Two-armed bandit problem for parallel data processing systems

We consider application of the two-armed bandit problem to processing a large number N of data where two alternative processing methods can be used. We propose a strategy which at the first stages, whose number is at most r ? 1, compares the methods, and at the final stage applies only the best one obtained from the comparison. We find asymptotically optimal parameters of the strategy and observe that the minimax risk is of the order of N ^α , where α = 2 ^r?1/(2 ^r ? 1). Under parallel processing, the total operation time is determined by the number r of stages but not by the number N of data.     

Application of radial basis function neural network for information processing in fiber optical distributed measuring systems

The paper discusses tomography reconstruction of distributed physical fields. The problem is shown to be solved by using distributed measuring networks based on optical fibre sensors. Special attention is paid to tomography measuring networks based on measuring elements with integrated sensitivity. The advantages of radial basis function neural networks (RBFNN) for data processing of signals in the distributed fiber optical measuring systems are studied. RBFNN specifics which enhance the efficiency of computations of physical fields and technical and technological objects under reconstruction are key issues. Comparative analysis of the operating efficiency of RBFNN method and standard analytical and algebraic method for fiber-optical tomography reconstruction is reported. The article is published in the original.     

测量轧制力的光纤传感系统的研制

研制了一种用于轧制力测量的光纤传感器,其传感头采用法布里-珀罗腔的结构。分析了该传感器的原理,导出了法布里 珀罗干涉腔反射光强与轧制力的关系表达式。实验结果表明,该方案测量准确度为0.18%,线应变灵敏度为1.2×104V,分辨力达到2.5×10-8。用该传感器测量轧制力是正确、可行的。     

An effective speedup metric for measuring productivity in large-scale parallel computer systems

With the parallel computer systems scaling-up, the measure index for performance of the systems demands a shift from traditional “high performance” to “high productivity.” This brings a new challenge to defining a synthetic, yet meaningful, measure index of multiple productivity variables; namely computing performance, reliability, energy consumption, parallel software development, etc. Traditional measures for large-scale parallel computer systems merely focus on computing performance, and are incapable of measuring the multiple productivity variables simultaneously in an effective manner. A recently proposed market-related money model, which pursues high utility/cost ratio, relies on money as a measure to consider the multiple productivity variables. Differing from the previous models, this paper proposes a novel system productivity speedup metric for large-scale parallel computer systems. The metric uses speedup instead of money to comprehensively unify the measures of multiple productivity variables. Finally, we propose a trade-off productivity measurement to weigh different productivity variables, to address different design targets. The measurement can facilitate the system evaluation, expose future technique tendencies, and guide future system design.     

Signal parallel input liquid-crystal devices for multichannel optical processing systems

Variants of liquid-crystal spatial light modulators control devices, that provide partial or fully parallel information input in multichannel optical signal processing systems are suggested. Applications of the proposed solutions enables to increase to a considerable extent the optical processors capacity that is actual for a number of practical problems.     

双光路光纤液位测量系统的研制

介绍了一种用于光纤液位传感器的电路测量系统。根据光纤光强调制的特点,设计了一种采用LD激光器以及能够进行对称补偿的双光路接收电路,消除了外界环境非测量因素的干扰。经现场试验,得到了理想的测量结果,证明可用于石化工业等危险环境的液位高效在线连续测量。     

Numerical techniques for the inverse optimal control problem in limited state feedback systems

The numerical problem of finding the performance index parameters {Q}, for which a given control {u = fx} is optimal, is studied. Two successful algorithms are described for the single input case. Both apply to systems which are optimal within the constraint of limited state availability. The structure of Q must be prespecified to allow only r free parameters (where r is the dimension of the feedback vector). This ensures that the solution is unique. Numerical examples and program listings are included.     

Designing parallel systems: a performance prediction problem

PSEE (Parallel System Evaluation Environment) is a software tool that provides a multiprocessor system for research into alternative architectural decisions and experimentation, with such issues as selection, design, tuning, scheduling, clustering and routing policies. PSEE facilitates simulation and performance evaluation as well as a prediction environment for the design and tuning of parallel systems. These tasks involve cycles through programming, simulation, measurement, visualization and modification of parallel system parameters. PSEE includes a parallel programming tool, a simulator for link oriented parallel systems, BOLAS, and a performance evaluation tool, GRAPH. These PSEE modules are tools oriented to support the above tasks in user-friendly, interactive and animated graphical form. PSEE provides quantitative information in a graphical tailored form. This numerical/graphical output helps the user make decisions about his/her particular development.     

Models of parallel data processing in multiprocessor computing systems

Models of parallel computations are considered for a wide class of data processing programs. Properties of programs are investigated and approaches to parallelizing sequential data processing programs and designing parallel programs are proposed. Computation optimizing problems are formulated.Translated from Kibernetika, No. 4, pp. 1–8, 42, July–August, 1989.     

测量甲烷体积分数的高灵敏度光纤传感器研究

基于气体的红外吸收原理,研究了一种能在复杂环境下测量甲烷气体体积分数的新方法.这种方法可以有效地减小由于光源的不稳定、环境的变化而引起的测量误差.在这种测量方法中设计了一条参考测量光路,此参考测量光路和测量光路同时随环境的变化而变化,通过对待测量气体光路与参考气体测量光路作对比而得出较为准确的待测甲烷气体体积分数.     

Reducing complexity of the distributed switch for parallel data processing systems

The paper aimed at demonstrating the feasibility of reducing complexity of the distributed switches interconnecting the units of the data processing systems. Simplification was obtained by the use of optical facilities: to switch n devices, it is possible to design the single-step switches of n log₂ n switching elements assuming any of the two possible states. Retroreflectors were proposed to simplify organization of the group connections. Methods for using the proposed devices in the switching modes that underlie many tasks of control of interaction of the data processing devices were presented.     

Avoiding the local-minimum problem in multi-agent systems with limited sensing and communication

In this paper, we consider a control problem for nonholonomic multi-agent systems in which agents and obstacles operate within a circular-shaped work area. We assume that agents only have limited sensing and communication ranges. We propose a novel control scheme using potential functions that drives agents from the initial to the goal configuration while avoiding collision with other agents, obstacles, and the boundary of the work area. The control scheme employs an avoidance strategy that ensures that the agents are never trapped at local minima that are typically encountered with most potential function-based approaches. A numerical simulation is presented to demonstrate the validity and effectiveness of the proposed control scheme.     

Robust stability of parameter uncertain systems with limited data rates

This article investigates the robust stability problem for parameter uncertain systems with limited data rates. A time-varying recursive allocation (TVRA) algorithm is proposed to solve the modal decomposition and data-rate allocation problems that have to be faced for a multi-dimensional uncertain system. Sufficient conditions for robust stability of the feedback loop are derived. A positive critical lower bound of data rates is presented, below which there exists no quantisation, coding and control scheme to stabilise an unstable parameter uncertain plant. Simulation results show the validity of the proposed scheme.     

大规模云同步归集数据系统的异步并行优化

国民经济非垂直管理行业或领域建立大数据中心,需要配备能大规模云同步归集行业数据的软件系统,“行业数据云通用的同步枢纽与大数据联合体平台”（GSMS）就是为此而研制的。GSMS主要用于通过互联网大规模同步采集各地异构自治系统（或设备）的业务或事实数据并加以开发应用。在实际应用中,当众多GSMS客户线程各自并发地向GSMS数据中心同步数据时,所产生的大规模数据同步会话将汇聚在GSMS服务端,从而形成处理瓶颈。此外,同步会话全程串行的锁步机制也会制约大规模数据同步归集的性能。为此,提出并实现了一种异步并行化改进GSMS系统方案：将服务端高时耗计算环节从数据同步串行锁步过程中分离出来,为其引入基于多道消息队列中间件的异步并行处理机制,并提供相应的松弛同步事务保障措施。实践表明,正确地实现这种异步并行处理能有效提升服务端处理速度并满足同步系统的可靠性和一致性要求。     

Exponential stabilisability of finite-dimensional linear systems with limited data rates

A critical notion in the field of communication-limited control is the smallest data rate above which there exists a stabilising coding and control law for a given plant. This quantity measures the lowest rate at which information can circulate in a stable feedback loop and provides a practical guideline for the allocation of communication resources. In this paper, the exponential stabilisability of finite-dimensional LTI plants with limited feedback data rates is investigated. By placing a probability density on the initial state and casting the objective in terms of state moments, the problem is shown to be similar to one in asymptotic quantisation. Quantisation theory is then applied to obtain the infimum stabilising data rate over all causal coding and control laws, under mild requirements on the initial state density.     

Artifacts in the A&;A meta-model for multi-agent systems

In this article we focus on the notion of artifact for agents in multi-agent systems (MAS) as a basis for a new meta-model promoting the modelling and engineering of agent societies and MAS environment as first-class entities. Its conceptual foundations lay upon theories and results coming from computational sciences as well as from organisational and cognitive sciences, psychology, computer supported cooperative work (CSCW), anthropology and ethology. In the resulting agents & artifacts (A&A) meta-model, agents are the (pro-)active entities in charge of the goals/tasks that altogether build up the whole MAS behaviour, whereas artifacts are the reactive entities providing the services and functions that make individual agents work together in a MAS, and that shape agent environment according to the MAS needs. After presenting the scientific background, we define the notions of artifact in the A&A meta-model, discuss how it affects the notion of intelligence in MAS, and show its application to a number of agent-related research fields.     

A parallel tabu search for solving the primal buffer allocation problem in serial production systems

This paper presents a novel parallel tabu search (PTS) algorithm equipped with a proper adaptive neighborhood generation mechanism to solve the primal buffer allocation problem, which consists of minimizing the total buffer capacity of a serial production system under a minimum throughput rate constraint. An evaluative method based on a specific algorithm has been implemented to simulate the system behavior. In order to validate the effectiveness of the proposed PTS a mixed integer linear programming-based simulation/optimization approach and several metaheuristics from the relevant literature have been implemented. Since most metaheuristics are sensitive to the parameter setting, a proper calibration analysis based on a non-parametric test has been performed. Then, a comprehensive comparison analysis, concerning with both quality of solutions and computational efficiency, has been carried out. Finally, through the numerical results obtained from PTS, a multi-factorial experimental analysis has been developed to analyze the influencing factors of the problem under investigation.     

An iso-time scaling method for big data tasks executing on parallel computing systems

Due to the sustained and rapid growth of big data and the demand on higher accuracy solutions for application problems, the completion time of fixed-time big data tasks executing on original parallel computing systems becomes longer and longer. To meet the requirement of fixed completion time, the original parallel computing systems need to be scaled accordingly. Therefore, this paper studies an iso-time scaling method to guide the scaling of parallel computing systems. Firstly, the models of big data parallel tasks and parallel computing systems are built, and an algorithm is designed to calculate the completion time of big data parallel tasks. Secondly, according to the actual situation of the current majority computing centers, we put forward some reasonable hypotheses, make full use of backup computational nodes, and optimize the cost of scaling parallel computing systems. Then, a vertical scaling algorithm is designed to upgrade computational nodes, and a horizontal scaling algorithm is designed to add computational nodes. Furthermore, this paper compares the two scaling algorithms in the aspects of time complexity, degree of parallelism and system utilization for scaled parallel computing system. Finally, some simulation experiments are conducted. The experimental results show that our method can keep the completion time within fixed time when the increasing data parallel tasks execute on the scaled parallel computing systems and it has better effect in scaling cost than traditional methods.