检索结果-内蒙古大学图书馆

Bi-Objective Optimization of Data-Parallel Applications on Heterogeneous HPC Platforms for Performance and Energy Through Workload Distribution

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2021年第3期32卷 543-560页

作者： Khaleghzadeh, Hamidreza Fahad, Muhammad Shahid, Arsalan Manumachu, Ravi Reddy Lastovetsky, Alexey Univ Coll Dublin Sch Comp Sci Dublin 4 Ireland

Performance and energy are the two most important objectives for optimization on modern parallel platforms. In this article, we show that moving from single-objective optimization for performance or energy to their bi-objective optimization on heterogeneous processors results in a tremendous increase in the number of optimal solutions (workload distributions) even for the simple case of linear performance and energy profiles. We then study full performance and energy profiles of two real-life data-parallel applications and find that they exhibit shapes that are non-linear and complex enough to prevent good approximation of them as analytical functions for input to exact algorithms or optimization software for determining the Pareto front. We, therefore, propose a solution method solving the bi-objective optimization problem on heterogeneous processors. The method's novel component is an efficient and exact global optimization algorithm that takes as an input performance and energy profiles as arbitrary discrete functions of workload size, which accurately and realistically take into account resource contention and NUMA inherent in modern parallel platforms, and returns the Pareto-optimal solutions (generally speaking, load imbalanced). To construct the input discrete energy functions, the method employs a methodology that accurately models the energy consumption by a hybrid data-parallel application executing on a heterogeneous HPC platform containing different computing devices using system-level power measurements provided by power meters. We experimentally analyse the proposed solution method using three data-parallel applications, matrix multiplication, 2D fast Fourier transform (2D-FFT), and gene sequencing, on two connected heterogeneous servers consisting of multicore CPUs, GPUs, and Intel Xeon Phi. We show that it determines a superior Pareto front containing the best load balanced solutions and all the load imbalanced solutions that are ignored by load bala

关键词： Optimization Program processors Energy consumption Heuristic algorithms Multicore processing software algorithms Sequential analysis Heterogeneous platforms data-parallel applications workload partitioning performance optimization energy optimization bi-objective optimization workload distribution multicore CPU GPU Intel Xeon Phi

来源：评论

学校读者我要写书评

暂无评论

A Multiobjective Optimization of PCB Prototyping Assembly With OFA Based on the Similarity of Intuitionistic Fuzzy Sets

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2021年第7期29卷 2054-2061页

作者： Zhang, Wei-Bo Zhu, Guang-Yu Fuzhou Univ Sch Mech Engn & Automat Fuzhou 350108 Peoples R China

Shop scheduling is a significant factor affecting the ability of manufacturers of printed circuit board (PCB) prototyping assemblies to remain profitable and meet the needs of customers. This scheduling is complicated and involves various factors;thus, the shop scheduling problem of a PCB prototyping assembly is regarded as a multiobjective permutation flow shop scheduling problem (MOPFSP). A mathematical model with four objective functions is built based on the characteristics of a PCB prototyping assembly shop. In this article an aggregation-based approach is designed to aggregate multiple objective function values into the similarity of intuitionistic fuzzy sets (sIFSs). This approach is adopted as a fitness function assignment strategy and is combined with the optimal foraging algorithm (OFA) to build a multiobjective evolutionary algorithm: the OFA based on sIFSs (OFA-sIFSs). To verify the performance of OFA-sIFSs, six congress on evolutionary computation benchmark test functions, ten MOPFSP benchmark instances and a practical problem for a PCB prototyping assembly are solved by OFA-sIFSs and three state-of-the-art algorithms. Three types of similarity measures are evaluated. During the process of testing, four performance metrics, statistical analysis, and business software are employed. The results of this study suggest that OFA-sIFSs can be used to solve the MOPFSP and have better performances compared with the other three algorithms.

关键词： Fuzzy sets Optimization Job shop scheduling Linear programming Mathematical model software algorithms Intuitionistic fuzzy sets (IFSs) multiobjective optimization multiobjective permutation flow shop scheduling problem (MOPFSP) optimal foraging algorithm (OFA) printed circuit board (PCB) prototyping assembly

来源：评论

学校读者我要写书评

暂无评论

Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking

引用

IEEE ACCESS 2021年 9卷 132491-132507页

作者： Abichandani, Pramod Speck, Christian Bucci, Donald Mcintyre, William Lobo, Deepan Newark Coll Engn NCE New Jersey Inst Technol Dept Elect & Comp Engn Robot & Data Lab RADLab Newark NJ 07103 USA Lockheed Martin Adv Technol Labs Cherry Hill NJ 08002 USA

Enabling coordinated motion of multiple quadrotors is an active area of research in the field of small unmanned aerial vehicles (sUAVs). While there are many techniques found in the literature that address the problem, these studies are limited to simulation results and seldom account for wind disturbances. This paper presents the experimental validation of a decentralized planner based on multi-objective reinforcement learning (RL) that achieves waypoint-based flocking (separation, velocity alignment, and cohesion) for multiple quadrotors in the presence of wind gusts. The planner is learned using an object-focused, greatest mass, state-action-reward-state-action (OF-GM-SARSA) approach. The Dryden wind gust model is used to simulate wind gusts during hardware-in-the-loop (HWIL) tests. The hardware and software architecture developed for the multi-quadrotor flocking controller is described in detail. HWIL and outdoor flight tests results show that the trained RL planner can generalize the flocking behaviors learned in training to the real-world flight dynamics of the DJI M100 quadrotor in windy conditions.

关键词： Wind Heuristic algorithms Atmospheric modeling software algorithms Mathematical models Licenses Birds Cooperative systems design for experiments unmanned aerial vehicles multi-agent systems motion planning supervised learning

来源：评论

学校读者我要写书评

暂无评论

algorithms and Data Structures for New Models of Computation

引用

IT PROFESSIONAL 2021年第1期23卷 9-15页

作者： Black, Paul E. Flater, David Bojanova, Irena Natl Inst Stand & Technol NIST Gaithersburg MD 20899 USA Natl Inst Stand & Technol NIST Informat Technol Lab Software & Syst Div Gaithersburg MD USA

In the early days of computer science, the community settled on a simple standard model of computing and a basic canon of general purpose algorithms and data structures suited to that model. With isochronous computing, heterogeneous multiprocessors, flash memory, energy-aware computing, cache and other anisotropic memory, distributed computing, streaming environments, functional languages, graphics coprocessors, etc., the basic canon of algorithms and data structures is not enough. software developers know of real-world constraints and new models of computation and use them to design effective algorithms and data structures. These constraints motivate the development of elegant algorithms with broad utility. As examples, we present four algorithms that were motivated by specific hardware nuances, but are generally useful: reservoir sampling, majority of a stream, B-heap, and compacting an array in Theta(log n) time.

关键词： Computational Complexity Data Structures Multiprocessing Systems Power Aware Computing Data Structures General Purpose algorithms Isochronous Computing Energy Aware Computing Distributed Computing Reservoir Sampling B Heap X 0398 Log N Time Algorithm Computational Modeling software algorithms Data Structures Data Models software Engineering

来源：评论

学校读者我要写书评

暂无评论

Automated Analysis Method for software Failure Modes Based on Models and Data

Automated Analysis Method for Software Failure Modes Based o...

引用

International Conference on Reliability, Maintainability and Safety,ICRMS

作者： Erqiang Feng Chuncheng Wu Software Engineering Department Establishment of Chinese Aero-polytechnology Beijing China

ISBN: (数字)9798350329988

ISBN: (纸本)9798350329995

The primary purpose of software engineering is to provide high-quality software, aimed at reducing the amount of software failures. To increase the effectiveness and efficiency of an ordinary software failure-mode analysis, an automated software failure-mode analysis method is proposed. The automated method combines a model-based approach with historical data to overcome the limitations of the ordinary method. Furthermore, the extracting and matching algorithms that are employed in the automated analysis method are discussed. Feature space is used to obtain software failure mode features. The advantages of the automated method over the ordinary method are verified through engineering applications.

关键词： Knowledge engineering Analytical models Databases software algorithms Feature extraction software Data models software reliability Safety software engineering

来源：评论

学校读者我要写书评

暂无评论

HASP: High Availability SFC Placement Approach in Data Center Network 23

HASP: High Availability SFC Placement Approach in Data Cente...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Xu, Ziqi Han, Qingmian Cheng, Bo Niu, Meng Chen, Junliang Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology China The 54th Research Institute of China Electronics Technology Group Corporation Beijing China

ISBN: (纸本)9781665494571

Network Function Virtualization (NFV) is a promising technology that decouples network functions from the hardware. Virtual Network Functions (VNFs) can form service function chains (SFCs) and be orchestrated like internet applications. However, there are higher availability requirements for SFCs because the network's failure causes more severe consequences. This paper proposes the High Availability SFC Placement Approach (HASP) for SFC placement in Data Center. HASP includes a cross-backup (CB) model to improve the availability of SFCs. The software runs on the physical machine (PM), and once the PM fails, the software assigned to it will also fail. The CB model adopts offsite redundant VNF instances to avoid PM failure and guarantee SFC availability. HASP also considers the impact of data link reliability on SFC availability. In addition, a heuristic limited area search optimization (LASO) algorithm is incorporated to place the VNFs of SFCs. The evaluation results show that the LASO algorithm is 300% faster than the traditional heuristic algorithm. Combining the CB model and the LASO algorithm, HASP can improve the availability of SFCs and obtain the optimal placement scheme. © 2021 IEEE.

关键词： Data centers Smart cities Service function chaining Heuristic algorithms software algorithms software Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Research of Multipath Routing and Load Balancing Processes in software Defined Networks Based on Bird Migration Algorithm

Research of Multipath Routing and Load Balancing Processes i...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Dmitry Perepelkin Maria Ivanchikova Tin Nguyen Faculty of Computer Engineering Ryazan State Radio Engineering University Ryazan Russian Federation

Technology software defined networks (SDNs) allows managing the network at the software level, expanding the functionality to control the process of data transfer in the network. SDNs provide a new level of network application abstraction to provide a level of quality of service. The purpose of the work is to develop a scientific approach to the study of multipath routing and load balancing in the SDNs based on the bird migration algorithm (BMA). The article studies and analyzes the bird migration algorithm to solve the problem of multipath routing in the SDNs. A visual software system SDNLoadBalancer has been developed and an experimental SDN topology has been designed, which makes it possible to study in detail the processes of multipath routing in the SDNs based on the proposed approach. The article also compares the proposed approach with the results of the genetic algorithm and the artificial bee colony algorithm. The obtained results show the effectiveness of the proposed approach in the SDNs, made it possible to obtain results close to optimal in an acceptable time, and also reduce the transmission delay jitter in the network.

关键词： Visualization software algorithms Birds Routing Load management software systems Artificial bee colony algorithm

来源：评论

学校读者我要写书评

暂无评论

Validation Experiment of a Single-View Image-Sequence Algorithm to Identify Scale and Sea-State Characteristics

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2021年第3期46卷 864-878页

作者： Lin, Yolanda C. Earls, Christopher J. Cornell Univ Sch Civil & Environm Engn Ithaca NY 14850 USA Univ New Mexico Dept Geog & Environm Studies Albuquerque NM 87131 USA Cornell Univ Ctr Appl Math Ithaca NY 14850 USA

In applied science and engineering contexts, ocean free-surface wave-field characterization is an ongoing research area relevant to many diverse applications. The use of optical means for this characterization, in particular, is an appealing solution due to the promise of relatively high spatial resolution and modest cost (i.e., applying off-the-shelf still cameras or video cameras). This work investigates the validity of a previously published algorithm related to visible-wavelength ocean free-surface wave-field videos. The first part of the algorithm uses the video content to determine scale from a single-perspective, uncalibrated video. The second part of the algorithm applies the video content to determine sea-state characteristics, such as dominant wave period and wavelength. Due to the complications of obtaining well-characterized real-world data sets, algorithms proposed within the literature are not always validated experimentally, but the scientific community relies on the process of verification and validation to build confidence in emerging scientific contributions. This work addresses the need to assess the performance of the existing algorithm through validation experiments. Video recordings of approximate deep-water waves are collected in a controlled indoor environment to experimentally validate the algorithm, and a suite of postprocessing parameters is explored to identify the algorithm's sensitivities for a chosen unit problem. Recommendations for the algorithm parameter selection and an assessment of the algorithm efficacy are offered for researchers interested in the implementation of this algorithm.

关键词： Cameras Image sequences Lighting Sea measurements Standards software algorithms Optical surface waves Image processing image scale sea-state characterization validation experiment wave-field imaging

来源：评论

学校读者我要写书评

暂无评论

A Learn-to-Rank Method for Model-Based Regression Test Case Prioritization

引用

IEEE ACCESS 2021年 9卷 16365-16382页

作者： Huang, Yechao Shu, Ting Ding, Zuohua Zhejiang Sci Tech Univ Sch Informat Sci & Technol Hangzhou 310018 Peoples R China

Regression testing plays an indispensable role in software maintenance, which refers to retest the software following modifications to determine whether the changes have introduced new faults. However, regression testing requires massive amounts of effort to achieve a high fault detection rate. To address this issue, the test case prioritization technique is used to improve the fault detection rate by adjusting the execution order of test cases. For model-based regression test case prioritization, existing approaches have been developed using the single aspect of model-related information extracted from the previous executed test cases. In this paper, a novel learn-to-rank technique is proposed to prioritize test cases by combining the multidimensional features of Extended Finite State Machine (EFSM) under test to improve fault detection rate. Specifically, our method utilizes the random forest algorithm to combine multiple existing heuristic prioritization methods. Detailed experiments are conducted to evaluate the proposed method's performance in terms of Average Percentage Fault Detected (APFD). The experimental results show that the mean APFD value of our method reaches 0.884 for five subject EFSMs, which is 33.9% higher than the compared methods.

关键词： Testing Unified modeling language software Fault detection software algorithms Monitoring Heuristic algorithms Regression testing model based testing EFSM test case prioritization learn to rank

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Class Rebalancing Methods for Security Bug Report Classification

引用

IEEE TRANSACTIONS ON RELIABILITY 2021年第4期70卷 1658-1670页

作者： Zheng, Wei Xun, Yuxing Wu, Xiaoxue Deng, Zhi Chen, Xiang Sui, Yulei Northwestern Polytech Univ Natl Engn Lab Integrated Aerosp Ground Ocean Big MIIT Key Lab Big Data Storage & Management Xian 710129 Peoples R China Northwestern Polytech Univ Sch Software Xian 710129 Peoples R China Yangzhou Univ Coll Informat Engn Coll Artificial Intelligence Yangzhou 225127 Jiangsu Peoples R China Northwestern Polytech Univ Sch Comp Sci & Technol Xian 710129 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China Univ Technol Sydney Sch Comp Sci Sydney NSW 2007 Australia

Identifying security bug reports (SBRs) accurately from a bug repository can reduce a software product's security risk. However, the class imbalance problem exists for SBR prediction since the number of SBRs is often limited, and this issue has not been thoroughly investigated in previous studies. In our study, we choose six real-world projects of different sizes with over 120 000 bug reports in total as our empirical subjects. We first analyze the impact of the class imbalance issue on SBR prediction and confirm its negative impact on prediction performance. Then we perform a comparative study of six state-of-the-art class rebalancing methods combined with five popular classification algorithms for SBR prediction. By comparing with the baseline method Farsec, using the class rebalancing methods can improve the performance in 78% of cases in the worst case. Moreover, the combination of the Rose and random forest classification algorithm can construct the model with the best performance, which increases the performance by 267% in the best case and 75% on average in terms of F1-score. Finally, we summarize eight main findings based on our empirical studies' results, which can provide guidelines for choosing appropriate class rebalancing methods and classifiers for SBR prediction in practice.

关键词： Computer bugs Security Prediction algorithms Electronic mail software algorithms Predictive models Dimensionality reduction Class imbalance problem class rebalancing methods classification algorithms security bug report (SBRs) classification

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：