In this paper, we propose Rainbow, a mesh based locality-aware P2P overlay multicast system. Nodes first self-organize into a two-layer overlay. A simple and accurate network coordinate system is used for more reliabl...
详细信息
ISBN:
(纸本)0769526950
In this paper, we propose Rainbow, a mesh based locality-aware P2P overlay multicast system. Nodes first self-organize into a two-layer overlay. A simple and accurate network coordinate system is used for more reliable node clustering. Pull-based method is used in data packet delivery. According to our simulation, the ARDP of Rainbow ranges from 63% to 76% of that in Binning overlay. Our real-world experiment on PlanetLab shows that the average packet loss rate of Rainbow is about 50% of that in ChainSaw.
Withthe increase in size, complexity, and heterogeneity of grid computing environments, we argue that, in addition to performance metrics, the resource allocation algorithms should be designed for robustness. that is...
详细信息
ISBN:
(纸本)9780769526942
Withthe increase in size, complexity, and heterogeneity of grid computing environments, we argue that, in addition to performance metrics, the resource allocation algorithms should be designed for robustness. that is, they should have the ability to maintain performance under a wide variety of operating conditions. Although robustness is easy to define, there are no widely used metrics for this property. We introduce the concept of robustness and present an analysis technique to determine the robustness of a resource allocation. As the main contributions of the paper, we present a mathematical description of a metric for the robustness of a resource allocation with respect to a specific disturbance. Simulation results prove the efficiency and applicability of our algorithms.
A fundamental concern in building a secure grid computing environment is authentication of local and remote entities in the environment. the existed authentication technologies in the grid computing environments can e...
详细信息
ISBN:
(纸本)9780769526942
A fundamental concern in building a secure grid computing environment is authentication of local and remote entities in the environment. the existed authentication technologies in the grid computing environments can effectively guarantee the valid authentication, but they cannot meet the demands of new security challenges in dynamic grid environment, such as flexibility, lightweight, and extensibility. In order to satisfy the security needs of the computational grid, we propose a reflective authentication framework which aims to improve the customizing ability of platform and adaptive ability in the open and dynamic grid environment.
In multi-objective context the evolutionary approach offers specific mechanisms such as Pareto selection, elitism and diversification. these techniques are proved to be efficient to characterize the Pareto Front. Howe...
详细信息
ISBN:
(纸本)9780769526942
In multi-objective context the evolutionary approach offers specific mechanisms such as Pareto selection, elitism and diversification. these techniques are proved to be efficient to characterize the Pareto Front. However, their high computing time constitutes a major handicap for their expansion. the parallelization of Multi-Objective Evolutionary Algorithms (MOEAs) may be an efficient way to overcome this problem. this parallelization aims not only to achieve time saving by distributing the computational effort but also to get benefit from the algorithmic aspect by the cooperation between different populations and evolutionary schemes. In this paper we propose a new parallel multi-objective evolutionary algorithm with multi front equitable distribution which is based on an elitist technique. Every population evolves differently on a processor and cooperates withthe others to preserve genetic diversity and to obtain a set of diversified non dominated solutions.
In this paper, we introduce a Linda [3] like peer-to-peer tuple space middleware build on top of distributed hash table - DTuples. Withthe help of DTuples, the development of the distributed cooperation and coordinat...
详细信息
ISBN:
(纸本)9780769526942
In this paper, we introduce a Linda [3] like peer-to-peer tuple space middleware build on top of distributed hash table - DTuples. Withthe help of DTuples, the development of the distributed cooperation and coordination task would be simplified. the decoupled style of tuple space [2] model is useful in peer-to-peer environment. In the application level, the Maples was used instead of the publish/subscribe model and message-passing model. In low level, the Maples service can be used as cooperation middleware and context-aware middleware. the tuples in the Maples are stored in distributed hash table based peer-to-peer tuple storage. In our current work, the in(), rd(), out() and copy-collect() primitives are supported. the eval() primitive will be added to D-Tuples in the future. In this paper, we present the key design concepts of DTuples.
Meteorology Grid computing aims to provide scientist with seamless, reliable, secure and inexpensive access to meteorological resources. However, the vision of achieving these goals has been encountered with many chal...
详细信息
ISBN:
(纸本)0769526950
Meteorology Grid computing aims to provide scientist with seamless, reliable, secure and inexpensive access to meteorological resources. However, the vision of achieving these goals has been encountered with many challenges such as the degree of easy-to-use and the capability of seamless automation. Fortunately, the emerging semantic web service and semantic grid technologies will bring some significant solutions for the above challenges. Currently, Semantic Meteorology Grid Architecture (SMGA) is being developed by us to support automated meteorology grid service discovery, selection, and composition. In this paper, we present a model for semantic annotation and publication of meteorology grid services by combining the expressive power of the present ontology language and the advantages of semantic web techniques. the presented model is an initial work to support automating the discovery, selection, and workflow composition of semantically described heterogeneous meteorological services, which offers the possibility of facilitating geographically distributed meteorological scientists to resolve complex scientific problems cooperately.
Service Level Agreements (SLAB) are currently one of the major research topics in Grid computing. Among many system components for supporting of SLA-aware Grid jobs, the SLA mapping mechanism receives important positi...
详细信息
ISBN:
(纸本)9780769526942
Service Level Agreements (SLAB) are currently one of the major research topics in Grid computing. Among many system components for supporting of SLA-aware Grid jobs, the SLA mapping mechanism receives important positions. It is responsible for assigning sub jobs of the workflow to Grid resource in a way that meet the user's deadline and as cheap as possible. Withthe distinguished workload and resource characteristics, mapping a heavy communication workflow within SLA context defines an unfamiliar problem and need a specific method to be solved. this paper presents the mapping algorithm, which can cope withthe problem. Performance measurements deliver evaluation results on the quality and efficiency of the method.
Researchers have proved that the general computing capability of the mainstream programmable GPU (Graph Processing Unit, the core of graphic card) is more powerful than that of the popular CPU (Central Processing Unit...
详细信息
ISBN:
(纸本)9780769526942
Researchers have proved that the general computing capability of the mainstream programmable GPU (Graph Processing Unit, the core of graphic card) is more powerful than that of the popular CPU (Central Processing Unit) recently [1]. In this paper, we attempt to develop such a desktop grid, in which the programmable GPUs' powerful general computing ability could be linked in. the hierarchical topology and benchmarks based scheduling algorithm are adopted in the grid to improve the efficiency of the desktop grid. We contrast the performances of GPUs general computing enabled and non-enabled desktop grid to prove the superiority of GPUs' linking supported by some simulation experiments.
Much recent work has focused on improving A QM performance through expediting response time. In this paper we explore the impact of propagation delay and topology on AQM discuss the question "faster the A QM cont...
详细信息
ISBN:
(纸本)9780769526942
Much recent work has focused on improving A QM performance through expediting response time. In this paper we explore the impact of propagation delay and topology on AQM discuss the question "faster the A QM controller responds, better it is?" We show that sometimes the fast responsive AQM controller leads to reduced link utilization and higher queue oscillations. Using simulations, we conclude that the performance of AQM is related to the network topology, propagation delay and the A QM schemes adopted by contemporaneous routers. Conservative scheme, such as PI, will be reassuring in uncertain network environment.
We propose a new proof technique which can be used to analyze many parallel load balancing algorithms. the technique is designed to handle concurrent load balancing actions, which are often the main obstacle in the an...
详细信息
暂无评论