检索结果-内蒙古大学图书馆

23rd International Conference on Computational Science and its Applications (ICCSA)

作者： Bodkhe, Sonali Mahajan, Anjali Sant Gadge Baba Amravati Univ Dept Comp Sci Amravati Maharashtra India Govt Polytech Nagpur Maharashtra India

ISBN: (纸本)9783031368042;9783031368059

Parallel computing and distributed computing are the popular terminologies of scheduling. With advancement in technology, systems have become much more compact and fast and need of parallelization plays a major role for this compaction. Wireless computing is also a common concept associated with each new development. Scheduling of tasks has always been a challenging area and is an NP-complete problem. Moreover, when it comes to wireless distributed computing, reliable scheduling plays an important role in order to complete a task in a wireless distributed system. This work proposes an algorithm to dynamically schedule tasks on heterogeneous processors within a wireless distributed computing system. A lot of heuristics, meta-heuristics & genetics have been used earlier with scheduling strategies. However, most of them haven't taken reliability into account before scheduling. Here a heuristic that deals with reliable scheduling is considered. The scheduler also works within an environment which has dynamically changing resources and adapts itself to changing system resources. The testing was carried out with up to 200 tasks being scheduled while testing in a real time wireless distributed environment. Experiments have shown that the algorithm outperforms the other strategies and can achieve a better reliability along with no increase in make-span, in spite of wireless nodes.

关键词： distributed computing Scheduling Reliability Wireless distributed Systems (WDS)

来源：评论

学校读者我要写书评

暂无评论

On Secure distributed Linearly Separable Computation

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2022年第3期40卷 912-926页

作者： Wan, Kai Sun, Hua Ji, Mingyue Caire, Giuseppe Tech Univ Berlin Elect Engn & Comp Sci Dept D-10587 Berlin Germany Univ North Texas Dept Elect Engn Denton TX 76203 USA Univ Utah Dept Elect & Comp Engn Salt Lake City UT 84112 USA

distributed linearly separable computation, where a user asks some distributed servers to compute a linearly separable function, was recently formulated by the same authors and aims to alleviate the bottlenecks of stragglers and communication cost in distributed computation. The data center assigns a subset of input datasets to each server in an uncoded manner, and each server computes some coded packets on the assigned datasets, which are then sent to the user. The user should recover the task function from the answers of a subset of servers, such that the effect of stragglers could be tolerated. In this paper, we formulate a novel secure framework for this distributed linearly separable computation, where we aim to let the user only retrieve the desired task function without obtaining any other information about the input datasets, even if it receives the answers of all servers. In order to preserve the security of the input datasets, some common randomness variable independent of the datasets should be introduced into the transmission. We show that any non-secure linear-coding based computing scheme for the original distributed linearly separable computation problem, can be made secure without increasing the communication cost (number of symbols the user should receive). Then we focus on the case where the computation cost of each server (number of datasets assigned to each server) is minimum and aim to minimize the size of the randomness variable (i.e., randomness size) introduced in the system while achieving the optimal communication cost. We first propose an information theoretic converse bound on the randomness size. We then propose secure computing schemes based on two well-known data assignments, namely fractional repetition assignment and cyclic assignment. These schemes are optimal subject to using these assignments. Motivated by the observation of the general limitation of these two schemes on the randomness size, we propose a computing scheme with nove

关键词： Servers Costs Task analysis Security Encoding Data centers Sun distributed computing security straggler mitigation

来源：评论

学校读者我要写书评

暂无评论

Realizability of Event Diagrams and Existence of Logical Clocks

引用

CYBERNETICS AND SYSTEMS ANALYSIS 2025年第1期61卷 11-20页

作者： Zholtkevych, G. Zozulia, A. V N Karazin Kharkiv Natl Univ Kharkiv Ukraine

This paper addresses the problem of the relationship between the correctness of the event diagram of distributed computing, from the standpoint of communication between the local processes of this computing, and the existence of a logical clock for that diagram. The problem is analyzed using the Coq Proof Assistant without assuming the fairness of the principle of excluded middle. That is, the obtained results are correct from the point of view of constructive logic, which is essential for computer science. The authors have formally proved that the existence of a logical clock for distributed computing ensures the irreflexivity of the causal relation related to that computing. They have also formulated the conjecture about the fairness of the converse statement.

关键词： distributed computing cloud platform blockchain digital distributed ledgers global time logical clock event ordering

来源：评论

学校读者我要写书评

暂无评论

The Concept of Green Cloud Infrastructure Based on distributed computing and Hardware Accelerator within FPGA as a Service 12

The Concept of Green Cloud Infrastructure Based on Distribut...

引用

Proceedings of IEEE East West Design and Test Symposium ( EWDTS 2014)

作者： Yanovskaya, O. Yanovsky, M. Kharchenko, V. Natl Aerosp Univ Kharkov Ukraine Ctr Safety Infrastruct Oriented Res & Anal Kharkov Ukraine

ISBN: (纸本)9781479976300

The article focuses on the energy efficiency issue and the negative impact on the environment of Cloud computing based on data centers infrastructure. A modernization of Cloud architecture in terms of Green computing is proposed, using FPGA hardware accelerators and distributed peer-to-peer networks. Customer and FPGA as a Service (FAAS) interaction scenarios are discussed. A distributed peer-to-peer Cloud architecture is suggested. The energy efficiency analysis of the proposed architectures shows its advantages.

关键词： cloud computing computer centres field programmable gate arrays peer-to-peer computing software architecture FAAS FPGA as a service FPGA hardware accelerators cloud architecture data centers infrastructure distributed computing distributed peer-to-peer networks energy efficiency green cloud infrastructure Cloud computing Computer architecture Energy consumption Field programmable gate arrays Green products Hardware Power demand Field programmable gate arrays Cloud computing distributed computing Energy efficiency Green products Peer to peer computing Power demand Computer Architecture hardware accelerator Software architecture Computer hardware energy consumption Environmental impact

来源：评论

学校读者我要写书评

暂无评论

DiAD - distributed Acceleration for Datacenter FPGAs 33

DiAD - Distributed Acceleration for Datacenter FPGAs

引用

33rd International Conference on Field-Programmable Logic and Applications (FPL)

作者： Lant, Joshua Skordalakis, Emmanouil Paraskevas, Kyriakos Toms, William B. Lujan, Mikel Goodacre, John Univ Manchester Dept Comp Sci Manchester M13 9PL Lancs England

ISBN: (纸本)9798350341515

The growing demands placed upon modern compute and network resources are far exceeding the capabilities of traditional computer architectures. It is now customary for accelerators to perform the bulk of compute, and this compute is being pushed ever closer to the network. FPGA vendors have brought powerful datacenter cards to the market, combining reprogrammable FPGA fabrics with high bandwidth networking capability. However, the supporting infrastructure has yet to reach maturity, so modern and diverse workloads are not yet able to fully leverage these architectural advances. In this paper we present DiAD;a novel framework providing FPGA firmware and driver support for fully unified, distributed compute and network acceleration across a commodity Ethernet network. We present a far richer feature set and greater flexibility than other existing solutions. We show comparable networking performance from the host when compared to Xilinx's OpenNIC solution. As well as allowing for host networking through the FPGA fabric, we demonstrate reliable data transfer directly between FPGA fabrics without host intervention, and show native memory transactions sent over the network supporting pointer-chasing workloads. We achieve line rate for dataflow type communication and approach line rate for larger native memory transfers (87G).

关键词： datacenter distributed computing FPGA networks

来源：评论

学校读者我要写书评

暂无评论

An objective comparison of two prominent virtual actor frameworks: *** and Orleans

引用

INTERNATIONAL JOURNAL OF COMMUNICATION NETWORKS AND distributed SYSTEMS 2024年第3期30卷 313-342页

作者： Sykes, Edward R. DiVito, Alec Sheridan Coll Ctr Mobile Innovat Oakville ON Canada

Recently there has been a significant increase in developing distributed systems easily and rapidly. Driven by the demand of software communities, developers seek tools and frameworks that abstract away low-level details of the underlying distributed system and the need to understand complex details on how the system works. Researchers have explored serverless frameworks, distributed key value stores, distributed stream processing frameworks and distributed actor frameworks. Currently, stateful serverless applications and distributed actor models may be the answer to what developers need. In this paper, we present a review of stateful distributed computing frameworks, and the results of experiments that compare Orleans and *** - two popular actor model frameworks - running on Kubernetes. We discovered that the *** performs at least two times faster than Orleans, but is more complex to learn. We present the results of these tests, and provide a discussion of future research opportunities highlighting virtual actor model frameworks.

关键词： actor model distributed computing microbenchmark tests serverless computing virtual actor frameworks

来源：评论

学校读者我要写书评

暂无评论

Tweets opinion analysis integration: ETL modeling with MapReduce

引用

CLUSTER computing-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2025年第5期28卷 1-21页

作者： Walha, Afef Mallek, Hana Ghozzi, Faiza Gargouri, Faiez Univ Sfax Multimedia InfoRmat Syst & Adv Comp Lab MIRACL Sfax Tunisia Univ Gabes Higher Inst Informat Sci & Multimedia Gabes ISIMG Gabes Tunisia Univ Sfax Higher Inst Informat Sci & Multimedia Sfax ISIMS Sfax Tunisia

The advent of social media has revolutionized the way people communicate and share information, leading to new business opportunities and challenges. Social media platforms offer a valuable resource in user-generated content (UGC), widely used for opinion analysis and business intelligence. However, traditional integration methods, particularly Extract-Transform-Load (ETL) tasks, need help to keep up with the vast volume, variety, and speed of big data generated on these platforms. This paper proposes MR_ETLSent, an ETL process model adopting MapReduce to perform opinion integration of a large volume of UGC data. It underlines the problem of covering time, cost, and complexity to semantically analyze informal and unstructured UGC texts and transform them into sentiments. This approach provides reusable models for the complex process that extracts UGC text, cleans it, semantically analyzes its data to detect sentiment, and transforms it into the data warehouse. The experimentation results of MR_ETLSent components in the Hadoop framework indicate that the proposed sentiment analysis method based on MapReduce performs well with large sets of UGC while minimizing time and computing resources. Overall, our approach is scalable, efficient, and cost-effective and can be integrated into decision-making systems that analyze opinions and handle large volumes of data.

关键词： Social media analytics Twitter text analysis Opinion mining Big data integration ETL modeling MapReduce distributed computing

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Middleware Platform for distributed computing on Wireless Sensor Networks

A Lightweight Middleware Platform for Distributed Computing ...

引用

5th International Conference on Ambient Systems, Networks and Technologies (ANT) / 4th International Conference on Sustainable Energy Information Technology (SEIT)

作者： Gaglio, Salvatore Lo Re, Giuseppe Martorella, Gloria Peri, Daniele DICGIM Univ Palermo I-90128 Palermo Italy CNR Ist Calcolo & Reti Ad Alte Prestaz ICAR I-90128 Palermo Italy

The peculiar features of Wireless Sensor Networks (WSNs) suggest to exploit the distributed computing paradigm to perform complex tasks in a collaborative manner, in order to overcome the constraints related to sensor nodes limited capabilities. In this context, we describe a lightweight middleware platform to support the development of distributed applications on WSNs. The platform provides just a minimal general-purpose software layer, while the application components, including communication and processing algorithms, as well as the exchanged data, are described symbolically, with neither preformed syntax nor strict distinction between data and code. Our approach allows for interactive development of applications on each node, and requires no cross-compilation, a common practice that makes the development of WSN applications rigid and time-consuming. This way, tasks and behavior of each node can be modified at runtime, even after the network deployment, by sending the node executable code. (C) 2014 Published by Elsevier B.V.

关键词： distributed computing WSN Middleware

来源：评论

学校读者我要写书评

暂无评论

Stragglers in distributed Matrix Multiplication 26th

Stragglers in Distributed Matrix Multiplication

引用

26th Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)

作者： Nissim, Roy Schwartz, Oded Hebrew Univ Jerusalem Jerusalem Israel

ISBN: (纸本)9783031439421;9783031439438

A delay in a single processor may affect an entire system since the slowest processor typically determines the runtime. Problems with such stragglers are often mitigated using dynamic load balancing or redundancy solutions such as task replication. Unfortunately, the former option incurs high communication cost, and the latter significantly increases the arithmetic cost and memory footprint, making high resource overhead seem inevitable. Matrix multiplication and other numerical linear algebra kernels typically have structures that allow better straggler management. Redundancy based solutions tailored for such algorithms often combine codes in the algorithm's structure. These solutions add fixed cost overhead and may perform worse than the original algorithm when little or no delays occur. We propose a new loadbalancing solution tailored for distributed matrix multiplication. Our solution reduces latency overhead by O (P/ log P) compared to existing dynamic load-balancing solutions, where P is the number of processors. Our solution overtakes redundancy-based solutions in all parameters: arithmetic cost, bandwidth cost, latency cost, memory footprint, and the number of stragglers it can tolerate. Moreover, our overhead costs depend on the severity of delays and are negligible when delays are minor. We compare our solution with previous ones and demonstrate significant improvements in asymptotic analysis and simulations: up to x4.4 and x5.3 compared to general-purpose dynamic load balancing and redundancy-based solutions, respectively.

关键词： Dynamic Load Balancing Straggler Mitigation distributed computing Numerical Linear Algebra

来源：评论

学校读者我要写书评

暂无评论

Cryptography in distributed Ledger Technologies from a Layered Perspective: A State of the Art 1

引用

3rd International Conference on Digital Technologies and Applications

作者： Barj, Sara Ouaddah, Aafaf Mezrioui, Abdellatif Natl Inst Posts & Telecommun Rabat Morocco

ISBN: (数字)9783031298608

ISBN: (纸本)9783031298592;9783031298608

Cryptography is the practice of secure communication to protect data's confidentiality, integrity, and authenticity. In the context of blockchains, cryptography is used to secure transactions, protect users' privacy, and ensure the integrity and security of the network. Nevertheless, this later is subject to many attacks, such as post-quantum attacks. In this paper, we survey and extract how cryptography is used in blockchains from a layered perspective: data, Consensus, and Execution to Application layers. We summarize our findings and results using a table containing the functions of cryptographic protocols, families, functions, primitives, and schemes and how they are utilized for each studied blockchain platform. We discuss each cryptographic technique's related DCEA layer in the forecited table. Therefore, this work helps assess current cryptographic techniques used in current distributed Ledger Technologies or design and develop new hardened ones by choosing post-quantum-related cryptographic techniques for each layer.

关键词： Cryptographic Protocols Privacy Data Security distributed computing Blockchain Design Improvement

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：