检索结果-内蒙古大学图书馆

Integrated Energy and Trust-Based Semi-Markov Prediction for Lifetime Maximization in Wireless Sensor Networks

WIRELESS PERSONAL COMMUNICATIONS 2021年第1期118卷 505-522页

作者： Famila, S. Jawahar, A. Vimalraj, S. Leones Sherwin Lydia, J. SSN Engn Coll Dept Elect & Commun Engn Chennai Tamil Nadu India Panimalar Engn Coll Dept Elect & Commun Engn Chennai Tamil Nadu India Easwari Engn Coll Dept Elect & Elect Engn Chennai Tamil Nadu India

Many of today's computing and communication models are distributed systems that are composed of autonomous computational entities that communicate with each other, usually by passing messages. Distributed systems encompass a variety of applications and wireless sensor networks (WSN) is an important application of it. The tiny, multiple functionality and low power sensor nodes are considered to be interconnected in the WSN for efficient process of aggregating and transmitting the data to the base station. The clustering-based schemes of sensor networks are capable of organizing the network through the utilization of a specifically designated node termed as the cluster head for the objective of energy conservation and data aggregation. Further, the cluster head is responsible for conveying potential information collected by the cluster member nodes and aggregate them before transmitting it to the base station. In this paper, a Reliable Cluster Head Selection Technique using Integrated Energy and Trust-based Semi-Markov Prediction (RCHST-IETSMP) is proposed with the view to extend the lifetime of sensor networks. This proposed RCHST-IETSMP incorporated two significant parameters associated with energy and trust for effective selection of cluster head facilitated through the merits of Semi-Markoc prediction integrated with the Hyper Erlang distribution process. The simulation results of the proposed RCHST-IETSMP scheme is proving to be efficient in upholding the residual energy of the network and the throughput to a maximum level of 23% and 19% predominant to the trust and energy-based clustering schemes considered for investigation.

关键词： Distributed algorithms Clustering Semi-Markov prediction Data aggregation parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Cloud-Ready Acceleration of Formal Method Techniques for Cyber-Physical Systems

IEEE DESIGN & TEST

引用

IEEE DESIGN & TEST 2021年第5期38卷 25-34页

作者： Khaled, Mahmoud Zamani, Majid Tech Univ Munich Munich Germany Univ Colorado Comp Sci Dept Boulder CO USA Ludwig Maximilian Univ Munich Munich Germany

Editor's notes: Controller synthesis using formal specifications has shown considerable promise in recent years. However, it is computationally very expensive. This article shows how cloud computing can come to th... 详细信息

关键词： Kernel Cloud computing parallel algorithms Task analysis Acceleration Copper Formal Methods Cyber-Physical Systems Internet of Things High Performance Computing parallel algorithms Cloud Computing OpenCL Message Passing Interface (MPI) GPGPU FPGA

来源：评论

学校读者我要写书评

暂无评论

Design of parallel Algorithm of Transfer Learning based on Weak Classifier 16

Design of Parallel Algorithm of Transfer Learning based on W...

引用

16th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2021

作者： Hui, Zong Guanqun, Tian Qiankun, Zhao Long, Hong Huaiyin Institute of Technology College of Computer Science and Technology Huaian China Nanjing University of Posts and Telecommunications College of Computer Science and Technology Nanjing China

ISBN: (纸本)9781665405539

In the TrAdaBoost method that based on sample transfer learning, weak classifier is the kernel of its design. Aiming at the problem of high time cost for the serial algorithm of weak classifier, a parallel algorithm of weak classifier is designed and applied to the prediction of diabetes in this paper. Experiments are performed on a computer with an 8-core processor, the speedup ratio of the TrAdaBoost algorithm after the parallelization of the weak classifier is 5.14, and the classification accuracy of diabetes prediction is 79%, which means this design can make an auxiliary diagnosis for patients. © 2021 IEEE.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Examination of Semi-Analytical Solution Methods in the Coarse Operator of Parareal Algorithm for Power System Simulation

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2021年第6期36卷 5068-5080页

作者： Park, Byungkwon Sun, Kai Dimitrovski, Aleksandar Liu, Yang Simunovic, Srdjan Oak Ridge Natl Lab Computat Sci & Engn Div Oak Ridge TN 37830 USA Univ Cent Florida Dept ECE Orlando FL 32816 USA Univ Tennessee Dept EECS Knoxville TN 37996 USA

With continuing advances in high-performance parallel computing platforms, parallel algorithms have become powerful tools for development of faster than real-time power system dynamic simulations. In particular, it has been demonstrated in recent years that parallel-in-time (Parareal) algorithms have the potential to achieve such an ambitious goal. The selection of a fast and reasonably accurate coarse operator of the Parareal algorithm is crucial for its effective utilization and performance. This paper examines semi-analytical solution (SAS) methods as the coarse operators of the Parareal algorithm and explores performance of the SAS methods to the standard numerical time integration methods. Two promising time-power series-based SAS methods were considered;Adomian decomposition method and Homotopy analysis method with a windowing approach for improving the convergence. Numerical performance case studies on 10-generator 39-bus system and 327-generator 2383-bus system were performed for these coarse operators over different disturbances, evaluating the number of Parareal iterations, computational time, and stability of convergence. All the coarse operators tested with different scenarios have converged to the same corresponding true solution (if they are convergent) and the SAS methods provide comparable computational speed, while having more stable convergence to the true solution in many cases.

关键词： Synthetic aperture sonar Power system stability Power system dynamics Numerical models Mathematical model Heuristic algorithms Computational modeling High-performance computing parallel algorithms power system dynamic simulations semi-analytical solution methods transient stability

来源：评论

学校读者我要写书评

暂无评论

Multi-GPU Design and Performance Evaluation of Homomorphic Encryption on GPU Clusters

引用

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED SYSTEMS 2021年第2期32卷 379-391页

作者： Al Badawi, Ahmad Veeravalli, Bharadwaj Lin, Jie Xiao, Nan Kazuaki, Matsumura Khin Mi Mi, Aung ASTAR Inst Infocomm Res I2R Singapore 138632 Singapore Natl Univ Singapore Dept Elect & Comp Engn Singapore 117576 Singapore Barcelona Supercomp Ctr BSC Barcelona Spain

We present a multi-GPU design, implementation and performance evaluation of the Halevi-Polyakov-Shoup (HPS) variant of the Fan-Vercauteren (FV) levelled Fully Homomorphic Encryption (FHE) scheme. Our design follows a data parallelism approach and uses partitioning methods to distribute the workload in FV primitives evenly across available GPUs. The design is put to address space and runtime requirements of FHE computations. It is also suitable for distributed-memory architectures, and includes efficient GPU-to-GPU data exchange protocols. Moreover, it is user-friendly as user intervention is not required for task decomposition, scheduling or load balancing. We implement and evaluate the performance of our design on two homogeneous and heterogeneous NVIDIA GPU clusters: K80, and a customized P100. We also provide a comparison with a recent shared-memory-based multi-core CPU implementation using two homomorphic circuits as workloads: vector addition and multiplication. Moreover, we use our multi-GPU Levelled-FHE to implement the inference circuit of two Convolutional Neural Networks (CNNs) to perform homomorphically image classification on encrypted images from the MNIST and CIFAR - 10 datasets. Our implementation provides 1 to 3 orders of magnitude speedup compared with the CPU implementation on vector operations. In terms of scalability, our design shows reasonable scalability curves when the GPUs are fully connected.

关键词： Homomorphic encryption parallel algorithms multi-GPU clusters performance evaluation

来源：评论

学校读者我要写书评

暂无评论

A Split Execution Model for SpTRSV

引用

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED SYSTEMS 2021年第11期32卷 2809-2822页

作者： Ahmad, Najeeb Yilmaz, Buse Unat, Didem Koc Univ Dept Comp Sci & Engn TR-34450 Istanbul Turkey Istinye Univ Dept Comp Sci TR-34010 Istanbul Turkey

Sparse Triangular Solve (SpTRSV) is an important and extensively used kernel in scientific computing. parallelism within SpTRSV depends upon matrix sparsity pattern and, in many cases, is non-uniform from one computational step to the next. In cases where the SpTRSV computational steps have contrasting parallelism characteristics- some steps are more parallel, others more sequential in nature, the performance of an SpTRSV algorithm may be limited by the contrasting parallelism characteristics. In this work, we propose a split-execution model for SpTRSV to automatically divide SpTRSV computation into two sub-SpTRSV systems and an SpMV, such that one of the sub-SpTRSVs has more parallelism than the other. Each sub-SpTRSV is then computed using different SpTRSV algorithms, which are possibly executed on different platforms (CPU or GPU). By analyzing the SpTRSV Directed Acyclic Graph (DAG) and matrix sparsity features, we use a heuristics-based approach to (i) automatically determine the suitability of an SpTRSV for split-execution, (ii) find the appropriate split-point, and (iii) execute SpTRSV in a split fashion using two SpTRSV algorithms while managing any required inter-platform communication. Experimental evaluation of the execution model on two CPU-GPU machines with a matrix dataset of 327 matrices from the SuiteSparse Matrix Collection shows that our approach correctly selects the fastest SpTRSV method (split or unsplit) for 88 percent of matrices on the Intel Xeon Gold (6148) + NVIDIA Tesla V100 and 83 percent on the Intel Core I7 + NVIDIA G1080 Ti platform achieving speedups up to 10x and 6.36x respectively.

关键词： Sparse matrices parallel algorithms Computational modeling Kernel Graphics processing units Fats Phased arrays Sparse triangular solve CPU-GPU computing heterogeneous computing sparse linear systems SpTRSV SpTS

来源：评论

学校读者我要写书评

暂无评论

A novel task scheduling approach for dependent non-preemptive tasks using fuzzy logic

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2021年第3期15卷 214-222页

作者： Hassan, Heba E. Nagib, Gihan Ibrahiem, Khaled Hosny Fayoum Univ Fac Engn Al Fayyum Egypt

Multiprocessor task scheduling problem is a pressing problem that affects systems' performance and is still being investigated by the researchers. Finding the optimal schedules is considered to be a computationally hard problem. Recently, researchers have used fuzzy logic in the field of task scheduling to achieve optimal performance, but this area of research is still not well investigated. In addition, there are various scheduling algorithms that used fuzzy logic but most of them are often performed on uniprocessor systems. This article presents a new proposed algorithm in which the priorities of the tasks are derived from the fuzzy logic and bottom level parameter. This approach is designed to find task schedules with optimal or sub-optimal lengths in order to achieve high performance for a multiprocessor environment. With respect to the proposed algorithm, the precedence constraints between the non-preemptive tasks and their execution times are known and described by a directed acyclic graph. The number of processors is fixed, the communication costs are negligible and the processors are homogeneous. The suggested technique is tested and compared with the Prototype Standard Task Graph Set.

关键词： computational complexity directed graphs fuzzy logic multiprocessing systems parallel algorithms processor scheduling

来源：评论

学校读者我要写书评

暂无评论

Efficient parallel determinacy race detection for structured futures 21

Efficient parallel determinacy race detection for structured...

引用

33rd ACM Symposium on parallelism in algorithms and Architectures, SPAA 2021

作者： Xu, Yifan Agrawal, Kunal Lee, I-Ting Angelina Washington University in St. Louis St. LouisMO United States

ISBN: (纸本)9781450380706

In task-parallel code, a determinancy race occurs when two logically parallel instructions access the same memory location in a conflicting way. A determinacy race tends to be a bug as it leads to non-deterministic program behaviors. Researchers have studied algorithms for detecting determinacy races in task-parallel code, with most prior work focuses on computations with nice structural properties (e.g., fork-join or pipeline parallelism). For such computations, one can devise provably efficient algorithms with constant overhead, leading to a asymptotically optimal running time - - O(T_1 / P + T_∞) on P cores for a computation with T_1 work and T_∞ span. More recently, researchers have begun to address the problem of race detecting computations with less structural properties, such as ones that arise from the use of futures. Due to the lack of structural properties, the race detection algorithm incurs higher overhead. % Given a computation with work T_1 and span T_∞, the state-of-the-art parallel algorithm for race detecting programs with futures runs in time O((T_1 lgk + k^2) / P + T_∞(lg k + lgr lgk )) on P cores (Xu γ•l, 2020), where k is the total number of futures used, k is the maximum number of future operations per "future task,'' and r is the maximum number of readers between two consecutive writes to a given memory location. Interestingly, it has been shown that when one imposes certain restrictions on the use of futures, referred to as the structured futures, although the restrictions do not entirely eliminate arbitrary dependences among subcomputations, one can race detect such programs more efficiently than that for programs with general futures (i.e., no restrictions). The improved efficiency has only been demonstrated for a sequential algorithm (Utterback γ•l, 2019) that race detects while executing the computation sequentially, however. The algorithm requires sequential execution, because the correctness of the algorithm relies on updating the neces

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on parallel algorithm based on AABB bounding box coordinate chain method 2

Research on parallel algorithm based on AABB bounding box co...

引用

2nd International Seminar on Computer Science and Engineering Technology, SCSET 2020

作者： Qu, Huiyan School of Information Technology Jilin Agricultural University Changchun Jilin Province130118 China

With the rapid development of virtual reality technology and collision detection technology, virtual reality has become a lot of research fields in China. Collision detection is one of the most important technologies, and virtual surgery simulation has gradually become an important application of medicine in virtual reality technology. Virtual surgery can not only provide a skilled training platform for medical staff, but also analyze the feasibility and danger of surgical scheme, so that medical staff can have the same authenticity and strong immersion in virtual environment as in physical surgery. In this paper, a mixed hierarchical bounding box is constructed to detect the collision between the virtual human soft tissue and the rigid tissue of surgical instruments, and a parallel algorithm, fast bounding box coordinate chain calculation, compression storage and so on are introduced. For the deformation model of the software which is difficult to construct, the collision detection can be completed quickly and accurately, which can effectively save the collision detection time and improve the real-time performance of the collision. © Published under licence by IOP Publishing Ltd.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

A parallel variable neighborhood search approach for the obnoxious p-median problem

引用

INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH 2020年第1期27卷 336-360页

作者： Herran, Alberto Colmenar, Jose M. Marti, Rafael Duarte, Abraham Univ Rey Juan Carlos Dept Comp Sci Madrid Spain Univ Valencia Dept Estadist & Invest Operat Valencia Spain

The obnoxious p-median problem consists of selecting p locations, considered facilities, in a way that the sum of the distances from each nonfacility location, called customers, to its nearest facility is maximized. This is an NP-hard problem that can be formulated as an integer linear program. In this paper, we propose the application of a variable neighborhood search (VNS) method to effectively tackle this problem. First, we develop new and fast local search procedures to be integrated into the basic VNS methodology. Then, some parameters of the algorithm are tuned in order to improve its performance. The best VNS variant is parallelized and compared with the best previous methods, namely branch and cut, tabu search, and GRASP over a wide set of instances. Experimental results show that the proposed VNS outperforms previous methods in the state of the art. This fact is finally confirmed by conducting nonparametric statistical tests.

关键词： obnoxious location metaheuristics VNS parallel algorithms

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：