基于议价机制的网格资源分配研究

资源管理和分配是网格计算的核心问题，用市场机制可有效地管理和分配网格资源。提出了一个基于议价机制的网格资源分配模型，设计了资源分配策略。模拟实验表明该模型能够较好地适应网格环境的动态变化，并实现各个网格计算资源的负载平衡。     

网格环境面向服务的Multi-Agent交互协议及协商模型

网格目的是为了实现地理上分布的异构资源和服务的共享.资源的分配、应用开发和模型使用是网格环境中的关键问题和复杂的任务.利用具有一定自主推理、自主决策能力的Agent以及由其组成的Multi-Agent系统(MAS)来模拟、优化、实施、控制网格资源的分配和管理为网格研究提供了一种有效的新方法.在基于MAS的网格系统中资源分配和调度活动都是通过协商完成的,因此如何保证Agent之间能够有效、有序地进行协商的协商机制是网格计算环境的重点.针对目前对协商的研究还只是单纯地研究协商协议或者只重视研究协商策略,缺乏对网格环境下协商模型的研究背景下,提出了一个医学图像处理网格环境下的面向服务的多代理协商模型.     

基于改进蚁群算法的网格组合拍卖资源分配

网格计算资源分配是一类组合优化问题,即如何将网格计算资源有效地分配到用户任务.针对当前网格环境中资源繁多的特点.为了更好地提高网格计算资源的利用率和资源分配的时间效率,提出了一种新的方法,采用一种通过改进转移概率准则和信息素的蚁群算法来解决网格组合拍卖模型中计算资源的优化分配问题.仿真结果表明,该算法能够保证在一个拍卖周期内满足服务的最大用户数和最短的平均等待时间,证明了改进蚁群算法在网格计算资源合理分配上的有效性.     

基于竞争机制的网格资源分配方法

针对在网格环境下对资源进行有效管理和调度的复杂性问题,提出一个基于竞争机制的网格资源分配模型,其中包括用户层、代理层及资源层。在该模型的基础上给出资源分配策略及一种费用优化算法。模拟实验表明,该模型能够较好地适应网格环境的动态变化,调整供给和需求的平衡。     

基于市场竞标机制的网格资源管理模型

网格资源管理是网格计算首要解决的核心问题。现行的网格资源管理模型通常需要在网格系统中建立一个高于其他节点的自身庞大的管理体系,以掌握全网格内资源动态信息,实现全局资源调配,这种模式的主要问题是管理成本高且资源配置效率低。文章基于市场经济中的招投标机理,提出了一种新的网格资源管理模型,本模型的资源分配机制是根据网格内资源供需关系和资源的市场价格通过招投标方式来决定。网格内站点是否参与网格计算交易活动,完全由站点自主地根据自身资源现状和资源的市场价格来确定而不需要一个高于自己的管理机构,本模型是一个完全的市场经济的资源分配模型。     

基于市场经济的多目标网格资源分配方法

目前资源分配已有一些方法,但都是基于某一个目标函数,针对网格计算基于市场经济机制下提出了一种新的资源分配方法,通过组建多目标线性规划模型来解决基于用户多个目标函数的问题,适应网格中多任务多目标的资源分配方式,且该模型不但可以满足用户的要求提高资源分配的成功率,而且可以提高资源的利用率.     

一种基于市场机制的随机服务系统模型

在市场机制的网格环境中对大量的用户进行有效的排队是很有必要的。本文以随机服务系统理论为基础针对网格计算提出了一种基于市场机制的资源分配系统的接受用户服务的模型。该模型可以提高计算网格资源的随机服务系统性能及其运行的优化和缓解网络堵塞和系统忙,可以提高网格资源分配的均衡和网格系统的运行效率。     

基于任务-资源分配图优化选取的网格依赖任务调度

任务调度是网格应用系统获得高性能的关键.网格计算中一个大型的应用程序往往被分解为具有依赖关系的多个任务.在资源个体差异较大、广域互连的网格环境下任务间的依赖关系对传统的调度策略提出了新的挑战.任务调度的主要工作是为任务分配资源以及确定任务的执行次序,将依赖任务的可能的资源分配方案表示为任务-资源分配图（T-RAG）,在该图的基础上提出了基于T-RAG优化选取的依赖任务调度模型,将依赖任务调度问题转化为图的优化选取问题,解析最优任务-资源分配图可以同时确定资源分配方案和任务的执行次序即为最优调度方案.最后,实现了基于该模型的任务调度算法,该算法与ILHA算法的对比分析表明,在资源差异较大及任务间存在大量数据传输的情况下所提出的算法更优.     

基于有机计算的网格资源管理模型的研究

网格的复杂性日益增加,网格资源管理成为一项复杂的任务.有机计算能采取适当的措施使网格环境实现自我管理,隐蔽网格系统的复杂性.文中给出网格资源管理的层次式模型,该模型具有四层:本地资源层、全局资源层、本地服务层和用户层.并将该模型嵌入有机计算体系结构中,灵活使用有机计算中的观测器和控制器对网格中各种资源进行监测和控制.该基于有机计算的网格资源管理模型中的观测器和控制器除了具备原有的功能外,还结合网格资源动态、异构、分布等特点,添加了新的功能模块,以方便对网格资源进行管理.该模型有效地提高了资源分配效率,优化了网格资源管理的性能.     

基于LDAP的FTP网格资源管理系统

介绍网格环境下FTP 网格资源管理系统的设计与模型, 需要在FTP 资源分布且动态变化的元计算环境下实现高性能文件传输及资源管理, 因此对目录文件资源的有效管理成为实现FTP 服务器网格的关键。在LDAP 协议的基础上, 实现了对网格FTP 资源的完备表示并给出了一个FTP 网格管理系统的实现模型。     

基于网格计算市场模型的资源管理和调度的研究

网格计算市场模型是把经济学的概念应用到网格资源管理和调度的模型。基于计算市场模型的网格资源管理系统借鉴人类社会竞争的市场调节机制，根据用户的经济需求进行资源管理与任务调度，不仅使资源所有者和资源消费者都能实现各自的经济目标，而且使资源消费者使用轻负栽和廉价的资源，达到整个网格资源整体的全局最优及合理利用。     

A commodity market algorithm for pricing substitutable Grid resources

A crucial goal for future Grid systems is to strive towards user-centric service provisioning. A way to achieve this is through the use of economics-based resource management. Currently, several models exist from among which auction- and commodity-based models are the most popular. This contribution will focus on the latter, and in particular on commodity markets, where the value of a Grid resource is determined by supply and demand. We propose some refinements to the application of Smale’s method for finding price equilibria in such a Grid market. We also extend the approach to substitutable goods. That is, we introduce ‘slow’ and ‘fast’ CPUs, two categories of the same type of good that are priced separately, but are strongly coupled with potentially strong shifts in demand. We show that Smale’s method can be adapted to handle this type of Grid resources market, and that price stability, allocative efficiency, and fairness are realized.     

Grid commerce, market-driven G-negotiation, and Grid resource management.

Although the management of resources is essential for realizing a computational grid, providing an efficient resource allocation mechanism is a complex undertaking. Since Grid providers and consumers may be independent bodies, negotiation among them is necessary. The contribution of this paper is showing that market-driven agents (MDAs) are appropriate tools for Grid resource negotiation. MDAs are e-negotiation agents designed with the flexibility of: 1) making adjustable amounts of concession taking into account market rivalry, outside options, and time preferences and 2) relaxing bargaining terms in the face of intense pressure. A heterogeneous testbed consisting of several types of e-negotiation agents to simulate a Grid computing environment was developed. It compares the performance of MDAs against other e-negotiation agents (e.g., Kasbah) in a Grid-commerce environment. Empirical results show that MDAs generally achieve: 1) higher budget efficiencies in many market situations than other e-negotiation agents in the testbed and 2) higher success rates in acquiring Grid resources under high Grid loadings.     

The DataGrid Workload Management System: Challenges and Results

The workload management task of the DataGrid project was mandated to define and implement a suitable architecture for distributed scheduling and resource management in a Grid environment. The result was the design and implementation of a Grid Workload Management System, a super-scheduler with the distinguishing property of being able to take data access requirements into account when scheduling jobs to the available Grid resources. Many novel issues in various fields were faced such as resource management, resource reservation and co-allocation, Grid accounting. In this paper, the architecture and the functionality provided by the DataGrid Workload Management System are presented.     

Modeling and analysis of the effects of QoS and reliability on pricing, profitability, and risk management in multiperiod grid-computing networks

In this paper we develop a network equilibrium model for optimal pricing and resource allocation in Computational Grid Network. We consider a general network economy model with Grid Resource Providers, Grid Resource Brokers and Grid Users. The proposed framework allows for the modeling and theoretical analysis of Computational Grid Markets that considers a non-cooperative behavior of decision-makers in the same tier of the grid computing network (such as, for example, Grid Resource Providers) as well as cooperative behavior between tiers (between Resource Providers and Grid Brokers). We introduce risk management into the decision making process by analyzing the decision-marker's reliability and quality of service (QoS) requirement. We analyze resource allocation patterns as well as equilibrium price based on demand, supply, and cost structure of the grid computing market network. We specifically answer the following questions with several numerical examples: How do system reliability levels affect the QoS levels of the service providers and brokers under competition? How do system reliability levels affect the profits of resource providers and brokers in a competitive market? How do system reliability levels influence the pricing of the services in a competitive environment? How do users' service request types, QoS requirements, and timing concerns affect users' behaviors, costs and risks in equilibrium? How does the market mechanism allocate resources to satisfy the demands of users? We find that for users who request same services certain timing flexibility can not only reduce the costs but also lower the risks. The results indicated that the value of QoS can be efficiently priced based on the heterogeneous service demands.     

Static strategy and dynamic adjustment: An effective method for Grid task scheduling

Task scheduling is the key technology in Grid computing. Hierarchical organization is suitable for the computational Grid because of the dynamic, heterogeneous and autonomous nature of the Grid. Although a number of Grid systems adopt this organization, few of them has dealt with task scheduling for the hierarchical architecture. In this paper, we present an effective method, fully taking into account both historical Grid trade data and dynamic variation of the Grid market to improve the task scheduling for a hierarchical Grid market. The main idea of the proposed method is a combination of an off-line static strategy using time series prediction and an on-line dynamic adjustment using reinforcement learning. The superiority of this new scheduling algorithm, in improving the inquiry efficiency for resource consumers, getting better load balancing of the whole hierarchical Grid market, and achieving higher success rate of the Grid service request, is demonstrated by simulation experiments.     

基于网格计算市场模型的资源与作业描述语言的研究

网格计算市场模型是把经济学的概念应用到网格的资源管理和作业调度中的模型。本文分析了网格计算市场模型中资源和作业描述语言的需求,简要介绍了资源和作业描述语言Classified Advertisements(Classad),指出它在网格计算市场模型中描述资源和作业的不足之处,对它做了相应的改进和扩充．以实现在经济模型下对资源和作业更加灵活、细枉度的描述。     

计算网格的资源分发和发现机制

1 引言计算网格的资源管理系统是为实现计算网格系统资源共享所应提供的最主要的服务之一。计算网格资源管理系统的基本功能是接受来自计算网格范围内的机器的资源请求,并且把特定的资源分配给资源请求者,并且合理地调度相应的资源,使请求资源的作业得以运行。资源分发、资源发现和资源的调度构成了计算网格资源管理系统的最主要的内容。资源分发和资源发现提供方法,通过该方法,在计算网格内部的机器能够形成一个可用的资源和其状态的一个视图。资源     

Modeling and Supporting Grid Scheduling

Grid resource management systems and schedulers are important components for building Grids. They are responsible for the selection and allocation of Grid resources to current and future applications. Thus, they are important building blocks for making Grids available to user communities. In this paper we briefly analyze the requirements of Grid resource management and provide a classification of schedulers. Then, we define an extensible formal model for Grid scheduling activities, and characterize the general Grid scheduling problem. Finally, we provide a reference architecture for the support of our model and discuss different aspects of architectural implementations.