Grid computing needs some application scenarios proved by operative implementations that should lead towards profitable real business applications. NeuroGrid represents the first step of a long way to connect the imme...
详细信息
ISBN:
(纸本)088986568X
Grid computing needs some application scenarios proved by operative implementations that should lead towards profitable real business applications. NeuroGrid represents the first step of a long way to connect the immense area of neural networks and its high potential applications to the fast emerging infrastructure possibilities of Grid computing. Based on the de-facto standard Grid middleware "Globus Toolkit" and the platform independent Java technology NeuroGrid demonstrates a proof-of-concept implementation for training and evaluating neural networks within a Grid environment.
In ad hoc networks, broadcasting is a primitive operation to support many applications and it is also an expensive process in terms of power consumed. Preserving energy and ensuring a high delivery ratio of broadcast ...
详细信息
ISBN:
(纸本)9780889866379
In ad hoc networks, broadcasting is a primitive operation to support many applications and it is also an expensive process in terms of power consumed. Preserving energy and ensuring a high delivery ratio of broadcast packets are crucial tasks for broadcasting in ad hoc networks. This paper proposes a localized broadcast scheme for use in ad hoc networks using variable-range transmission power. Varying transmission range dynamically by individual broadcast relaying node contributes to the overall power savings and interference alleviation during communication. We analyzed the performance of the proposed scheme and compared it to one of the existing schemes that employ variable transmission power and other prevalent broadcast schemes based on common-range transmission power.
A large number of tasks in distributed systems are based on the fundamental problem of tracing the causal dependencies among the events that characterize a run of the computation. This problem is commonly solved by ap...
详细信息
ISBN:
(纸本)9780889866379
A large number of tasks in distributed systems are based on the fundamental problem of tracing the causal dependencies among the events that characterize a run of the computation. This problem is commonly solved by appliance of vector clocks as a means of capturing the flow of information within and among distributed processes. In the paper at hand a new kind of logical clock concept is presented and examined that is meant to overcome the vector clocks' great drawback: that the number of processes in the distributed system has to be constant and known in advance. Tree clocks are designed to naturally and efficiently scale with the dynamic creation and termination of processes without losing their primary functionality, such as causality tracing, event ordering, and gap detection. In most aspects, they even are more efficient than vector clocks.
In this paper, we present an integrated scheduling algorithm for sensing time and power management problem of an intelligent mobile sensor network based on divisible load scheduling model. It integrates four character...
详细信息
ISBN:
(纸本)9780889866386
In this paper, we present an integrated scheduling algorithm for sensing time and power management problem of an intelligent mobile sensor network based on divisible load scheduling model. It integrates four characteristics of mobile sensor nodes: sensing, mobility, communication, and computation. The problem is to minimize the total response time and global power consumption of the network with respect to the total number of sensors in the network. Simulation results for linearly chained wireless sensor networks are presented.
This paper deals with a novel communication timing control for wireless networks and radio interference problem. Communication timing control is based on the mutual synchronization of coupled phase oscillatory dynamic...
详细信息
ISBN:
(纸本)9780889866386
This paper deals with a novel communication timing control for wireless networks and radio interference problem. Communication timing control is based on the mutual synchronization of coupled phase oscillatory dynamics with a stochastic adaptation. Through local and fully distributed interactions, the coupled phase dynamics self-organizes collision free communication timing. In a wireless communication, the influence of the interference wave causes unexpected collision. Therefore, we propose a more effective timing control by selecting the interaction nodes according to received signal strength.
For wireless multi-hop message transmission in ad-hoc networks, sensor networks and mesh networks, on-demand route detection is important due to limited battery capacity and mobility. For route detection, it is desira...
详细信息
ISBN:
(纸本)9780889866379
For wireless multi-hop message transmission in ad-hoc networks, sensor networks and mesh networks, on-demand route detection is important due to limited battery capacity and mobility. For route detection, it is desirable for mobile computers to transmit less control messages;however, flooding of a route request message in DSR and AODV or repeated location information advertisement in GEDIR, FACE and GPSR is required. This paper proposes no-beacon extensions of GEDIR ad-hoc routing protocol applying on-demand exchange of location information in NB-GEDIR and timer setting based on distance in CNB-GEDIR. Since both protocols do not require repeatedly broadcasted beacon messages, no communication overhead is required in case that there is no route detection request. In simulation, CNB-GEDIR requires 85.1% less control messages than NB-GEDIR.
Passive testing is a technique suitable for continuous, non-intrusive, autonomous testing of qualitative behavioural properties (correctness) of a deployed distributed system. A real passive tester has to face observa...
详细信息
ISBN:
(纸本)9780889866379
Passive testing is a technique suitable for continuous, non-intrusive, autonomous testing of qualitative behavioural properties (correctness) of a deployed distributed system. A real passive tester has to face observational uncertainty, which may lead to false verdicts. We submit the novel idea of a self-tuned passive tester, which is able to adapt to a priori unknown, and possibly changing delays in communication channels. We propose the structure and algorithms of a passive tester that "tunes itself" basing solely on its own, locally issued verdicts. This seemingly counter-intuitive principle is shown by simulation to be viable and effective.
The major challenges in designing optical switched interconnection networks include the lack of optical buffering and the crosstalk originated from the optical switching elements. Vertical Stacking Banyan networks and...
详细信息
ISBN:
(纸本)088986568X
The major challenges in designing optical switched interconnection networks include the lack of optical buffering and the crosstalk originated from the optical switching elements. Vertical Stacking Banyan networks and Data Vortex networks provide two different approaches to solve the problem. Both networks utilize several parallel planes in conjunction with traffic scheduling to eliminate the contention and the crosstalk within the routing nodes. While the two share similar compromise between system cost and switch performance, their traffic control mechanism has fundamental difference due to specific configurations of the parallel routing planes. This paper provides a comparison study of two network approaches, focusing on the overall system complexity and the resulting switch performance in throughput and latency.
This paper research on how to select a subtree with exactly k leaves and a diameter of at most 1, which minimizes the distance from the farthest vertex to the subtree. We call such a subtree (k, l)-center of a tree ne...
详细信息
ISBN:
(纸本)9780889866386
This paper research on how to select a subtree with exactly k leaves and a diameter of at most 1, which minimizes the distance from the farthest vertex to the subtree. We call such a subtree (k, l)-center of a tree network. In this paper, an efficient parallel algorithm is proposed for finding a (k, l)-center of a tree network. This algorithm performs on the EREW PRAM in O(log n) time using O(n) work.
In wireless mesh networks (WMN), each node operates not only as an access point but also as a router that forwards user frames to and from a gateway which is connected to the Internet. It has been shown that there is ...
详细信息
ISBN:
(纸本)9780889866386
In wireless mesh networks (WMN), each node operates not only as an access point but also as a router that forwards user frames to and from a gateway which is connected to the Internet. It has been shown that there is a fairness problem in such wireless mesh networks in that nodes farther away from the gateway may be starved by nodes closer to the gateway. In this paper, the end-to-end fairness problem in a chain topology is first analyzed. A solution consisting of Token-based distributed Scheduling (TDS) and per-flow queuing is then proposed to avoid nodes being starved and to improve the total flow throughput.
暂无评论