检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Dasgupta, Prithviraj Distributed Intelligent Systems Section Information Technology Division Naval Research Laboratory WashingtonDC United States

We consider the problem of learning to perform a task from demonstrations given by teachers or experts, when some of the experts' demonstrations might be adversarial and demonstrate an incorrect way to perform the task. We propose a novel technique that can identify parts of demonstrated trajectories that have not been significantly modified by the adversary and utilize them for learning, using temporally extended policies or options. We first define a trajectory divergence measure based on the spatial and temporal features of demonstrated trajectories to detect and discard parts of the trajectories that have been significantly modified by an adversarial expert, and could degrade the learner's performance, if used for learning, We then use an options-based algorithm that partitions trajectories and learns only from the parts of trajectories that have been determined as admissible. We provide theoretical results of our technique to show that repairing partial trajectories improves the sample efficiency of the demonstrations without degrading the learner's performance. We then evaluate the proposed algorithm for learning to play an Atari-like computer-based game called LunarLander in the presence of different types and degrees of adversarial attacks of demonstrated trajectories. Our experimental results show that our technique can identify adversarially modified parts of the demonstrated trajectories and successfully prevent the learning performance from degrading due to adversarial demonstrations. © 2023, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Performance Measurements in iVIC Virtual Machine Clones

Performance Measurements in iVIC Virtual Machine Clones

引用

International Conference on Advanced Information Networking and Applications Workshops (AINAW)

作者： James Hardy Lu Liu Nik Bessis Lei Cui Jianxin Li Distributed and Intelligent Systems Research Group School of Computing and Mathematics University of Derby Derby UK Advanced Computing Technology Institute Beihang University Beijing China

ISBN: (纸本)9781467308670

Virtualisation is a prevalent technology in current computing. Virtualisation can reduce hardware costs by server consolidation, implement "green computing" by reducing power consumption and is an underpinning process for cloud computing enabling the creation of a range of virtual networks and virtual supercomputers. This paper presents performance measurements for a cloning system known as iVIC developed in Beihang University, China. iVIC creates clusters of virtual computers that can communicate with each other through virtual switch mechanisms. The virtual switches can also allow communication between the clone environment and the physical world. The paper presents the results of impartial testing to identify the limiting factors for creating and starting numbers of clone machines, measure the power consumption of the physical system and the computational performance capability of the clones.

关键词： Cloning Random access memory Servers Virtual machining Documentation Testing Switches

来源：评论

学校读者我要写书评

暂无评论

Handling drifts and shifts in on-line data streams with evolving fuzzy systems

Handling drifts and shifts in on-line data streams with evol...

引用

作者： Lughofer, E. Angelov, P. Department of Knowledge-based Mathematical Systems Johannes Kepler University of Linz Altenbergerstrasse 69 A-4040 Linz Austria Intelligent Systems Research Laboratory School of Computing and Communications Lancaster University LA1 4WA United Kingdom

In this paper, we present new approaches to handling drift and shift in on-line data streams with the help of evolving fuzzy systems (EFS), which are characterized by the fact that their structure (rule base and parameters) is not fixed and not pre-determined, but is extracted from data streams on-line and in an incremental manner. When dealing with so-called drifts and s hifts in data streams, one needs to take into account (1) automatic detection of drifts and shifts and (2) automatic reaction to the drifts and shifts. This is important to avoid interruptions in the learning process and downtrends in predictive accuracy. To address the first problem, we propose an approach based on the concept fuzzy rule age. The second problem is addressed by including gradual forgetting of (1) antecedent parts and (2) consequent parameters. The latter can be achieved by including a forgetting factor in the recursive local learning process of the parameters, whose value is automatically extracted based on the intensity of the shift/drift. For addressing the former problem, we introduce two alternative methods: one is based on the evolving density-based clustering (eClustering) used to form the antecedents in the eTS approach;the other is based on the automatic adaptation of the learning rate of the evolving vector quantization (eVQ) method used to form the antecedent in the FLEXFIS approach. The paper concludes with an empirical evaluation of the impact of the proposed approaches in (on-line) real-world data sets in which drifts and shifts occur. © 2010 Elsevier B.V. All rights reserved.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Energy-Aware Offloading in Edge-Cloud Vehicular Networks 18

Machine Learning-based Energy-Aware Offloading in Edge-Cloud...

引用

18th International Conference on Mobile systems and Pervasive computing, MobiSPC 2021, The 16th International Conference on Future Networks and Communications, FNC 2021 and the 11th International Conference on Sustainable Energy Information Technology, SEIT 2021

作者： Ismail, Leila Materwala, Huned Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates

A vehicular network underpinned by the 3-tier vehicle-edge-cloud infrastructure enables an efficient and safer travel experience. The compute-intensive vehicular applications are often offloaded to the edge and/or cloud servers to enhance the applications' Quality of Services (QoS). The underlying edge-cloud servers consume a high among of energy. Consequently, it becomes crucial to optimizing energy consumption in the offloading process. Current energy-efficient offloading strategies in 2-tier vehicle-edge infrastructure, do not account for cloud computing energy consumption. In this paper, we address this void by proposing a machine learning-based energy-aware offloading algorithm, which optimizes the energy of the edge-cloud computing platform. The offloading strategy is enabled by the Support Vector Machine (SVM) regression model machine learning algorithm used for the edge-cloud power prediction. The experimental results show that the proposed algorithm is a promising approach in energy savings. © 2021 Elsevier B.V.. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Production Line Energy Cost Optimization with Renewable Energy Resource Usage in a Flexible Job Shop Configuration

引用

IFAC-PapersOnLine 2023年第2期56卷 7972-7977页

作者： Bruno Mota Pedro Faria Carlos Ramos GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Porto 4249-015 Portugal

Ever-increasing electricity prices due to inflation has become one of the main problems for manufacturing industries to deal with, mainly in a competitive market. The usage of Renewable Energy Resources (RER)s can be a great way to mitigate the energy costs of the electricity market, by not only covering the energy consumption but also turning a profit with the surplus. This paper aims to address these issues by proposing an intelligent production line scheduling system, in a flexible job shop configuration, that focuses on reducing energy costs. It considers dynamic pricing, RERs usage and surplus selling, and complex constraints applied in the production plan. To achieve these results, a Genetic Algorithm (GA) is employed. A case study from the literature, that uses real production data, is presented which does not take into account energy selling. Results show that with the proposed GA energy costs can be further reduced by 24.6% when considering RERs surplus selling.

关键词： Energy cost optimization Evolutionary algorithm Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Building a personal high performance computer with heterogeneous processors

Building a personal high performance computer with heterogen...

引用

International Conference on Grid and Cloud computing

作者： Li, Qiang Huo, Zhigang Sun, Ninghui National Research Center for Intelligent Computing Systems Beijing 100190 China Key Laboratory of Computer System and Architecture Chinese Academy of Sciences Beijing China Graduate University of Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9780769543130

Personal high performance computer (PHPC) requires lower cost and high performance. The Teraflops PHPC systems with special accelerator units like GPGPU have been presented, but they have difficulties in programming, compatibility and applicability. In this paper, we present HPP-PHPC, a hybrid architecture of heterogeneous processors connected by non-coherent off-chip system bus. The performance of HPP-PHPC is ensured by special processors integrated with vector units and high-efficiency interconnection between heterogeneous processors. And by the adoption of general processors and features like global physical address space and synchronization semantics in hardware, HPP-PHPC is more compatible and convenient for massage passing and PGAS programming model. Also it is more applicable to most applications, including those with many execution branches. Initial results obtained from our prototype system have proved our design. © 2010 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of multiple site resource provisioning: effects of the precision of availability information 08

引用

Proceedings of the 15th international conference on High performance computing

作者： Marcos Dias De Assunção Rajkumar Buyya Grid Computing and Distributed Systems Laboratory Department of Computer Science and Software Engineering The University of Melbourne Australia and NICTA Victoria Research Laboratory The University of Melbourne Australia Grid Computing and Distributed Systems Laboratory Department of Computer Science and Software Engineering The University of Melbourne Australia

ISBN: (纸本)9783540898931

Emerging deadline-driven Grid applications require a numberof computing resources to be available over a time frame, startingat a specific time in the future. To enable these applications, it is importantto predict the resource availability and utilise this informationduring provisioning because it affects their performance. It is impracticalto request the availability information upon the scheduling of everyjob due to communication overhead. However, existing work has notconsidered how the precision of availability information influences theprovisioning. As a result, limitations exist in developing advanced resourceprovisioning and scheduling mechanisms. This work investigateshow the precision of availability information affects resource provisioningin multiple site environments. Performance evaluation is conductedconsidering both multiple scheduling policies in resource providers andmultiple provisioning policies in brokers, while varying the precision ofavailability information. Experimental results show that it is possible toavoid requesting availability information for every Grid job scheduledthus reducing the communication overhead. They also demonstrate thatmultiple resource partition policies improve the slowdown of Grid jobs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The prototype of continuous media file system, CrownFS

The prototype of continuous media file system, CrownFS

引用

International Conference on Information Networking

作者： Se-Jin Hwang Jin-Uok Kim Myong-Soon Park Oh-Young Kwon Tae-Geun Kim Computer Systems Laboratory Computer Science Department Korea University Seoul South Korea Distributed Computing Laboratory Network Computing Department Systems Engineering Research Institute Daejeon South Korea

ISBN: (纸本)0818672250

Currently, many multimedia or continuous media server system is under development on top of either workstations or high-end PCs clustered with high speed networking facilities. In this paper we introduce Crown, a continuous media server on clustered high performance PCs with Myrinet, fast network switching equipment, and then address CrownFS, a file system on top of Crown, to offer continuous media streams to many subscribers at the same time. For easy and rapid tuning of the performance of CrownFS, we prototyped it. Prototyping requires less efforts and costs than direct implementation. Also, more reliable system optimization is obtainable rather than simulation. By using the prototype, we measured the scalability of CrownFS according to disk access strategies.

关键词： Prototypes File systems Streaming media Network servers Personal communication networks Multimedia systems Workstations High-speed networks File servers Costs

来源：评论

学校读者我要写书评

暂无评论

Scheduling algorithm for grid computing systems: An evolutionary multi-objective optimization

Scheduling algorithm for grid computing systems: An evolutio...

引用

4th Indian International Conference on Artificial Intelligence, IICAI 2009

作者： Perez-Cebreros, Arturo Martinez-Luna, Gilberto Vargas-Arroyo, Rocio Centre for Computer Research Database and Information Systems Laboratory National Polytechnic Institute Av. Juan Dios Batiz s/n Zacatenco 07738 Mexico City Mexico Centre for Computer Research Distributed Computing Laboratory CENIDET Interior Internado Palmira s/n Col. Palmira Cuernavaca Morelos Mexico

ISBN: (纸本)9780972741279

The accelerated development in Grid computing has positioned it as the promising next generation of computing platforms. Grid computing involves resource management, task scheduling, security problems, information management and so on. In particular, scheduling is one of the core issues to take in consideration in order to exploit the capabilities of Grid systems. In this paper we present a Multi-Objective Particle Swarm (MOPSO) based schedulers for efficiently allocating jobs to resources in a Grid system. The experimental study showed that MOPSO-based schedulers outperform existing GA implementations in the literature for the problem and also revealed their efficiency when makespan and flowtime are minimized. Copyright © 2009 by IICAI.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Demand Response Programs for Peak Reduction Using Consumers Aggregation

引用

IFAC-PapersOnLine 2023年第2期56卷 10941-10946页

作者： Modar Zheiry Pedro Faria Zita Vale Intelligent Systems Associated Laboratory (LASI) Research Group for Intelligent Engineering and Computing for Advanced Innovation and Development (GECAD) Polytechnic of Porto (P.PORTO) Porto Portugal

Many studies have examined the potential of the flexible loads within the power systems, taking advantage of Demand Response (DR) programs and Data Mining (DM) to optimize the system response and achieve sustainability through load management. The authors propose aggregation models to study their impact on the power system, using unsupervised DM technique which is Clustering (k-means). The scientific contribution of this paper is related to providing peak-reduction using clustering for load aggregation. A case study has been provided, consisting of three scenarios based on the load aggregation model. The results indicate the system responses to the different scenarios and illustrate the features of each load aggregation model. Furthermore, the results demonstrate how using DR programs combined with DM can effectively provide benefits to the system stability.

关键词： Energy Management Demand Response Peak Reduction Load Aggregation Clustering

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：