A data-based approach for multivariate model predictive control performance monitoring

An intelligent statistical approach is proposed for monitoring the performance of multivariate model predictive control (MPC) controller, which systematically integrates both the assessment and diagnosis procedures. Model predictive error is included into the monitored variable set and a 2-norm based covariance benchmark is presented. By comparing the data of a monitored operational period with the “golden” user-predefined one, this method can properly evaluate the performance of an MPC controller at the monitored operational stage. Characteristic direction information is mined from the operating data and the corresponding classes are built. The eigenvector angle is defined to describe the similarity between the current data set and the established classes, and an angle-based classifier is introduced to identify the root cause of MPC performance degradation when a poor performance is detected. The effectiveness of the proposed methodology is demonstrated in a case study of the Wood-Berry distillation column system.     

Performance analysis challenges and framework for high-performance reconfigurable computing

Reconfigurable computing (RC) applications employing both microprocessors and FPGAs have potential for large speedup when compared with traditional (software) parallel applications. However, this potential is marred by the additional complexity of these dual-paradigm systems, making it difficult to identify performance bottlenecks and achieve desired performance. Performance analysis concepts and tools are well researched and widely available for traditional parallel applications but are lacking in RC, despite being of great importance due to the applications’ increased complexity. In this paper, we explore challenges and present new techniques in automated instrumentation, runtime measurement, and visualization of RC application behavior. We also present ideas for integration with conventional performance analysis tools to create a unified tool for RC applications as well as our initial framework for FPGA instrumentation and measurement. Results from a case study are provided using a prototype of this new tool.     

一种基于统计分析的存储系统性能调优方法

计算机系统参数的合理配置能有效提升应用程序的性能。以NFS网络存储系统为例,提出了一种基于统计分析的存储系统性能调优方法,该方法分为关键系统参数识别和关键参数性能优化两个子阶段。阶段一采用方差分析(ANOVA)来建模系统参数的性能灵敏度,识别出对应用性能有显著影响的关键系统参数;然后在此基础上,阶段二采用响应面分析(RSM)来考察各关键参数对性能响应的影响,并综合前两个子阶段给出了性能调优算法,通过该算法找出系统的最优配置,从而最终达到性能调优的目的。最后,用实验评价了文中方法在Web, E-mail, Fileserver,Linux实用程序以及微基准测试等多种重要应用场景下的性能调优结果,实验结果证实了该调优方法的有效性和实用性。     

Transformation of four-component vertical seismic profiling records from Kola superdeep borehole, Russia

Multicomponent vertical seismic profiling (VSP) provides valuable and reliable information about the geologic structure of the subsurface and is one of the best ways to study seismic anisotropy. However, some VSP tools have no orientation instrumentation, and additional preprocessing steps may be required. Using the example of the 1992 VSP survey on the Kola Superdeep Borehole, Russia, we describe a general approach to the data reduction for a VSP tool with any number of channels. Due to data redundancy provided by the four-component Kola VSP tool, we are able to increase signal-to-noise ratio, estimate coupling variations, perform geophone gain corrections, and carry out an additional quality control. We describe the computer implementation of the method based on the seismic processing system currently being developed. The program is able to apply tool-rotation correction based on the polarization properties of the first break. This rotation technique works well in the case of offset VSPs; whereas for zero-offset VSPs, we recommend more robust rotation procedure based on the use of the direct shear wave. We find that plotting of instantaneous polarization azimuths provides a useful device to control the performance of tool-correction approaches.     

异构平台下的并行程序性能可视化方法

为了便于对异构平台下的并行程序性能进行分析,在对可视化技术和并行计算与控制显示平台研究的基础上设计了一种异构环境下的性能可视化模型.针对该模型的特点利用监测代码插桩技术、性能数据事后分析等方法,给出了并行性能数据获取、转换与绘图的具体方法和实现过程,为跨平台并行性能数据的采集和转换提供了一种简便方法.实验结果表明了在异构环境下该方法对并行性能数据可视化的可行性与有效性.     

Evaluating approaches to resource demand estimation

Resource demands are a key parameter of stochastic performance models that needs to be determined when performing a quantitative performance analysis of a system. However, the direct measurement of resource demands is not feasible in most realistic systems. Therefore, statistical approaches that estimate resource demands based on coarse-grained monitoring data (e.g., CPU utilization, and response times) have been proposed in the literature. These approaches have different assumptions and characteristics that need to be considered when estimating resource demands. This paper surveys the state-of-the-art in resource demand estimation and proposes a classification scheme for estimation approaches. Furthermore, it contains an experimental evaluation comparing the impact of different factors (monitoring window size, number of workload classes, load level, collinearity, and model mismatch) on the estimation accuracy of seven different approaches. The classification scheme and the experimental comparison helps performance engineers to select an approach to resource demand estimation that fulfills the requirements of a given analysis scenario.     

汽车散热器性能测试的计算机测控系统设计

介绍了一种汽车散热器散热性能和阻力特性测试系统,重点讨论了系统参数的检测和控制思路。采用基于CANBus的分布式测控模式,对现场测控模块实时检测和控制测试系统的温度、压力和流量等参数,监控计算机完成测试参数的输入、数据监控和测试结果分析。系统具有测试精度高、速度快、耗能少的特点,性能指标完全符合JB2293-78要求。目前该系统已稳定运行一年多,可应用于汽车散热器研究和生产机构。     

Measurement system design for civil infrastructure using expected utility

For system identification, most sensor-placement strategies are based on the minimization of the model-parameter uncertainty. However, reducing the uncertainty in remaining-life prognosis of structures is often more relevant. This paper proposes an optimization strategy using utility theory and probabilistic behavior prognoses based on model falsification to support decisions related to monitoring interventions. This approach, illustrated by the full-scale case study of a bridge, allows quantification of the expected utility of measurement systems while also indicating the profitability of monitoring actions. In addition, this approach is able to determine when the expected performance of monitoring configurations is reduced due to over-instrumentation. The use of model falsification for system identification allows for explicit inclusion of engineering heuristics in this knowledge intensive task while also offering robustness to effects of systematic modeling errors that are associated with idealization of complex civil structures.     

Implementing Fuzzy Logic and AHP into the EFQM model for performance improvement: A case study

In the current volatile and demanding business environment, managers are so eager to demonstrate that their organizations are excellent which can mainly be achieved through continuous performance improvement. The most applicable and suitable tools that by the assessment of organizations shows how successful they are in the organizational excellence path is European Foundation for Quality Management (EFQM) Excellence Model. This study aims at presenting a new integrated approach based on EFQM model using Fuzzy Logic, Analytical Hierarchy Process (AHP) technique and Operations Research (OR) model to improve the organizations’ excellence level by increasing the quality of business performance evaluation and determining of improvement projects with high priority. A case study in Yazd Regional Electricity Co. in Iran is presented to demonstrate the applicability of the proposed approach. In a way that, primarily, performance assessment by crisp method and the proposed method, Fuzzy method, is carried out. Then, strength points and the areas for improvement are identified by defining the scores for sub-criteria. Next, sub-criteria are prioritized to define the improvement projects by using AHP technique and Operations Research model. Finally, improvement projects with high priority are determined and some action plans for improvement projects are defined.     

一种用于涡街流量计的差分电荷放大器的研制

电荷放大器是涡街流量计信号调理电路中的一个关键模块,对整个测量系统的性能起到重要作用.该文设计一种基于经典仪用放大器结构的电荷放大器,并进行了理论分析、模型仿真和电路实验,证明该电荷放大器能够有效地改善对低速流体的测量性能,有助于扩展涡街流量计的量程比.     

基于网络断层扫描的网格网络性能测量分析

网格计算通过网络连接来获得一个高性能和高效的计算平台。网格网络的监测和性能测量为网格性能分析、负载平衡、任务调度等提供了重要的科学依据,而成为大规模网格服务的关键组件。现有的几种网格监测方法因缺乏对监测数据的推断分析而无法对网格网络的性能进行测量。通过对网格网络性能测量的特点、GloPerf及传统网络测量技术的分析,提出了基于网络断层扫描的网格网络性能测量方法。研究结果为网格网络性能的测量提供了新的途径。     

Impact of the integration of tactical supply chain planning determinants on performance

In fulfilling customers’ orders, one of the goals of tactical supply chain planning is to satisfy the customers in terms of delivery efficiency, delivery quantity accuracy and on-time delivery. These performance objectives can be impacted by the way firms plan each of the three phases of the supply chain: procurement, production and distribution. Though the link between each of these phases and supply chain performance has been studied in extant literature, very few authors have considered all three phases at the same time. By adopting an integrated approach, this paper therefore aims to study the manner in which, taken together in one model, the planning determinants of the different phases impact on supply chain performance. It is important for managers to understand, from a holistic and integrated perspective, how a given combination of the planning determinants of the supply chain functions impacts positively or negatively on the performance of the supply chain. To carry out this study, this paper starts by proposing an integrated framework that is based on the SCOR model and the customer order decoupling point (CODP), followed by a five-step methodology for tactical supply chain planning. Then, using an analytical model and simulations, and based on a numerical example, it shows how the proposed methodology can be applied in a given decision-making situation. Our results enabled to identify the worst and the best combinations of planning determinants.     

微信流量特性分析与建模

微信是现代互联网的主要应用之一,到目前为止有关微信流量特性分析与建模的研究较少.本文以微信流量为研究对象,分析验证微信流量同时具有自相似性和突发性.针对这两种特性进行微信流量建模,采用线性分形稳定噪声模型刻画微信流量特性,完成了模型的参数估算和效果分析.本文的研究成果是后续的网络性能分析、网络流量监管等的基础.     

基于事件的并行程序性能监测库的实现技术

并行程序性能分析工具的一种主要设计思想是采用源程序们随法,而其中性能监测库是这类并行程序性能分析工具的重要组成部分,提出了玫种基于事件的并行程序性能监测库的实现技术,并给出了一个基于ＳＶＭ系统的性能分析工具的性能监测库的实现方法。     

Dynamic monitoring of land subsidence in mining area from multi-source remote-sensing data – a case study at Yanzhou,China

Energy consumption in China is currently based on coal, but the exploitation of coal resources is accompanied by serious threats to the environment. In order to balance mine exploitation, land resource protection and land reclamation, there is an opportunity for monitoring land subsidence in mining area. This article examines a case study of Yanzhou mining area (YZMA) and proposes a new method for dynamic monitoring of land subsidence, which is a hybrid approach using a combination of multi-scale edge detection, relational model establishment and digital elevation model (DEM) difference analysis. A wavelet transform is used to extract the edges of water and marsh, which are buffered with the model to achieve the acquisition of the subsidence edge. DEM difference analysis is finally used to modify the results. The results indicate that this hybrid method improves subsidence monitoring performance by ±0.02 km² of the area accuracy. This method can be viewed as an effective approach to monitor a wide range of land subsidence in plain mining areas of China.     

基于WCET分析的实时系统轨迹获取技术

时序约束是判断实时系统运行是否正确的重要规约.为了减小测试时由于对系统进行插装而产生的对实时系统行为的影响,提出了一种混合式监控方法.它对系统的时间干扰比纯软件方式小,并支持对系统的完全测试.此外,还提出一种基于WCET(worst-case execution time)分析技术的目标系统时间补偿方法,在精确地计算插入断言对目标系统的时间影响基础上,给出时间补偿.     

Rewriting executable files to measure program behavior

Inserting instrumentation code in a program is an effective technique for detecting, recording, and measuring many aspects of a program's performance. Instrumentation code can be added at any stage of the compilation process by specially-modified system tools such as a compiler or linker or by new tools from a measurement system. For several reasons, adding instrumentation code after the compilation process—by rewriting the executable file—presents fewer complications and leads to more complete measurements. This paper describes the difficulties in adding code to executable files that arose in developing the profiling and tracing tools qp and qpt. The techniques used by these tools to instrument programs on MIPS and SPARC processors are applicable in other instrumentation systems running on many processors and operating systems. In addition, many difficulties could have been avoided with minor changes to compilers and executable file formats. These changes would simplify this approach to measuring program performance and make it more generally useful.     

A new approach to performance modelling of Client/Server distributed data base architectures

The recent technological advances in the field of computer and communication lead to distributed data base (DDB) architectures based on the Client/Server paradigm. Available DDB performance prediction methodologies are not sufficiently adequate being too expensive both in the model definition and in the model analysis because of the structural complexity and the large system dimension.

This paper concentrates on a new approach to performance modeling of DDB systems called “independent modelling approach”. This approach separates the DDB software model from the DDB machinery model, and models from solution techniques. This way the aspects related to data contention can be analysed as a pure software characteristic and separated from resource contention, considered as a machinery characteristic. Furthermore, it is possible to analytically model some system aspects (e.g., the software only, or part of it, without involving the machinery model), and apply combined analytical/simulation methods for the remaining system aspects. This results in higher flexibility at lower computational cost in the performance analysis of complex DDB architectures.

A case study is developed and experimental results are discussed to show the effectiveness of the approach.