检索结果-内蒙古大学图书馆

3rd International Mediterranean Modelling Multiconference

作者： Claeys, Filip H. A. Vanrolleghem, Peter A. Fritzson, Peter Univ Ghent Dept Appl Math Biometr & Proc Control BIOMATH Coupure Links 653 B-9000 Ghent Belgium Univ Laval Dept Genie Civil modelEAU Quebec City PQ G1K 7P4 Canada Linkoping Univ Programming Environm Lab PELAB SE-58183 Linkoping Sweden

ISBN: (纸本)9788469007266

Tornado is a new advanced kernel for modelling and virtual experimentation (i.e., any evaluation of a model) in the water quality domain. Although primarily intended for use within this particular domain, the kernel is generic in nature and has a plethora of generally applicable features. This paper focuses on the ability of Tornado to perform a priori explorations of the integration solver setting space (i.e., the powerset of all possible combinations of solver settings such as accuracy, stepsize, ...) in order to find improved settings that may boost the efficiency of complex virtual experiments. The technique is an extension of the standard scenario analysis virtual experiment type that normally allows for evaluating the effects of changes in model parameters and initial conditions. It is shown that through a priori solver setting space exploration, the total execution time of computationally complex virtual experiments can be substantially reduced. Results from an application of the method to Monte Carlo simulation of a river system in Luxembourg are included.

关键词： modelling & simulation software development numerical solvers distributed execution

来源：评论

学校读者我要写书评

暂无评论

DEX: Scaling Applications Beyond Machine Boundaries 40

DEX: Scaling Applications Beyond Machine Boundaries

引用

40th IEEE International Conference on distributed Computing Systems (ICDCS)

作者： Kim, Sang-Hoon Chuang, Ho-Ren Lyerly, Robert Olivier, Pierre Min, Changwoo Ravindran, Binoy Ajou Univ Suwon South Korea Virginia Tech Blacksburg VA USA Univ Manchester Manchester Lancs England

ISBN: (纸本)9781728170022

Increasing the computing performance within a single-machine form factor is becoming increasingly difficult due to the complexities in scaling processor interconnects and coherence protocols. On the other hand, converting existing applications to run on multiple nodes requires a significant effort to rewrite application logic in distributed programming models and adapt the code to the underlying network characteristics. This paper presents DEX, an operating system-level approach to extend the execution boundary of existing applications over multiple machines. DEX allows the threads in a process to be relocated and distributed dynamically through a simple function call. DEX makes it trivial for developers to convert any application to be distributed over multiple nodes and for applications to transparently utilize disaggregated resources in a rack-scale system with minimal effort. Evaluation results using a running prototype and eight real applications showed promising results - six out of the eight scaled beyond the single-machine performance on DEX.

关键词： Thread migration distributed execution distributed memory RDMA

来源：评论

学校读者我要写书评

暂无评论

Communication decision in decentralized control of coordinated system

Communication decision in decentralized control of coordinat...

引用

IEEE International Conference on Mechatronics and Automation

作者： Liu, Haitao Qiao, Limin Hong, Bingrong Piao, Songhao Harbin Inst Technol Sch Comp Sci & Technol Harbin 150006 Heilongjiang Peoples R China

ISBN: (纸本)9781424408276

Although instantaneous and free communication simplifies multi-agent partially observable Markov decision processes (POMDPs) to single-agent POMDPs, in practice, communication is not free and reducing the amount of communication is often desirable. We present a novel approach for using a DAG to maintain and reason the possible joint beliefs of the team at the less cost of memory, by which communication decisions are made in a decentralized style. Our algorithm, called DAG-DEC-COMM, makes a tradeoff between the performance achieved by the team and the amount of communication used in planning. The experimental results on the benchmark problem show that our approach drastically reduces the communication with a significant decrease in storing the possible joint beliefs while improving the performance of distributed execution.

关键词： communication directed acyclic graph distributed execution decentralized POMDP

来源：评论

学校读者我要写书评

暂无评论

Using distributed object middleware to implement scalable workflow management systems

引用

Journal of Integrated Design and Process Science 1999年第2期3卷 1-19页

作者： Schuster, H. Neeb, J. Schamburger, R. MCC Austin TX United States University of Erlangen-Nuremberg Department of Computer Science Erlangen Germany

Support of distributed workflow execution and scalability are important issues for workflow management systems. Many cooperating workflow servers should build up a distributed workflow management system to meet the requirements especially of large enterprises. In these enterprises, access to workflows is usually restricted by certain organizational. Consequently, if an agent wants to start a workflow, only a small subset of the workflow servers of the enterprise is eligible to serve this request. One of them has to be selected. In this paper, we develop a formalization of these organizational rules and we provide a generally applicable distributed execution model for workflows, which is based on the distributed execution of subworkflows. This model is implemented by an advanced distributed object middleware. The distributed object system uses the organizational rules to implement the coordination among the workflow servers and to implement the load balancing and scheduling of workflow instances. © 1999, IOS Press. All rights reserved.

关键词： .scalability MANAGEMENT SYSTEMS SCALABLE WORKFLOW distributed workflow workflow servers distributed execution subworkflows distributed object system workflow instances WfMS

来源：评论

学校读者我要写书评

暂无评论

Increasing the Efficiency of Code Offloading through Remote-side Caching 11

Increasing the Efficiency of Code Offloading through Remote-...

引用

11th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)

作者： Berg, Florian Duerr, Frank Rothermel, Kurt Univ Stuttgart Inst Parallel & Distributed Syst D-70569 Stuttgart Germany

ISBN: (纸本)9781467377010

End users execute today on their smart phones different kinds of mobile applications like calendar apps or high-end mobile games, differing in local resource usage. Utilizing local resources of a smart phone heavily, like playing high-end mobile games, drains its limited energy resource in few hours. To prevent the limited energy resource from a quick exhaustion, smart phones benefit from executing resource-intensive application parts on a remote server in the cloud (code offloading). During the remote execution on the remote server, a smart phone waits in idle mode until it receives a result. However, code offloading introduces computation and communication overhead, which decreases the energy efficiency and induces monetary cost. For instance, sending or receiving execution state information to or from a remote server consumes energy. Moreover, executing code on a remote server instance in a commercial cloud causes monetary cost. To keep consumed energy and monetary cost low, we present in this paper the concept of remote-side caching for code offloading, which increases the efficiency of code offloading. The remote-side cache serves as a collective storage of results for already executed application parts on remote servers, avoiding the repeated execution of previously run application parts. The smart phone queries the remote-side cache for corresponding results of resource-intensive application parts. In case of a cache hit, the smart phone gets immediately a result and continues the application execution. Otherwise, it migrates the application part and waits for a result of the remote execution. We show in our evaluation that the use of a remote-side cache decreases energy consumption and monetary cost for mobile applications by up to 97% and 99%, respectively.

关键词： Mobile Cloud Computing Code Offloading distributed execution Data Replication Function Caching

来源：评论

学校读者我要写书评

暂无评论

Implementation and Validation of a Master-Slave distributed Crawler Applied in Internet Information Retrieval

Implementation and Validation of a Master-Slave Distributed ...

引用

7th International Conference on Computing and Convergence Technology (ICCCT)

作者： Passos, Anderson Miyazaki Int Coll Dept Comparat Culture Miyazaki Japan

ISBN: (纸本)9781467308946;9788994364261

This study describes a preliminary research on Information Retrieval (IR) systems. We developed a prototype tool that runs on a master-slave model and uses distributed processing in order to decentralize the workload while retrieving information from the Internet. Later, its viability is demonstrated with a set of executions and the discussion follows with an analysis of the master process overload versus the number of slaves connected.

关键词： web crawling information retrieval data mining parallel execution master-slave distributed execution

来源：评论

学校读者我要写书评

暂无评论

BRAIN-IoT Architecture and Platform for Building IoT Systems 7

BRAIN-IoT Architecture and Platform for Building IoT Systems

引用

7th International Conference on Internet of Things, Big Data and Security (IoTBDS)

作者： Chehida, Salim Bensalem, Saddek Conzon, Davide Ferrera, Enrico Tao, Xu Univ Grenoble Alpes VERIMAG CNRS Grenoble France LINKS Fdn IoT & Robot Area Turin Italy Univ Kentucky Comp Sci Dept Lexington KY 40506 USA

ISBN: (纸本)9789897585647

The integration of Internet of Things (IoT) for building complex and critical systems requires powerful platforms enabling to deal with multiple issues, including modeling, monitoring, control, maintaining and management of IoT applications. In this work, the authors propose a new platform based on layered architecture that integrates a set of assets for model-based development of IoT systems. This platform named BRAIN-IoT aims to meet the new challenges of IoT applications and to reduce the effort for building and managing these applications. It consists of three frameworks that allow building decentralized IoT applications with computing capacity at the edge in a computing continuum with the cloud. The modeling and validation framework is used to design, develop, and validate IoT applications logic. The distributed execution framework provides an autonomic distributed infrastructure for the dynamic deployment and execution of IoT services on a mixed cloud-edge environment. The security framework enables access control, end-to-end security and privacy of data collected using IoT devices. The BRAIN-IoT platform is mapped to a well-established IoT reference architecture and experimented on two industrial use cases.

关键词： IoT Architecture Model-based Design Interoperability distributed execution Security and Privacy Monitoring Resiliency Cloud Edge Decentralized IoT Applications

来源：评论

学校读者我要写书评

暂无评论

Decentralized communication strategies for coordinated multi-agent policies

引用

3rd International Workshop on Multi-Robot Systems

作者： Roth, M Simmons, R Veloso, M Carnegie Mellon Univ Inst Robot Pittsburgh PA 15213 USA

ISBN: (纸本)1402033885

Although the presence of free communication reduces the complexity of multi-agent POMDPs to that of single-agent POMDPs, in practice, communication is not free and reducing the amount of communication is often desirable. We present a novel approach for using centralized "single-agent" policies in decentralized multi-agent systems by maintaining and reasoning over the possible joint beliefs of the team. We describe how communication is used to integrate local observations into the team belief as needed to improve performance. We show both experimentally and through a detailed example how our approach reduces communication while improving the performance of distributed execution.

关键词： communication distributed execution decentralized POMDP

来源：评论

学校读者我要写书评

暂无评论

Legate NumPy: Accelerated and distributed Array Computing 19

Legate NumPy: Accelerated and Distributed Array Computing

引用

International Conference for High Performance Computing, Networking, Storage and Analysis (SC)

作者： Bauer, Michael Garland, Michael NVIDIA Santa Clara CA 95051 USA

ISBN: (数字)9781450362290

ISBN: (纸本)9781450362290

NumPy is a popular Python library used for performing array-based numerical computations. The canonical implementation of NumPy used by most programmers runs on a single CPU core and is parallelized to use multiple cores for some operations. This restriction to a single-node CPU-only execution limits both the size of data that can be handled and the potential speed of NumPy code. In this work we introduce Legate, a drop-in replacement for NumPy that requires only a single-line code change and can scale up to an arbitrary number of GPU accelerated nodes. Legate works by translating NumPy programs to the Legion programming model and then leverages the scalability of the Legion runtime system to distribute data and computations across an arbitrary sized machine. Compared to similar programs written in the distributed Dask array library in Python, Legate achieves speed-ups of up to 10X on 1280 CPUs and 100X on 256 GPUs.

关键词： Legate NumPy Legion Python HPC distributed execution GPU Control Replication Logical Regions Thsk-Based Runtimes

来源：评论

学校读者我要写书评

暂无评论

Petri net splitting operation within embedded systems co-design

Petri net splitting operation within embedded systems co-des...

引用

5th IEEE International Conference on Industrial Informatics

作者： Costa, Aniko Gomes, Luis Univ Nova Lisboa Fac Ciencias & Tecnol P-2829516 Caparica Portugal

ISBN: (纸本)9781424408504

As system complexity increases, the role of Model Based Development is more and more important. Several modeling formalisms are widely used when considering the area of hardware-software co-design of embedded systems. The goal of the work presented in this paper is to contribute for the usage of Petri nets as the system-level specification language. Techniques for system model partitioning into components are a major concern within co-design methodologies. This paper proposes a net operation, called net splitting, able to decompose a Petri net model into Petri net sub-models using synchronous communication channels. The operation is based on the definition of a valid cutting set. Specific rules are presented in order to obtain the sub-models from the initial one. The generated sub-models are associated with components to be executed concurrently, allowing a distributed execution of the initial model. On the other hand, at the implementation level, it is necessary to accommodate a severe deviation on synchronous communication channel execution semantics (as far as the components are in execution in different controllers and zero time delay is not possible to obtain). For some specific situations, initial model properties are not preserved considering execution of components obtained after net splitting operation. Although, it is possible to anticipate the impact of using specific communication channels models at the implementation level. For that end, a second step on property verification is needed in order to validate a specific partitioning solution. An illustrative example applying the referred mechanisms is presented.

关键词： Petri net embedded systems co-design distributed execution system partitioning

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：