P2P application is one of the most popular applications in the Internet, but its performance is badly influenced by the churn character-the nodes continuous arrival and departure. On the basis of introducing the origi...
详细信息
P2P application is one of the most popular applications in the Internet, but its performance is badly influenced by the churn character-the nodes continuous arrival and departure. On the basis of introducing the origin of the churn, the definition of it and its influences to the P2P system performance, we minutely describe the research on the statistical properties, and discover some dynamic law including nodes' session time generally obey the heavy-tailed distribution. Then we detail the measurement methods. For passive monitoring, active monitoring, sample and so on, we present the advantages and disadvantages of each method, and explain the corresponding improving method to enhance the accuracy of the measurement. After that we elaborate the resilience strategies to the churn. Towards the neighbor selection, failure recovery, replica maintenance, link lifetime maintenance and so on, we present also the advantage and disadvantage of each strategy, and present our view to each of aspects. Finally, the summary and prospect of the future research are given.
Lots of toolboxes of accelerating MatLab using GPU are available now[1], but, users are confused by which toolbox is best suitable for a particular task. Three toolboxes-Jacket, GPUmat, and parallel Computing Toolbox ...
详细信息
Lots of toolboxes of accelerating MatLab using GPU are available now[1], but, users are confused by which toolbox is best suitable for a particular task. Three toolboxes-Jacket, GPUmat, and parallel Computing Toolbox of MatLab are selected. For each toolbox, its advantages and pitfalls are reviewed, with an aim to allow the reader to identify which toolbox is appropriate for a given task. Strategies of whether a function should execute on GPU are given after a formula analysis. The analysis is also a framework for program automatically decides which function is cost-efficient to execute on GPU. A series of benchmark of different types of computing, including data transfer between GPU and CPU, data matrix Generation, matrix operation and GPU functions were tested in all three toolboxes. And the results show that Jacket is the best one. Some advices to improve the performance of toolboxes are given in the end.
Many applications demand distributing data with different contents efficiently in the network environment with unreliable links and a high node churn. Existing approaches mostly focus on optimizing either efficiency o...
详细信息
Network size is one of the fundamental information of distributed applications. The approach to estimate network size must feature both high accuracy and robustness in order to adapt to the dynamic environment in diff...
详细信息
Nested Circular Directional MAC, a modified medium access control protocol of DMAC protocol, is proposed in this paper to support both directional antennas and omni-directional antennas simultaneously in one Ad Hoc ne...
详细信息
We introduce a novel method for the consolidation of unorganized point clouds with noise, outliers, non-uniformities as well as sharp features. This method is feature preserving, in the sense that given an initial est...
详细信息
In this paper, we explore a parallel block multigrid preconditioner based on factorization of the coefficient matrix generated in three-dimensional unstructured grids system. This preconditioner is robust with respect...
详细信息
As the system scales up continuously, the problem of power consumption for high performance computing (HPC) system becomes more severe. Heterogeneous system integrating two or more kinds of processors, could be better...
详细信息
Insects build architecturally complex nests and search for remote food by collaboration work despite their limited sensors, minimal individual intelligence and the lack of a central control system. Insets' collabo...
详细信息
Existing routing protocols for Wireless Mesh Networks (WMNs) are generally optimized with statistical link measures, while not addressing on the intrinsic uncertainty of wireless links. We show evidence that, with the...
详细信息
ISBN:
(纸本)9781424459889
Existing routing protocols for Wireless Mesh Networks (WMNs) are generally optimized with statistical link measures, while not addressing on the intrinsic uncertainty of wireless links. We show evidence that, with the transient link uncertainties at PHY and MAC layers, a pseudo-deterministic routing protocol that relies on average or historic statistics can hardly explore the full potentials of a multi-hop wireless mesh. We study optimal WMN routing using probing-based online anypath forwarding, with explicit consideration of transient link uncertainties. We show the underlying connection between WMN routing and the classic Canadian Traveller Problem (CTP) [1]. Inspired by a stochastic recoverable version of CTP (SRCTP), we develop a practical SRCTP-based online routing algorithm under link uncertainties. We study how dynamic next hop selection can be done with low cost, and derive a systematic selection order for minimizing transmission delay. We conduct simulation studies to verify the effectiveness of the SRCTP algorithms under diverse network configurations. In particular, compared to deterministic routing, reduction of end-to-end delay (51:15∼73:02%) and improvement on packet delivery ratio (99:76%) are observed.
暂无评论