributed computing systems Provenance metadata Blockchain technology Access rights Rights delegation Hyperledger fabric

来源：评论

学校读者我要写书评

暂无评论

A Control Loop-based Algorithm for Operational Transformation 14

A Control Loop-based Algorithm for Operational Transformatio...

引用

IEEE 14th International Symposium on Applied Computational Intelligence and Informatics (SACI)

作者： Gadea, Cristian Ionescu, Bogdan Ionescu, Dan Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON Canada

ISBN: (纸本)9781728173764

Operational Transformation (OT) has emerged as a viable theoretical principle for the implementation of real-time collaboration applications. In such systems, the collaboration consists of operations generated by members of a group who are performing concurrent actions on the same document or content. This powerful multi-user co-editing has been researched ever since the seminal works of the late 1980s. As the web evolved into a dominant platform for content consumption and creation, classes of algorithms like OT and Conflict-free Replicated Data Types (CRDT) have enabled flexible content synchronization for applications such as online word processors. Despite their long history in academia, OT and CRDT continue to have unsolved issues due to the centralized approach required for scalable and reliable web-based document editing. This paper proposes a Control Loop-based OT approach based on a serverless architecture and on Finite State Automata (FSA). A control loop principle is used to design a series of algorithms for distributed conflict resolution. The proposed architecture consists of a series of blocks which internally contain a number of multi-level Finite State Machines. The architecture of the new serverless approach for OT is introduced and the basic FSAs that model the co-editing processes are described. Cases encountered in the dynamics of the co-editing processes were modeled to prove that the essential OT properties of causality preservation, convergence, and intention preservation are all satisfied. Simulation results are given at the end of the paper.

关键词： Control Loop Architecture Decision Making Automata Collaborative Software Platforms distributed computing systems Consistency and Concurrency Finite State Automata Real-Time Automata Real-Time systems

来源：评论

学校读者我要写书评

暂无评论

Reliability of A distributed computing System Considering Task Abort 10

Reliability of A Distributed Computing System Considering Ta...

引用

10th IEEE Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Peng, Rui Gao, Kaiye Wu, Di Zhai, Qingqing Beijing Univ Technol Sch Econ & Management Beijing Peoples R China Beijing Informat Sci & Technol Univ Sch Econ & Management Beijing Peoples R China Xi An Jiao Tong Univ Sch Management Xian Peoples R China Shanghai Univ Sch Management Shanghai Peoples R China

ISBN: (纸本)9781728108612

This paper studies the reliability of a distributed computing system where the task on a computer may be aborted if it is still not finished until a time threshold. The mission is regarded as successful if all these tasks are completed by at least one computer before a pre-specified time. An abort policy model is proposed and a multi-valued decision diagram approach is adopted to evaluate the system reliability for any given abort policy. A numerical example is provided to illustrate the applications.

关键词： distributed computing systems abort policy multi-valued decision diagram reliability

来源：评论

学校读者我要写书评

暂无评论

ObliDC: An SGX-based Oblivious distributed computing Framework with Formal Proof 19

ObliDC: An SGX-based Oblivious Distributed Computing Framewo...

引用

ACM Asia Conference on Computer and Communications Security (Asia CCS)

作者： Wu, Pengfei Shen, Qingni Deng, Robert. H. Liu, Ximeng Zhang, Yinghui Wu, Zhonghai Peking Univ Beijing Peoples R China Singapore Management Univ Singapore Singapore Fuzhou Univ Fuzhou Peoples R China Xian Univ Posts & Telecommun Xian Peoples R China

ISBN: (纸本)9781450367523

Data privacy is becoming one of the most critical concerns in cloud computing. Several proposals based on Intel SGX such as VC3 [1] and M2R [2] have been introduced in the literature to protect data privacy during job execution in the cloud. However, a comprehensive formal proof of their security guarantees is still lacking. In this paper, we propose ObliDC, a general UC-secure SGX-based oblivious distributed computing framework. First, we model the life-cycle of a distributed computing job as data-flow graphs. Under the assumption of malicious, adaptive adversaries in the cloud, we then formally define data privacy of a distributed computing job by introducing a notion named ODC-privacy, which encompasses both semantic security (to protect data confidentiality during computation and transmission) and oblivious traffic (to prevent data leakage from traffic analysis). ObliDC is composed of four two-party protocols - job deployment, job initialization, job execution, and results return, which allow for modular construction of concrete privacy-preserving job protocols in different distributed computing frameworks. Finally, inspired by a formal abstraction for trusted processors proposed by R. Pass et al. [3], we formally prove the security of ObliDC under the universal composability (UC) framework.

关键词： oblivious computation Intel SGX distributed computing systems formal proof

来源：评论

学校读者我要写书评

暂无评论

1+1 Protection of Overlay distributed computing systems: Modeling and Optimization

引用

12th International Conference on Computational Science and Its Applications (ICCSA)

作者： Walkowiak, Krzysztof Rak, Jacek Wroclaw Univ Technol Wybrzeze Wyspianskiego 27 PL-50370 Wroclaw Poland Gdansk Univ Technol PL-80233 Gdansk Poland

ISBN: (纸本)9783642311277;9783642311284

The development of the Internet and growing amount of data produced in various systems have triggered the need to construct distributed computing systems required to process the data. Since in some cases, results of computations are of great importance, (e.g., analysis of medical data, weather forecast, etc.), survivability of computing systems, i.e., capability to provide continuous service after failures of network elements, becomes a significant issue. Most of previous works in the field of survivable computing systems consider a case when a special dedicated optical network is used to connect computing sites. The main novelty of this work is that we focus on overlay-based distributed computing systems, i.e., in which the computing system works as an overlay on top of an underlying network, e. g., Internet. In particular, we present a novel protection scheme for such systems. The main idea of the proposed protection approach is based on 1+1 protection method developed in the context of connection-oriented networks. A new ILP model for joint optimization of task allocation and link capacity assignment in survivable overlay distributed computing systems is introduced. The objective is to minimize the operational (OPEX) cost of the system including processing costs and network capacity costs. Moreover, two heuristic algorithms are proposed and evaluated. The results show that provisioning protection to all tasks increases the OPEX cost by 110% and 106% for 30-node and 200-node systems, respectively, compared to the case when tasks are not protected.

关键词： distributed computing systems protection survivability optimization

来源：评论

学校读者我要写书评

暂无评论

The Economics of Introducing the Peer-to-peer System of Storage and Processing of Protected Information at an Enterprise 21

The Economics of Introducing the Peer-to-peer System of Stor...

引用

21st International Conference on Complex systems - Control and Modeling Problems (CSCMP)

作者： Nenashev, Alexey Khryashchev, Victor Samara State Tech Univ Samara Russia

ISBN: (纸本)9781728167008

The method of evaluating the effectiveness of the economic parameters for the implementation at industrial enterprises of "Peer-to-Peer distributed Storage and Processing of Protected Information in Corporate Networks," designed primarily to protect distributed computing and isolate private networks without limiting the possibilities of useful interaction in the framework of the technologies Industry 5.0 and Super Smart Society is proposed. Within the framework of these concepts, there is a gradual integration of production, logistics, sales, and information systems into a global information exchange system. The proposed system provides for effective counteraction to the threats using cryptography, protection against unauthorized access using biometrics, and an innovative protocol for information interaction and control of topology based on distributed ledger technologies, it optimizes the use of computing power and provides tools for distributed computing without changing the logic of existing software.

关键词： Industry 5.0 Super Smart Society distributed ledger cybersecurity performance evaluation computer simulation peer-to-peer networks information security distributed computing systems

来源：评论

学校读者我要写书评

暂无评论

Analysis and Optimisation of PBS/TORQUE Fault Tolerance Tools 15

Analysis and Optimisation of PBS/TORQUE Fault Tolerance Tool...

引用

15th International Asian School-Seminar on Optimization Problems of Complex systems (OPCS)

作者： Efimov, Alexandr V. Pavsky, Kirill V. Comp Syst Lab ISP SB RAS Comp Syst Dept SibSUTIS Novosibirsk Russia

This work is devoted to the problem of detecting and processing faults of computing nodes during execution of parallel programs on distributed computing systems. The fault tolerance tools of PBS/TORQUE are considered.... 详细信息

ISBN: (纸本)9781728129860

关键词： distributed computing systems fault tolerance resource management PBS/TORQUE

来源：评论

学校读者我要写书评

暂无评论

A High Performance Model for Task Allocation in distributed computing System Using K-Means Clustering Technique

引用

INTERNATIONAL JOURNAL OF distributed systems AND TECHNOLOGIES 2018年第3期9卷 1-23页

作者： Kumar, Harendra Chauhan, Nutan Kumari Yadav, Pradeep Kumar Gurukula Kangri Univ Dept Math & Stat Haridwar 249404 Uttarakhand India Cent Bldg Res Inst Dept Res Planning & Business Dev Roorkee Uttar Pradesh India

Tasks allocation is an important step for obtaining high performance in distributed computing system (DCS). This article attempts to develop a mathematical model for allocating the tasks to the processors in order to achieve optimal cost and optimal reliability of the system. The proposed model has been divided into two stages. Stage-I, makes the 'n' clusters of set of 'm' tasks by using k-means clustering technique. To use the k-means clustering techniques, the inter-task communication costs have been modified in such a way that highly communicated tasks are clustered together to minimize the communication costs between tasks. Stage-II, allocates the 'n' clusters of tasks onto 'n' processors to minimize the system cost. To design the mathematical model, executions costs and inter tasks communication costs have been taken in the form of matrices. To test the performance of the proposed model, many examples are considered from different research papers and results of examples have compared with some existing models.

关键词： distributed computing systems K-Means Clustering System Cost System Reliability Task Allocation

来源：评论

学校读者我要写书评

暂无评论

Spontaneous Emergence of Programs from "Primordial Soup" of Functions in distributed Computer systems

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2018年第1期52卷 40-48页

作者： Kol'chugina, E. A. Penza State Univ Fed State Budgetary Educ Inst Higher Educ Penza 440026 Russia

This article considers a problem of possible spontaneous emergence of high level of abstraction programs from the set of independent parallel processes, which are performing different functions and using shared variables. The model proposed in the article is based on the principles of artificial chemistry and describes the distributed computing. As the results of simulations, unstable cyclic computational structures of different kinds spontaneously arose in the model. These structures are considered as implicit programs.

关键词： self-organization spontaneous emergence of programs artificial chemistry artificial life distributed computing systems artificial intelligence

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：