PLEIADES: An Internet‐based parallel/distributed system

The use of LAN‐based clusters of computers for computational purposes has been in use for several years with significant success and acceptability. The introduction of the Internet infrastructure as the interconnection medium of the cluster allows for additional flexibility and transparency of such systems. PLEIADES is an Internet‐based parallel/distributed system whose purpose is to allow users to use distant computational resources in order to form virtual clusters. In addition, PLEIADES can be used as a computational infrastructure service provider for applications in need of computational resources. PLEIADES uses a tiered architecture with particular emphasis on the existence of a middle tier, whose task is to assist in the communication between the interface and the resource management tiers. The existence of the middle tier allows for the creation of an open system that is able to easily integrate with new resource management platforms and tools. Since the use of a mature resource management system for parallel/distributed computing was a prerequisite of the PLEIADES architecture, the Condor resource management environment was used. The design and implementation characteristics of PLEIADES together with some experimental uses of the system are also presented. Copyright © 2002 John Wiley & Sons, Ltd.     

元计算系统的一个可扩展层次型资源管理模型

资源管理是元计算系统中的关键问题，为了支持大规模元计算应用，必须有效地解决资源联合分配问题。提出了一种可扩展层次型资源管理模型，在充分利用已有的批处理调度系统的基础上，通过核心资源管理器与局域资源调度系统的交互，为异构资源提供统一的接口，为解决资源的联合分配问题，提出了基于站点的层次型管理机制，可将应用程序的资源请求分布在相对紧密的资源集合上，不仅减小了元计算应用程序的整体通信开销，而且计算提供了资源预约服务。     

A dynamic framework for integrated management of all types of resources in P2P systems

Traditional Peer-to-Peer (P2P) systems were restricted to sharing of files on the Internet. Although some of the more recent P2P distributed systems have tried to support transparent sharing of other types of resources, like computer processing power, but none allow and support sharing of all types of resources available on the Internet. This is mainly because the resource management part of P2P systems are custom designed in support of specific features of only one type of resource, making simultaneous access to all types of resources impractical. Another shortcoming of existing P2P systems is that they follow a client/server model of resource sharing that makes them structurally constrained and dependent on dedicated servers (resource managers). Clients must get permission from a limited number of servers to share or access resources, and resource management mechanisms run on these servers. Because resource management by servers is not dynamically reconfigurable, such P2P systems are not scalable to the ever growing extent of Internet. We present an integrated framework for sharing of all types of resources in P2P systems by using a dynamic structure for managing four basic types of resources, namely process, file, memory, and I/O, in the same way they are routinely managed by operating systems. The proposed framework allows P2P systems to use dynamically reconfigurable resource management mechanisms where each machine in the P2P system can at the same time serve both as a server and as a client. The pattern of requests for shared resources at a given time identifies which machines are currently servers and which ones are currently clients. The client server pattern changes with changes in the pattern of requests for distributed resources. Scalable P2P systems with dynamically reconfigurable structures can thus be built using our proposed resource management mechanisms. This dynamic structure also allows for the interoperability of different P2P systems.     

网格计算及其关键技术综述

网格计算是近年来兴起的一个研究热点。它旨在使互联网上所有资源(计算资源、存储资源、通信资源、软件资源、信息资源、知识资源等)实现全面共享与协同工作,使整个因特网整合成一台巨大的超级计算机,为用户提供“即连即用”式的服务。论文不仅介绍了网格计算的概念、特点、起源、研究现状及当前几个典型的系统,而且从网格计算即异构网格结点在网络环境下的分布动态协同工作的角度出发,着重介绍了网格计算的体系结构、资源管理、任务管理、通信技术、安全机制、用户界面等关键技术。     

The implications of complexity for integrated resources management

Integrated environmental resources management is a purposeful activity with the goal to maintain and improve the state of an environmental resource affected by human activities. In many cases different goals are in conflict and the notion “integrated” clearly indicates that resources management should be approached from a broad perspective taking all potential trade-offs and different scales in space and time into account. However, we are yet far from putting into practice integrated resources management fully taking into account the complexity of human-technology-environment systems. The tradition of resources management and of dealing with environmental problems is characterized by a command and control approach. The increasing awareness for the complexity of environmental problems and of human-technology-environment systems has triggered the development of new management approaches. The paper discusses the importance of focusing on the transition to new management paradigms based on the insight that the systems to be managed are complex adaptive systems. It provides arguments for the role of social learning processes and the need to develop methods combining approaches from hard and soft systems analysis. Soft systems analysis focuses on the importance of subjective perceptions and socially constructed reality. Soft systems methods and group model building techniques are quite common in management science where the prime target of management has always been the social system. Resources management is still quite slow to take up such innovations that should follow as a logical consequence of adopting an integrated management approach. Integrated water resources management is used as example to provide evidence for the need to implement participatory and adaptive management approaches that are able to cope with increasing uncertainties arising from fast changing socio-economic conditions and global and climate change. Promising developments and future research directions are discussed. The paper concludes with pointing out the need for changes in the scientific community to improve the conditions for interdisciplinary, system-oriented and trans-disciplinary research.     

AAOP-based dynamically reconfigurable monitoring system

A key aspect of resource management is efficient and effective deployment of available resources whenever needed. The issue typically covers two areas: monitoring of resources used by software systems and managing the consumption of resources. A key aspect of each monitoring system is its reconfigurability – the ability of a system to limit the number of resources monitored at a given time to those that are really necessary at any particular moment. The authors of this article propose a fully dynamic and reconfigurable monitoring system based on the concept of Adaptable Aspect-Oriented Programming (AAOP) in which a set of AOP aspects is used to run an application in a manner specified by the adaptability strategy. The model can be used to implement systems that are able to monitor an application and its execution environment and perform actions such as changing the current set of resource management constraints applied to an application if the application/environment conditions change. Any aspect that implements a predefined interface may be used by the AAOP-based monitoring system as a source of information. The system utilizes the concept of dynamic AOP, meaning that the aspects (which are sources of information) may be dynamically enabled/disabled.     

Deploying Web-based visual exploration tools on the grid

Grid-based computing facilitates access to different resources. But management in a grid-based environment isn't centralized. To use grid resources effectively, researchers need a central access point to manage the resources, provide a visual means to explore the data, and record these explorations for further investigation and dissemination. This article describes such a system that's being developed jointly by the University of California, Davis, and the Lawrence Berkeley National Laboratory (LBNL). The centralized system acts as a portal into grid-enabled visualization systems. Scientists using the portal can focus on the important task of extracting insights from their data through visualization instead of having to worry about process management. Because scientists at LBNL and their collaborators require access to the portal from around the world, the portal's interface is entirely Web-based. Authenticated users only need a standards-compliant Web browser to explore their data from anywhere in the world. The portal provides a Web-based interface not just for exploring but also for encapsulating visualization data. Encapsulating the process lets users reproduce the visualization results for validation or extend those results by continuing data exploration. We discuss the integration of our grid-enabled visualization server, the visualization Web application that performs the visualization session management, and the Web-based interface.     

分布式教育资源管理系统的设计与实现

广州中小学基础教育信息化从2002年开始至今,已建设多种教学资源应用系统。教师从各个区域已建独立的资源系统中查询、获取课程所需内容是最主要的问题。由此设计分布式的资源管理系统,提高资源分布均衡与使用率,使不同地域的教育信息化资源相对统一。分布式资源管理系统的实现计算机网络能够让用户快速查找、访问各种多媒体资源。     

Market-oriented Grids and Utility Computing: The State-of-the-art and Future Directions

Traditional resource management techniques (resource allocation, admission control and scheduling) have been found to be inadequate for many shared Grid and distributed systems, that consist of autonomous and dynamic distributed resources contributed by multiple organisations. They provide no incentive for users to request resources judiciously and appropriately, and do not accurately capture the true value, importance and deadline (the utility) of a user’s job. Furthermore, they provide no compensation for resource providers to contribute their computing resources to shared Grids, as traditional approaches have a user-centric focus on maximising throughput and minimising waiting time rather than maximising a providers own benefit. Consequently, researchers and practitioners have been examining the appropriateness of ‘market-inspired’ resource management techniques to address these limitations. Such techniques aim to smooth out access patterns and reduce the chance of transient overload, by providing a framework for users to be truthful about their resource requirements and job deadlines, and offering incentives for service providers to prioritise urgent, high utility jobs over low utility jobs. We examine the recent innovations in these systems (from 2000–2007), looking at the state-of-the-art in price setting and negotiation, Grid economy management and utility-driven scheduling and resource allocation, and identify the advantages and limitations of these systems. We then look to the future of these systems, examining the emerging ‘Catallaxy’ market paradigm. Finally we consider the future directions that need to be pursued to address the limitations of the current generation of market oriented Grids and Utility Computing systems.     

Sharc: managing CPU and network bandwidth in shared clusters

We argue the need for effective resource management mechanisms for sharing resources in commodity clusters. To address this issue, we present the design of Sharc-a system that enables resource sharing among applications in such clusters. Sharc depends on single node resource management mechanisms such as reservations or shares, and extends the benefits of such mechanisms to clustered environments. We present techniques for managing two important resources-CPU and network interface bandwidth-on a cluster-wide basis. Our techniques allow Sharc to 1) support reservation of CPU and network interface bandwidth for distributed applications, 2) dynamically allocate resources based on past usage, and 3) provide performance isolation to applications. Our experimental evaluation has shown that Sharc can scale to 256 node clusters running 100,000 applications. These results demonstrate that Sharc can be an effective approach for sharing resources among competing applications in moderate size clusters.     

采用串行干扰消除的CDMA蜂窝系统中的跨层资源管理*

在采用串行干扰消除的CDMA蜂窝系统中,资源的稀缺性以及不同的译码顺序导致不同的系统性能等因素的存在,使得研究联合译码顺序调整的跨层资源管理很有必要。讨论了这类系统中无线资源管理的研究现状,包括功率控制、速率分配、容量分析与接纳控制等方面,分析了当前研究的局限性;给出了跨层资源管理的进一步研究方向。     

基于网格的物流资源挖掘模型的研究

分布在因特网上的物流资源具有地理分散和职权自治的特性,资源结构和接口难以统一。该文以网格、Agent和增量挖掘技术为基础,提出了不通过资源整合就能够实现全局信息挖掘的方法。分析了基于Web的物流资源网格系统,将其划分为物流域的集合实施分级管理。提出了新的面向网格的信息挖掘模型并设计了域内动态资源挖掘算法和域间请求式资源挖掘算法。该模型解决了不同物流系统之间的信息挖掘难题,算法中引入的增量挖掘技术提高了域间资源挖掘效率。     

基于Shibboleth的在线实验平台多资源访问认证

基于联盟认证的单点登录能够认证不同组织的用户,但资源的多样化导致了管理上的困难。针对该问题,采用Shibboleth联盟认证方式,规范多种资源访问的REST API接口,借助Shibboleth的属性筛选策略发布访问资源的授权码,实现多组织用户访问多种复杂资源的统一认证。以基于OpenEdX的在线实验平台为例,验证了采用Shibboleth进行用户统一认证,通过REST API接口以及授权码的发布可实现复杂资源共享,并在OpenEdX上以XBlock的方式实现与其余系统的数据交互。     

Knowledge management component in managing human resources for enterprises

Both human resources and knowledge are valuable assets for enterprises; therefore, effective management of these assets becomes inevitably critical for business success. While human resource management systems have been a research topic for more than two decades, knowledge management systems applied to human resource management are relatively new to both academia and industry. This study examines the use of knowledge management in a business environment such as human resource management. The evolution of information systems and information processing in the human resource management domain is presented, and a knowledge-based decision support system for human resource management is proposed.     

Multicore Resource Management

Current resource management mechanisms and policies are inadequate for future multicore systems. Instead, a hardware/software interface based on the virtual private machine abstraction would allow software policies to explicitly manage microarchitecture resources. VPM policies, implemented primarily in software, translate application and system objectives into VPM resource assignments. Then, VPM mechanisms securely multiplex, arbitrate, or distribute hardware resources to satisfy the VPM assignments.     

Material for publication

Abstract

Experimental applications of data from multispectral and other advanced sensors have demonstrated that remote sensing can make a valuable contribution to the monitoring and management of Canada's land resources. More frequent coverage and additional spectral bands on satellites planned for the mid-1980s and beyond will increase the opportunities for regular use of remotely sensed data. To effectively utilize these data in resource management, the remote sensing input must be matched with the resource management systems existing at that time. Thus, it is essential to anticipate the needs of resource management systems of the late 1980s and 1990s, to determine the appropriate role for remotely sensed data and to develop and implement a plan which will yield the remote sensing systems and methodologies necessary to meet the operational resource management requirements

Previous studies of resource information requirements indicate that there will be a need for geocoded remotely sensed data, improved image analysis techniques and better information integration concepts for future resource management systems. To develop a plan for meeting the anticipated requirements, the flow from the recording of the remotely sensed data to the end use of the derived information is considered first. The timeliness and accuracy requirements of different users, the diverse data types and forms for individual applications, the analysis methods/decision models needed and the implications of these factors for the configuration(s) of remote sensing input into the future resource management systems are examined. From this analysis, areas requiring further work (research, development, demonstration, transfer) are identified, and a plan of action is suggested.     

Soft sets based symbiotic organisms search algorithm for resource discovery in cloud computing environment

The dynamicity, coupled with the uncertainty that occurs between advertised resources and users’ resource requirement queries, remains significant problems that hamper the discovery of candidate resources in a cloud computing environment. Network size and complexity continue to increase dynamically which makes resource discovery a complex, NP-hard problem that requires efficient algorithms for optimum resource discovery. Several algorithms have been proposed in literature but there is still room for more efficient algorithms especially as the size of the resources increases. This paper proposes a soft-set symbiotic organisms search (SSSOS) algorithm, a new hybrid resource discovery solution. Soft-set theory has been proved efficient for tackling uncertainty problems that arises in static systems while symbiotic organisms search (SOS) has shown strength for tackling dynamic relationships that occur in dynamic environments in search of optimal solutions among objects. The SSSOS algorithm innovatively combines the strengths of the underlying techniques to provide efficient management of tasks that need to be accomplished during resource discovery in the cloud. The effectiveness and efficiency of the proposed hybrid algorithm is demonstrated through empirical simulation study and benchmarking against recent techniques in literature. Results obtained reveal the promising potential of the proposed SSSOS algorithm for resource discovery in a cloud environment.     

The roles of artificial intelligence in information systems

By classifying information processing tasks which are suitable for artificial intelligence approaches we determine an architectural structure for large systems. We visualize a three-layer architecture of private applications, mediating information servers, and an infrastructure which provides information resources.The base information resources are likely to use algorithmic techniques, since they will deal with many similar base objects. Their results are at higher level of abstraction, diverse, and fewer in number. The information servers must consider the scope, assumptions, and meaning of those intermediate results. Such processing will require techniques grounded in artificial intelligence concepts. Applications will need artificial intelligence techniques to augment the human interface and provide high-level decision support.Information processing in the intermediate layer is domain-specific and a module is constrained to a single ontology. Processing here is comprised of search and control of search, focusing, pruning, fusion, and other means of data reduction. There are also control tasks associated with effective resource management. Their results are then composable by higher-level applications, which have to solve problems involving multiple subtasks.The architecture presented here is a generalization of a server-client model. The mediating server modules will need a machine-friendly interface to support the application layer. The partitioning enhances maintainability, but raises questions of effectiveness and efficiency.Without new and composable structures we will be stuck with a mixture of obsolete large systems and isolated new applications. A formal partitioning provides a model where subproblems become accessible to research. Interoperation is now a distinct source of research problems. We identify some of these issues, and hope that composability of solutions will permit progress in building effective large systems.This paper is substantially based on [50] and [51]. I thank both the original and recent reviewers and listeners for feedback received on this material. Further comments were given by Marianne Siroker and Maria Zemankova.     

Production service system enabled by cloud-based smart resource hierarchy for a highly dynamic synchronized production process

The rapidly changing market demands entail a modern production system to cope with ever more diversified production orders. Not only the parameters and flow of the production process, sometimes the production resources and the corresponding application systems which make production decision and control even need to be reconfigurable. Due to the inability to provide dynamically reconfigurable manufacturing resources, systems and application systems, enterprises have to sacrifice profits to narrow their business scope or take risks to purchase a large number of production resources. In any case, it has brought operational burden to enterprises. This paper systematically analyses the production management requirements of a large-scale production system in terms of both hardware (production equipment) and software (application system) which is oriented to dynamic production demands, and then proposes a production service system enabled by cloud-based smart resource hierarchy (PnSS-CSRH). The platform is based on an open resource management system and inherits the general cloud structure and the AUTOM framework. PnSS-CSRH provides industrial users with integrated and synchronization services for the software and hardware resources involved in the production process in the PnSS mode. Using the integrated service mode, PnSS-CSRH not only helps resource providers to increase the frequency of resource leases, provides customers with targeted and systemic hardware and software overall solutions, and increases the platform usage rate, which brings more benefits to the stakeholders of PnSS-CSRH. At last, the PnSS-CSRH is used to provide services to the case company to validate the effectiveness.     

面向分布对象存储结构的高性能计算系统资源管理方法

当前的高性能计算系统的资源管理和调度关注的焦点是计算资源,然而随着高性能计算系统的规模增大和计算能力增强,其I/O瓶颈问题日益突出.由于高性能计算系统的存储结构多样性带来了存储资源管理分配的难题,在目前主流的资源管理系统中尚未有针对I/O存储资源的调度和管理.随着对象存储结构的发展和广泛使用,大多数主流高性能系统采用分布对象存储系统,研究对分布对象存储系统的管理并结合资源管理系统,实现面向存储的作业优化调度,对提升高性能计算系统的实际性能有重要意义.针对具有分布对象存储结构的高性能计算系统,研究面向分布存储的资源管理方法,在作业调度和资源分配时考虑不同应用的I/O需求,通过建立分布对象存储资源模型和应用程序I/O能力需求模型,并在资源调度和分配上根据不同的I/O应用级别,为作业分配合适的存储资源,设计并实现基于I/O能力分级的作业调度和资源分配算法.系统测试表明:该方法可以显著提高多作业环境下应用的性能,保证应用程序的性能稳定性,提高系统的吞吐率.