检索结果-内蒙古大学图书馆

IEEE International Conference on Utility and Cloud computing (UCC)

作者： Ali Mokhtari Saeid Ghafouri Pooyan Jamshidi Mohsen Amini Salehi University of Louisiana at Lafayette LA USA Queen Mary University London UK University of South Carolina SC USA University of North Texas TX USA

ISBN: (数字)9798350367201

ISBN: (纸本)9798350367218

Despite extensive research on system heterogeneity, there remains a gap in measuring its impact on system performance. Previous studies have primarily focused on the binary definition of heterogeneity based on architectural diversity, without exploring dimensions of system heterogeneity and their impacts on the system performance. To bridge this gap, in this study, we propose a heterogeneity measure that, for a given heterogeneous system, offers a representation of its performance. This heterogeneity measure is instrumental for solution architects in proactively defining their systems to be sufficiently heterogeneous to meet their desired performance objectives. Accordingly, we develop a mathematical model to characterize a heterogeneous system in terms of its task and machine heterogeneity dimensions and then condense it to a single value, called Homogeneous Equivalent Execution Time (HEET), which represents the execution time behavior of the entire system. We used AWS EC2 instances to implement a machine learning inference system. Using HEET scores in various heterogeneous system configurations demonstrated that HEET can accurately characterize the performance behavior of these systems. In particular, the results show that HEET can help predict the true makespan of heterogeneous systems with an average precision of 84%.

关键词： Uncertainty Atmospheric measurements System performance Transforms Throughput Particle measurements Probabilistic logic Vectors Time measurement distributed computing

来源：评论

学校读者我要写书评

暂无评论

Multi-access distributed computing Models using Map-Reduce Arrays

Multi-access Distributed Computing Models using Map-Reduce A...

引用

IEEE International Symposium on Information Theory

作者： Shanuja Sasi Onur Günlü B. Sundar Rajan Linkoping University Linkoping Sweden Indian Institute of Science Bengaluru India

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

A novel distributed computing model called Multi-access distributed computing (MADC) was recently introduced in [B. Federico and P. Elia, “Multi-Access distributed computing,” June 2022, [online] Available: http://***:2206.12851]. The MADC models with Combinatorial Topology (CT) were studied, where there are $\Lambda$ mapper nodes and $\dot{K}=\binom{\lambda}{\alpha}$ reducer nodes with each reducer node connected to distinct $\alpha$ mapper nodes. In this paper, we represent MADC models via 2-layered bipartite graphs called Map-Reduce Graphs (MRGs), and a set of arrays called Map-Reduce Arrays (MRAs) inspired from the Placement Delivery Arrays (PDAs) used in the coded caching literature. The connection between MRAs and MRGs is established, thereby providing coded shuffling schemes for the MADC models using the structure of MRAs. Moreover, a set of $g$ -regular MRAs is provided which corresponds to the existing scheme for MADC models with CT. One of the major limitations of the existing scheme for CT is that it requires an exponentially large number of reducer nodes for large $\Lambda$ . This can be overcome by representing CT by MRAs, where coding schemes can be derived even if some of the reducer nodes are not present.

关键词： Computational modeling Encoding Topology Bipartite graph distributed computing

来源：评论

学校读者我要写书评

暂无评论

Efficient Construction of Encoding Polynomials in a distributed Coded computing Scheme

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 2024年第3期E107A卷 476-485页

作者： Hibino, Daisuke Shibuya, Tomoharu Sophia Univ Grad Sch Sci & Technol Tokyo 1028554 Japan Sophia Univ Dept Informat & Commun Sci Tokyo 1028554 Japan TIS Inc Tokyo 1600022 Japan

distributed computing is one of the powerful solutions for computational tasks that need the massive size of dataset. Lagrange coded computing (LCC), proposed by Yu et al. [15], realizes private and secure distributed computing under the existence of stragglers, malicious workers, and colluding workers by using an encoding polynomial. Since the encoding polynomial depends on a dataset, it must be updated every arrival of new dataset. Therefore, it is necessary to employ efficient algorithm to construct the encoding polynomial. In this paper, we propose Newton coded computing (NCC) which is based on Newton interpolation to construct the encoding polynomial. Let K, L, and T be the number of data, the length of each data, and the number of colluding workers, respectively. Then, the computational complexity for construction of an encoding polynomial is improved from O(L(K+T) log2(K+T) log log(K+T)) for LCC to O(L(K+T) log(K+T)) for the proposed method. Furthermore, by applying the proposed method, the computational complexity for updating the encoding polynomial is improved from O(L(K + T) log2(K + T) log log(K + T)) for LCC to O(L) for the proposed method.

关键词： distributed computing Lagrange interpolation Newton interpolation polynomial evaluation computational complexity

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient distributed computing via Matrix Factorization

Communication-Efficient Distributed Computing via Matrix Fac...

引用

Asilomar Conference on Signals, Systems & Computers

作者： Seif Hussein Saeed Razavikia Sajad Daei Carlo Fischione School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

This paper presents a novel distributed computing framework, DCbMF (distributed computing by Matrix Factorization), for the efficient computation of linearly separable functions. Our framework operates within a multicast network of interconnected computing nodes to compute a set of output functions from input data through an efficient three-step process - Map, Shuffle, and Reduce. We cast the computation procedure as a sparse matrix factorization problem to achieve efficient communication and computation. To this end, we formulate an ℓ 0 optimization problem that seeks to minimize the number of nonzero elements in each matrix factor. Due to the intractability of ℓ 0 minimization, we turn to a relaxed ℓ 1 formulation of the problem. We devise a modified alternating direction method of multipliers to solve the biconvex optimization problem and prove the convergence of our algorithm to a stationary solution. The numerical experiments show that DCbMF outperforms similar computing frameworks for linearly separable function computation, achieving a substantial reduction in communication overhead by 98% while maintaining the same computation cost. Notably, leveraging sparse matrix factorization and alternating optimization highlights a fundamental tradeoff between compu-tation and communication costs and paves the way for scalable and efficient distributed computing applications.

关键词： Costs Simulation Prevention and mitigation Redundancy Minimization Computational efficiency Sparse matrices distributed computing Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Resilient, Secure, and Private Coded distributed Convolution computing for Mobile-Assisted Metaverse

引用

IEEE TRANSACTIONS ON MOBILE computing 2024年第12期23卷 12892-12906页

作者： Qiu, Houming Zhu, Kun Niyato, Dusit Tang, Bin Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 210016 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Hohai Univ Coll Comp Sci & Software Engn Nanjing 211100 Peoples R China

The Metaverse is recognized as the next-generation Internet that provides immersive interaction experiences for users. Convolutional neural networks (CNNs) play a crucial role in providing strong immersive experiences in the Metaverse. However, the Metaverse faces challenges in meeting the escalating demands for computing and storage resources due to the explosive growth of convolution tasks, resulting in severe performance degradation. To tackle these issues, coded distributed computing (CDC) is commonly employed. In this paper, we first propose an efficient and reliable mobile-assisted CDC framework to perform large-scale CNN training tasks for the Metaverse. In this framework, the various mobile devices act as workers contributing their resources to collaborate with each other to complete convolution operation tasks. Furthermore, we design a novel resilient, secure, and private coded convolution (RSPCC) scheme for the proposed framework. The RSPCC scheme achieves several significant performances. First, it substantially reduces computation latency compared to conventional convolution. Second, it efficiently mitigates an adverse impact of straggling workers returning results exceedingly slow. Third, we integrate a verifiable computing approach into the encoding/decoding process to check the correctness of the final computation results. Fourth, the PSPCC scheme considers the existence of colluding workers, providing information-theoretic privacy protection for input data. Finally, experimental results demonstrate that our proposed RSPCC scheme can significantly reduce execution time while ensuring the correctness of computation results within the CDC-based Metaverse framework.

关键词： Metaverse Convolution Task analysis Mobile handsets distributed computing Convolutional neural networks Immersive experience Coded distributed computing metaverse convolution mobile-assisted resiliency security privacy stragglers

来源：评论

学校读者我要写书评

暂无评论

Accelerating Causal Algorithms for Industrial-scale Data: A distributed computing Approach with Ray Framework 23

Accelerating Causal Algorithms for Industrial-scale Data: A ...

引用

Proceedings of the Third International Conference on AI-ML Systems

作者： Vishal Verma Vinod Reddy Jaiprakash Ravi Dream11 India

ISBN: (纸本)9798400716492

The increasing need for causal analysis in large-scale industrial datasets necessitates the development of efficient and scalable causal algorithms for real-world applications. This paper addresses the challenge of scaling causal algorithms in the context of conducting causal analysis on extensive datasets commonly encountered in industrial settings. Our proposed solution involves enhancing the scalability of causal algorithm libraries, such as EconML, by leveraging the parallelism capabilities offered by the distributed computing framework Ray. We explore the potential of parallelizing key iterative steps within causal algorithms to significantly reduce overall runtime, supported by a case study that examines the impact on estimation times and costs. Through this approach, we aim to provide a more effective solution for implementing causal analysis in large-scale industrial applications.

关键词： causal machine learning distributed computing observational study

来源：评论

学校读者我要写书评

暂无评论

Research on Concurrent Destruction of Embedded High-Availability distributed computing Platform

Research on Concurrent Destruction of Embedded High-Availabi...

引用

International Conference on Computer and Information Science (ACIS)

作者： Qinhan He Jinhui Liu Lijun He Guangfei Zhou School of Artificial intelligence Xidian University Xi'an China School of Computer Science and Technology Xidian University Xi'an China Aeronautics Computing Technique Research Institute Xi'an China

ISBN: (数字)9798350376647

ISBN: (纸本)9798350376654

The embedded distributed computing platform runs large-scale tasks with high complexity and high computing capacity requirements, and divides the embedded tasks required by super computing capacity into multiple independent sub-tasks, which can be simultaneously allocated to multiple computing nodes for paralleled execution. This paper researches that the embedded high-availability distributed computing platform ensures the real-time and deterministic requirements of embedded system function execution through the distribution of computing resources, network communication resources and storage resources, and implements the allocation and execution of distributed tasks under static partition configuration based on the distributed computing framework of the Actor model. In the paper, the destruction technology of large-scale storage resources in embedded high-availability distributed computing platform is also studied, the concurrent destruction is proposed, which improves the efficiency of destructive power input, solves the problems of large amount of computing nodes destruction, large destructive current and long destructive duration of large-scale storage resources in embedded system, and effectively solves the leakage of key information.

关键词： Information science Embedded systems Computational modeling Real-time systems Complexity theory Resource management distributed computing

来源：评论

学校读者我要写书评

暂无评论

A Communication-efficient Collaborative Task Offloading Method Based on distributed computing Cloud

A Communication-efficient Collaborative Task Offloading Meth...

引用

International Symposium on Parallel and distributed Processing with Applications, ISPA

作者： Ke Zhang Ruixing Zong Yingjie Song Yong Zhou Xiong Xiao Hunan University Changsha China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

An interconnected distributed computing cloud, comprising network-linked computational nodes, facilitates the allocation of computational resources across diverse locations. The strategic offloading of computationally demanding tasks from resource-constrained nodes to proximate nodes endowed with ample resources can enhance the resource utilization within the computing cloud. Given the interdependencies among segmented tasks, improper task partitioning may engender supplementary overheads. Furthermore, the process of task offloading introduces additional communication overhead. Consequently, the judicious division of task components and the selection of appropriate offloading destinations assume paramount significance in mitigating collaborative computing complexity and communication overhead. To address these challenges, we propose a communication-efficient collaborative task offloading methodology, which entails the segmentation and offloading of computation-intensive tasks from the source node to one or more high-performance nodes to fully leverage device resources. Additionally, we devise a subtask placement strategy predicated on minimizing communication distances, whereby multiple subtasks are allocated to distinct nodes based on the calculated communication latencies between the source node and various computing nodes. Experiments demonstrate that our task offloading method exhibits the lowest overall loss.

关键词： distributed processing Costs Accuracy Collaboration Reinforcement learning Prediction algorithms Complexity theory Resource management distributed computing

来源：评论

学校读者我要写书评

暂无评论

The Influence of Placement on Transmission in distributed computing of Boolean Functions

The Influence of Placement on Transmission in Distributed Co...

引用

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Ahmad Tanha Derya Malak Communication Systems Department EURECOM Sophia Antipolis France

ISBN: (数字)9798350393187

ISBN: (纸本)9798350393194

In this paper, we explore a distributed setting, where a user seeks to compute a linearly-separable Boolean function of degree M from N servers, each with a cache size M. Exploiting the fundamental concepts of sensitivity and influences of Boolean functions, we devise a novel approach to capture the interplay between dataset placement across servers and server transmissions and to determine the optimal solution for dataset placement that minimizes the communication cost. In particular, we showcase the achievability of the minimum average joint sensitivity, $\frac{N}{{{2^{M - 1}}}}$, as a measure for the communication cost.

关键词： Wireless communication Boolean functions Costs Sensitivity Atmospheric measurements Conferences Signal processing Particle measurements Servers distributed computing

来源：评论

学校读者我要写书评

暂无评论

Service Fluctuation Mitigated Energy and Effective computing Contract for distributed computing Network

Service Fluctuation Mitigated Energy and Effective Computing...

引用

IEEE International Conference on Communications in China Workshops (ICCC)

作者： Shoufeng Wang Ye Ouyang Fan Li Jianchao Guo Xuan Chen Lexi Xu Zhongke Zhang Lianhua Zhang Limeng Ma Xinzhou Cheng AsiaInfo technologies (China) INC. China China Unicom Beijing Branch Beijing China The Intelligent Network Innovation Center of China Unicom Beijing China China Unicom Research Institute Beijing China

ISBN: (数字)9798350377675

ISBN: (纸本)9798350377682

In the realm of distributed computing networks, managing service fluctuations and optimizing energy consumption are paramount challenges. This paper introduces the Service Fluctuation Mitigated Energy and Effective computing Contract (SrvfmEECC), which is a novel framework designed to address these challenges. The SrvfmEECC provides two contracting models, including Full Time Contract (FTC) and Part Time Contract (PTC), for computing nodes (CNs) upon their integration into the network. The framework strategically distributes computing services (CSs) across CNs to mitigate service fluctuations and optimize energy efficiency. Innovative aspects of SrvfmEECC include an initial performance threshold evaluation, specialized monitoring for FTC nodes, and a dynamic task allocation algorithm that prioritizes task reuse, PTC CN preferences, and load balancing. Numerical analysis demonstrates that SrvfmEECC can reach superior total gain and energy savings, particularly in larger network scales. The proposed algorithm enhances operational efficiency and contributes to environmental sustainability, marking a significant advancement in distributed computing resource management.

关键词： Energy consumption Fluctuations Numerical analysis Heuristic algorithms Energy conservation Energy efficiency Resource management distributed computing Contracts Monitoring

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：