Characterizing and optimizing TPC-C workloads on large-scale systems using SSD arrays在大规模系统上优化 TPC-C 评测程序

Transaction processing performance council benchmark C (TPC-C) is the de facto standard for evaluating the performance of high-end computers running on-line transaction processing applications. Differing from other standard benchmarks, the transaction processing performance council only defines specifications for the TPC-C benchmark, but does not provide any standard implementation for end-users. Due to the complexity of the TPC-C workload, it is a challenging task to obtain optimal performance for TPC-C evaluation on a large-scale high-end computer. In this paper, we designed and implemented a large-scale TPC-C evaluation system based on the latest TPC-C specification using solid-state drive (SSD) storage devices. By analyzing the characteristics of the TPC-C workload, we propose a series of system-level optimization methods to improve the TPC-C performance. First, we propose an approach based on SmallFile table space to organize the test data in a round-robin method on all of the disk array partitions; this can make full use of the underlying disk arrays. Second, we propose using a NOOP-based disk scheduling algorithm to reduce the utilization rate of processors and improve the average input/output service time. Third, to improve the system translation lookaside buffer hit rate and reduce the processor overhead, we take advantage of the huge page technique to manage a large amount of memory resources. Lastly, we propose a locality-aware interrupt mapping strategy based on the asymmetry characteristic of non-uniform memory access systems to improve the system performance. Using these optimization methods, we performed the TPC-C test on two large-scale high-end computers using SSD arrays. The experimental results show that our methods can effectively improve the TPC-C performance. For example, the performance of the TPC-C test on an Intel Westmere server reached 1.018 million transactions per minute.     

Parametric Stabilization of Quantized Interconnected Systems with Application to Coupled Inverted Pendulums

This paper studies the analysis of parametric stability and decentralized state feedback control of a kind of quantized interconnected systems. The output of each controller is quantized logarithmically before it is input to the subsystem, and the quantized density would affect the stability of the systems. First, a decentralized state feedback controller is designed for interconnected systems without quantization and the corresponding stable region is obtained. Second, for a given controller, the lower bound of the quantization density is evaluated from parameters of local controllers. Finally, the proposed method is applied to coupled inverted pendulums systems which can be viewed as quantized interconnected systems. The simulation results show that by using the proposed quantized controllers, the interconnected inverted pendulum systems are parametrically stabilized.     

Experimental study of a novel hybrid constructed wetland for water reuse and its application in Southern China

A new type of hybrid constructed wetland (CW), consisting of both vertical-baffled flow wetland (VBFW) and horizontal subsurface flow wetland (HSFW), has been deployed in Southern China to naturally accelerate the removal of organic matter and nitrogen. The hybrid CW system is characterised by a combination of continuous baffled flow vertical wetland and 'S' pattern horizontal subsurface flow wetland with natural aeration ditches to increase the concentration of dissolved oxygen in the HSFW bed. An internal circulatory system from the HSFW effluent back to the VBFW may optionally be operated to enhance the biological denitrification effect. Cyperus alternifolius is the main macrophyte in the wetland bed. The performance of the hybrid CW was studied with a pilot-scale system and three full-scale systems for municipal sewage treatment in Southern China. The results suggest that this new hybrid CW can achieve removal efficiencies of chemical oxygen demand, suspended solids, ammonia nitrogen, total nitrogen, and total phosphorus of better than 83.6, 95.0, 71.7, 64.5 and 68.1% respectively, with a specific wetland bed area of 0.70-0.93 m(2) PE(-1). The mean effluent concentrations of these parameters would meet the regulatory discharge limits for wastewater treatment systems (GB18918, 2002) and reuse in the context of agricultural irrigation solutions in China.     

可重构阵列自主容错方法研究

设计了一种具有故障自诊断和自修复能力的可重构阵列单元结构。在功能细胞单元内部实现分布式的故障自诊断,在测试到故障后,可以自主地将距故障单元最近的空闲单元进行替换,接着自动取消受故障影响的线网,并在新的布线端点间对这些线网重新布线。以4位并行乘法器为例,实验结果证明了可重构单元阵列的故障自修复能力,并验证其重构时间较短且可靠性较高。     

扫描型红外图像实时目标检测研究

针对扫描型红外图像数据量大、背景复杂、横纹杂波干扰大和目标图像信噪比低等特点,提出一种适用于360°全方位扫描型红外图像目标检测的实时处理算法。算法预处理部分消除横纹杂波,实现目标增强和背景抑制;然后采用两级特征提取,大幅降低图像的数据量;最后根据帧间图像灰度特征相关的思想,完成扫描型红外图像目标检测的功能。根据本文算法的特点,以DSP+FPGA为核心处理器设计了具有实时处理能力强,数据传输容量大等优点的图像处理板。实验结果表明,本文算法是有效、可行的,图像处理板稳定、可靠,能满足扫描型红外图像实时目标检测的需求。     

Optimal models for single-period supply chain problems with fuzzy demand

The aim of this paper is to develop an optimal technique for dealing with the fuzziness aspect of demand uncertainties. Triangular fuzzy numbers are used to model external demand, and decision models in both non-coordination and coordination situations are constructed. It is shown that in the decision models there exists a unique solution that can be expressed analytically. Based on the closed form solutions for both models, the behaviors and relationships of both the manufacturer and the retailer are quantitatively analyzed, and a cooperative policy for the optimization of the whole supply chain is put forward.     

最小通路法在通信保密装备可靠性建模中的应用

针对通信保密装备可靠性建模难度大的问题,提出了一种新的适用于复杂系统的可靠性建模方法一最小通路法。通过在系统拓扑结构图上搜索出所有能够使系统正常工作的最小通路,建立系统的可靠性模型。该方法基于广义的网络拓扑结构,因此网络的源节点和目标节点不必局限于严格的定义,可以随意指定,具有很大的灵活性。实例证明,该方法可行有效。     

AES中字节代换和列混合的硬件可逆设计

针对AES硬件实现占用大量资源的缺点,对其两个核心计算部件(字节代换和列混合)进行了硬件可逆设计.该设计采用模块复用技术,使字节代换及其逆变换模块最大限度地共享GF(2<'8>)域中的模逆运算单元,而使列混合及其逆变换模块最大限度地共享p(x)乘运算单元,以较小的硬件代价实现了字节代换模块和列混合模块的硬件可逆设计.最后在Xilinx的FPGAVirtexE xev2000e-6上进行了仿真验证,实验结果表明,与其他同类设计相比,新设计方案明显减少了硬件开销.     

基于方差变化率判据-四分位的风电场功率异常数据识别

风电场运行中产生了数量巨大的历史数据,而提升历史数据的质量是实现风电场高效智能运维的前提。为此,文中分析了风电场风功率数据的分布特征和形成机理,提出基于方差变化率判据-四分位法组合的风电场风功率异常数据识别方法。首先,利用物理规则对原始风功率曲线进行预处理,剔除明显异常的数据;然后,利用风功率方差变化率判据法识别并清洗风功率曲线的堆积型异常功率数据点,判据的阈值借助箱型图自动获取;同时,利用四分位法识别并清洗剩余的离散型异常数据点;最后,通过算例验证了所提算法的可行性。研究结果表明所提算法具有易实现、效率高和通用性强的优点,其异常识别效果优于局部离群因子(local outlier factor,LOF)算法和Thompson tau-四分位算法,其耗时比LOF和Thompson tau-四分位算法分别减少9.6 s和0.49 s,且在5个不同位置的风电场验证了所提算法的通用性。