Current research in Internet computing does not address the problem of specifying and realizing QoS parameters described in a trusted capability. In a Web environment, an Internet server can receive several requests w...
详细信息
ISBN:
(纸本)088986392X
Current research in Internet computing does not address the problem of specifying and realizing QoS parameters described in a trusted capability. In a Web environment, an Internet server can receive several requests with varying QoS requirements. The server's admission control should either deny or allow the request without degrading the system performance in accordance with service guarantees and other security attributes specified in a digitally signed XML structure called a trusted QoS capability. The problem becomes challenging when requests are accompanied by delegated credentials. The goal is to provide sustenance of Quality of Service while continuing to maintain stability and determinism on servers. This paper develops a mathematical model for QoS based delegation, and describes the process of using such capabilities.
This paper presents a parallel genetic algorithm to the Steiner Problem in Networks. Several previous papers have proposed the adoption of GAs and others metaheuristics to solve the SPN demonstrating the validity of t...
详细信息
ISBN:
(纸本)088986392X
This paper presents a parallel genetic algorithm to the Steiner Problem in Networks. Several previous papers have proposed the adoption of GAs and others metaheuristics to solve the SPN demonstrating the validity of their approaches. This work differs from them for two main reasons: the dimension and the characteristics of the networks adopted in the experiments and the aim from which it has been originated. The reason that aimed this work was namely to build a comparison term for validating deterministic and computationally inexpensive algorithms which can be used in practical engineering applications, such as the multicast transmission in the Internet. On the other hand, the large dimensions of our sample networks require the adoption of a parallel implementation of the Steiner GA, which is able to deal with such large problem instances.
In this paper, we apply divisible load theory to model the Grid scheduling problem involving multiple sources to multiple sinks, and present an optimized scheduling technique for this scenario. This scheduling techniq...
详细信息
ISBN:
(纸本)088986392X
In this paper, we apply divisible load theory to model the Grid scheduling problem involving multiple sources to multiple sinks, and present an optimized scheduling technique for this scenario. This scheduling technique can be easily extended to schedule resources with buffer space constraints. We provide a step-wise scheduling algorithm for these constraints. Two example calculations will show the practical utility and efficiency of DLT.
A novel combination of emergent algorithmic methods, powerful computational platforms and supporting infrastructure is described. These complementary tools and technologies are used to launch systematic attacks on com...
详细信息
ISBN:
(纸本)088986392X
A novel combination of emergent algorithmic methods, powerful computational platforms and supporting infrastructure is described. These complementary tools and technologies are used to launch systematic attacks on combinatorial problems of significance. As a case study, optimal solutions to very large instances of the NP-hard vertex cover problem are computed. To accomplish this, an efficient sequential algorithm and two forms of parallel algorithms are devised and implemented. The importance of maintaining a balanced decomposition of the search space is shown to be critical to achieving scalability. With the synergistic combination of techniques detailed here, it is now possible to solve problem instances that before were widely viewed as hopelessly out of reach. Target problems need only be amenable to reduction and decomposition. Applications are also discussed.
This paper presents a new method for a request-based self-stabilizing token passing. A self-stabilizing dynamic BFS tree rooted at each request source process is combined with token passing. That is, a token knows the...
详细信息
ISBN:
(纸本)088986392X
This paper presents a new method for a request-based self-stabilizing token passing. A self-stabilizing dynamic BFS tree rooted at each request source process is combined with token passing. That is, a token knows the request occurrence by touching the tree edge, and is passed toward the root. Even if more than two tokens stay at distinct roots, it can be shown that they will be merged into a unique token. Another feature is to attach power to each tree and it is periodically raised until the request is serviced. As a result, such a tree with a request which has long been neglected grows larger and larger. Since a large tree easily reaches a token, our method is lockout-free. Finally, some properties of our method, stabilization time, space complexity, and the efficiency of servicing k requests, called k-covering time, are shown.
In this paper we describe the main architectural and implementation aspects of a system, the Netlab Java Integration System (N-JIS), which makes it possible to developers of RMI distributed applications to access RFC ...
详细信息
ISBN:
(纸本)088986392X
In this paper we describe the main architectural and implementation aspects of a system, the Netlab Java Integration System (N-JIS), which makes it possible to developers of RMI distributed applications to access RFC based Web Services in the same way they access RMI Objects. Moreover N-JIS allows to register multiple components, either RMI Objects or Web Services, providing the same functionalities and is able to perform a run time selection of the best component according to a programmer specified evaluation criterion.
In this paper, we present an efficient and portable parallel algorithm for multichannel inverse filter design in sound reproduction systems. The actual matrix used to specify the electroacoustic transmission paths is ...
详细信息
ISBN:
(纸本)088986392X
In this paper, we present an efficient and portable parallel algorithm for multichannel inverse filter design in sound reproduction systems. The actual matrix used to specify the electroacoustic transmission paths is the matrix of causal finite impulse response filters. An array of finite impulse response filters is designed in a way that best approximates a given time domain response in the least squares sense. We exploit the non-symmetric block-Toeplitz structure of the multichannel system matrix in order to develop a fast parallel algorithm to solve the arising least squares problem. Experimental results, obtained on a cluster of personal computers and on a bi-processor board, show the performance of our approach to the inverse filtering problem.
Traditionally, a cluster is defined as a collection of homogeneous nodes interconnected by a single high performance communication technology. However, in some cases, cluster nodes may be organized into several partit...
详细信息
ISBN:
(纸本)088986392X
Traditionally, a cluster is defined as a collection of homogeneous nodes interconnected by a single high performance communication technology. However, in some cases, cluster nodes may be organized into several partitions - sub-clusters - internally interconnected by one or more selected SAN technologies. In order to constitute a multi-networked cluster, sub-clusters must share a common SAN technology or a bridge facility must be used. In this paper we show how RoCL - a lightweight user-level communication library designed to support multi-threading in a multi-networked environment - manages to exploit such cluster organization. Performance evaluation results obtained by using two partitions of Myrinet and Gigabit SMP nodes demonstrate the usefulness of our approach both for low-level and high-level operation.
In the existing Fault-Tolerant Software distributed Shared Memory (FT-SDSM) with the message logging, the logs are used only to recover the failed nodes. In our previous work, we have implemented a lightweight logging...
详细信息
ISBN:
(纸本)088986392X
In the existing Fault-Tolerant Software distributed Shared Memory (FT-SDSM) with the message logging, the logs are used only to recover the failed nodes. In our previous work, we have implemented a lightweight logging protocol, called remote logging, on the SDSM for fault tolerance, which incurs low logging overhead with a fast network and a remote memory for back-up data. In this paper, we propose two practical schemes for the logs, which enhance our based remote logging protocol. In these proposed schemes, the logs are applicable to reduce the stalled times for updating the invalid pages, minimizing the failure-free execution time.
We propose a novel load balancing algorithm for a static load balancing problem that considers processing multiclass jobs in distributed networks. Our objective is to minimize the mean response time of the jobs that a...
详细信息
ISBN:
(纸本)088986392X
We propose a novel load balancing algorithm for a static load balancing problem that considers processing multiclass jobs in distributed networks. Our objective is to minimize the mean response time of the jobs that arrive at the system. We formulate the problem as a constrained nonlinear minimization problem with job-flow rate, communication delays, and processing delays, as constraints. Using a systematic methodology, we transform the formulated problem into an equivalent virtual routing problem and propose an algorithm, referred to as Load Balancing via Virtual Routing (LBVR). Thus, we establish a correspondence between the load balancing problem and the routing problem. We show that the proposed algorithm has several interesting properties and guarantees to deliver a super-linear rate of convergence in obtaining an optimal solution, whenever it exists. With rigorous experiments we test the performance of our algorithm in terms of its rate of convergence and quality of solution.
暂无评论