Grid resource management policies for load-balancing and energy-saving by vacation queuing theory

The resource management is the central component of grid system. The analysis of the workload log file of LCG including the job arrival and the resource utilization daily cycle shows that the idle sites in the Grid are the source of load imbalance and energy waste. Here we focus on these two issues: balancing the workload by transferring jobs to idle sites at prime time to minimize the response time and maximize the resource utilization; power management by switch the idle sites to sleeping mode at non-prime time to minimize the energy consume. We form the M/G/1 queue model with server vacations, startup and closedown to analysis the performance metrics to instruct the design of load-balancing and energy-saving policies. We provide our Adaptive Receiver Initiated (ARI) load-balancing strategy and power-management policy for energy-saving. The simulation experiments prove the accuracy of our analysis and the comparisons results indicate our policies are largely suitable for large-scale heterogeneous grid environment.     

A routing-table-based adaptive and minimal routing scheme on network-on-chip architectures

In this paper, we present a routing algorithm that combines the shortest path routing and adaptive routing schemes for NoCs. In specific, routing follows the shortest path to ensure low latency and low energy consumption. This routing scheme requires routing information be stored in a series of routing tables created at the routers along the routing path from the source to the destination. To reduce the exploration space and timing cost for selecting the routing path, a routing list and routing table for each node are created off-line. Routing table is updated on-line to reflect the dynamic change of the network status to avoid network congestion. To alleviate the high hardware implementation cost associated with the routing tables, a method to help reduce the size of the routing tables is also introduced. Compared to the existing routing algorithms, the experimental results have confirmed that the proposed algorithm has better performance in terms of routing latency and power consumption.     

Design and implementation of an agent-based collaborative product design system

The evolution of computer science and technology has brought new opportunities for multidisciplinary designers and engineers to collaborate with each other in a concurrent and coordinated manner. The development of computational agents with unified data structures and software protocols contributes to the establishment of a new way of working in collaborative design, which is increasingly becoming an international practice. In this paper, based on the analysis of the dynamic nature of collaborative design process, a new framework for collaborative design is described. This framework adopts an agent-based approach and relocates designers, managers, systems, and the supporting agents in a unified knowledge representation scheme for product design. In order to model the constantly evolving design process and the rationales resulted from design collaboration, a Collaborative Product Data Model (CPDM) and a constraint-based Collaborative Design Process Model (CDPM) are proposed to facilitate the management and coordination of the collaborative design process as well as design knowledge management. A prototype system of the proposed framework is implemented and its feasibility is evaluated using a real design scenario whose objective is designing a set of dining table and chairs.     

Complete discriminant evaluation and feature extraction in kernel space for face recognition

This work proposes a method to decompose the kernel within-class eigenspace into two subspaces: a reliable subspace spanned mainly by the facial variation and an unreliable subspace due to limited number of training samples. A weighting function is proposed to circumvent undue scaling of eigenvectors corresponding to the unreliable small and zero eigenvalues. Eigenfeatures are then extracted by the discriminant evaluation in the whole kernel space. These efforts facilitate a discriminative and stable low-dimensional feature representation of the face image. Experimental results on FERET, ORL and GT databases show that our approach consistently outperforms other kernel based face recognition methods.

Towards capacity and profit optimization of video-on-demand services in a peer-assisted IPTV platform

This paper studies the conditions under which peer-to-peer (P2P) technology may be beneficial in providing IPTV services over typical network architectures. It has three major contributions. First, we contrast two network models used to study the performance of such a system: a commonly used logical “Internet as a cloud” model and a “physical” model that reflects the characteristics of the underlying network. Specifically, we show that the cloud model overlooks important architectural aspects of the network and may drastically overstate the benefits of P2P technology. Second, we propose an algorithm called Zebra that pre-stripes content across multiple peers during idle hours to speed up P2P content delivery in an IPTV environment with limited upload bandwidth. We also perform simulations to measure Zebra’s effectiveness at reducing load on the content server during peak hours. Third, we provide a cost-benefit analysis of P2P video content delivery, focusing on the profit trade-offs for different pricing/incentive models rather than purely on capacity maximization. In particular, we find that under high volume of video demand, a P2P built-in incentive model performs better than any other model, while the conventional no-P2P model generates more profits when the request rate is low. The flat-reward model generally falls in between the usage-based model and the built-in model in terms of profitability except for low request rates. We also find that built-in and flat-reward models are more profitable than the usage-based model for a wide range of subscriber community sizes. Funding for J. Rahe’s research has been provided by AT&T Labs, the State of California under the MICR Oprogram, and by the Toshiba Corporation. Zhen Xiao is partially supported by China MOST project (2006BAH02A10).     

Structure identification of Bayesian classifiers based on GMDH

This paper introduces group method of data handing (GMDH) theory to Bayesian classification, and proposes GMBC algorithm for structure identification of Bayesian classifiers. The algorithm combines two structure identification ideas of search & scoring and dependence analysis, and is able to accomplish the process of adaptive structure identification. We experimentally test two versions of Bayesian classifiers (GMBC-BDe and GMBC-BIC) over 25 data sets. The results show that, the structure identification of the two Bayesian classifiers especially GMBC-BDe is very effective. And when the data sets contain lots of noise, the superiority of Bayesian classifiers learned by GMBC is more obvious. Finally, giving a classification domain without any prior information about the noise, we recommend adopting GMBC-BDe rather than GMBC-BIC.     

Recognizing control chart patterns with neural network and numerical fitting

Control chart has been widely used to determine whether the state of machining process is stable or not, and pattern recognition technology is often used to automatically judge the changing modes of control chart. It is because that the abnormal patterns of a control chart can reveal the potential problem of machining quality. In order to improve the recognition rate and efficiency of control chart patterns, a neural network-numerical fitting (NN-NF) model is proposed to recognize different control chart patterns. A back propagation (BP) network is first used to recognize control chart patterns preliminarily. And then, numerical fitting method is adopted to estimate the parameters and specific types of the patterns, which is different from the traditional neural network-based control chart pattern recognition methods. Based on this, Monte Carlo simulation is used to generate training and testing data samples. The results of simulated experiment show that training time of this NN-NF model can be reduced. At the same time, the recognition rate can also be improved. At last, a real example is also provided to illustrate the NN-NF model.     

电磁流量计示值误差校准不确定度评定

针对目前电磁流量计在出厂时只标注有允许误差或准确度等级,其不确定度未予表述这一现状,依据<电磁流量计检定规程>JJG 1033-2007,进行水流量标准装置实流校验试验.分别介绍了评定的测量依据、环境条件、测量标准、被测对象、测量过程以及评定结果的使用.示值误差校准不确定度分析评定表明,该标定装置的不确定度对于电磁流量计的测量非常重要.     

基于MSP430的无功补偿系统设计与实现

针对电网中无功补偿问题,介绍了一种基于MSP430F449的无功补偿系统,简要地论述了系统的硬件和软件设计.系统能够通过430F449内部自带的A/DC12模块实现电流、电压的采集,同时利用定时器的捕获功能来计算信号相位差,求得输出控制量,控制自动投切并联补偿电容器组,实现系统的无功补偿.     

无线传感器网络TBCCA树形分簇算法

针对当前无线传感器网络分簇和拓扑控制算法中存在的问题,例如能耗过大、负载不均、计算复杂性高和存在额外开销等,提出了一种新型的TBCCA(tree-based clustering construction algorithm)分簇算法.该算法基于正三角形簇树结构,并利用RSSI(received signal strength indicator)值控制簇半径,从而产生3类集合--Near集、Common集和Medium集,及其相应的选择策略.其后,根据树的度数和结构,设计了簇树的建立算法.性能分析和实验仿真表明,相对于现有的几种算法,例如TopDisc和DLMST等,TBCCA算法具有较低的计算复杂性;与Leach协议和HEED协议相比,该算法能在保证较高连通性与覆盖率的同时,有效节约能量,均衡负载,延长网络的生命周期.