Optimal divisible job load sharing for bus networks

Optimal load allocation for load sharing a divisible job over N processors interconnected in bus-oriented network is considered. The processors are equipped with front-end processors. It is analytically proved, for the first time, that a minimal solution time is achieved when the computation by each processor finishes at the same time. Closed form solutions for the minimum finish time and the optimal data allocation for each processor are also obtained     

Equal allocation scheduling for data intensive applications

A new analytical model for equal allocation of divisible computation and communication load is developed. Equal allocation of load is attractive in multiple processor systems when real time information on processor and link capacity that is necessary for optimal scheduling is not available. The model includes a detailed accounting of solution reporting time. Equal allocation scheduling is compared with sequential scheduling and a new type of multi-installment scheduling. Aerospace applications include the processing of satellite imagery, radar, and sensor networks.     

Divisible load scheduling on single-level tree networks with buffer constraints

Scheduling a divisible load on a heterogeneous single-level tree network with processors having finite-size buffers is addressed. We first present the closed-form solutions for the case when the available buffer size at each site is assumed to be infinite. Then we analyze the case when these buffer sizes are of finite size. For the first time in the domain of DLT (divisible load theory) literature, the problem of scheduling with finite-size buffers is addressed. For this case, we present a novel algorithm, referred to as incremental balancing strategy, to obtain an optimal load distribution. Algorithm IBS adopts a strategy to feed the divisible load in a step-by-step incremental balancing fashion by taking advantage of the available closed-form solutions of the optimal scheduling for the case without buffer size constraints. Based on the rigorous mathematical analysis, a number of interesting and useful properties exhibited by the algorithm are proven. We present a very useful discussion on the implications of this problem on the effect of sequencing discussed in the literature. Also, the impact of Rule A, a rule that obtains a reduced optimal network to achieve optimal processing time by eliminating a redundant set of processor-link pairs, is also discussed. Numerical examples are presented.     

Signature search time evaluation in flat file databases

For the first time, divisible load scheduling theory is used to solve for the expected time for searching for both single and multiple signatures in certain multiple processor database architectures. The target architectures examined for illustrative purposes are linear daisy chains and single level tree networks with single and multiple installment load distribution. The use of divisible load modeling and analysis yields elegant expressions for expected search time.     

Processor equivalence for daisy chain load sharing processors

A linear daisy chain of processors in which processor load is divisible and shared among the processors is examined. It is shown that two or more processors can be collapsed into a single equivalent processor. This equivalence allows a characterization of the nature of the minimal time solution, a simple method to determine when to distribute load for linear daisy chain networks of processors without front end communication subprocessors and closed form expressions for the equivalent processing speed of infinitely large daisy chains of processors     

Wireless sensor networks: scheduling for measurement and data reporting

An optimal load allocation approach is presented for measurement and data reporting in wireless sensor networks with a single level tree network topology. The measurement problem investigated involves a measurement space, part of which can be sampled by each sensor. We seek to optimally assign sensors part of the measurement space to minimize reporting time and energy usage. Three representative measurement and reporting strategies are studied. This work is novel as it considers, for the first time, the measurement capacity of processors and assumes negligible computation time which is radically different from the traditional divisible load scheduling research to date. Aerospace applications include satellite remote sensing and monitoring and sensor networks deployed and monitored from the air.     

A flexible processor for a digital adaptive array radar

A digital beamforming processor for an adaptive array radar is described. The functionality and the architecture of the processor are strongly driven by a goal of achieving adaptive null depths in the 60-dB to 70-dB range, which necessitates substantial preprocessing of each channel. In particular, conversion to baseband quadrature channels is accomplished digitally using a single A/D converter per channel, and FIR (finite impulse response) equalizing filters are employed in each channel to match channel transfer functions. The processor is highly modular, and this not only distributes the total processing load, but also the I/O (input/output) bandwidth requirement. This is accomplished by distributing the adaptive beamforming algorithm systolically across a linear array of processing nodes. The processor is expandable to a different number of channels and sufficiently flexible to be applied to other problems of an array signal processing nature. Experimental data presented demonstrate that the processor is capable of supporting channel-to-channel cancellation of interfering signals to the level of -65 dB     

Task allocation and reallocation for fault tolerance inmulticomputer systems

The goal of task allocation in a set of interconnected processors (computers) is to maximize the efficient use of resources and thus reduce the job turnaround time. Proposed is a simple yet effective method to allocate the tasks in multicomputer systems for minimizing the interprocessor communication cost subject to resource limitations defined by the system and designer. The limitations can be viewed as results from the load balancing since the execution time of each task, the number of available processors, processor speed, and memory capacity are known to the system or designer. As the number of processors increases, the probability of a failure existing somewhere in the systems at any time also increases. Very few established task allocation models have considered the reliability property. In multicomputer systems, we define system reliability as the probability that the system can run the tasks successfully. After the (nonredundant) task scheduling strategy is defined, tasks are then reallocated to processors statically and redundantly. This is a form of time redundancy, in which if some processors fail during the execution, all tasks can be completed on the remaining processors (but at a longer time). Due to static preallocation of tasks this method is simpler and thus more practical than well-known dynamic reconfiguration and rollback recovery techniques in multicomputer systems. We demonstrate the effectiveness of the task allocation and reallocation for hardware fault tolerance by illustrations of applying the methods to different examples and practical communications network multiprocessor system     

Design and implementation for a digital synchronous reluctancedrive

A systematic controller design for a synchronous reluctance drive system is presented. This controller consists of two parts: a forward-loop H^∞ controller to improve the transient response, and a load compensator to reduce the load disturbance. Based on a simplified model of the drive system, a control algorithm has been derived. Detailed analysis of the characteristics of the closed-loop system is presented. The effects of the parameter variations are also studied. A digital signal processor, TMS-320-C30, is used to implement the control algorithm. Both the speed control and the position control of the drive system can be implemented by using the proposed control method. Furthermore, all the control loops are executed by the digital signal processor. The system, as a result, is very flexible. The whole drive system performs well although its hardware is very simple. For speed control, the system can be operated at a speed as low as 1 r/min. For position control, the system can accurately control a one-axis table. In addition, the system also has good position tracking ability. Several experimental waveforms validate the simulated results     

Identification and standardization of maneuvers based upon operational flight data

To find a way of loads analysis from operational flight data for advanced aircraft,maneuver identification and standardization jobs are conducted in this paper. For thousands of sorties from one aircraft, after studying the flight attitude when performing actions, the start and end time of the maneuvers can be determined. According to those time points, various types of maneuvers during the flight are extracted in the form of multi-parameters time histories. By analyzing the numerical range and curve shape of those parameters, a characteristic data library is established to model all types of maneuvers. Based on this library, a computer procedure using pattern-recognition theory is programmed to conduct automatic maneuver identification with high accuracy. In that way, operational loads are classified according to maneuver type. For a group of identified maneuvers of the same type, after the processes of time normalization, trace shifting, as well as averaging and smoothing, the idealization standard time history of each maneuver type is established.Finally, the typical load statuses are determined successfully based on standard maneuvers. The proposed method of maneuver identification and standardization is able to derive operational loads effectively, and might be applied to monitoring loads in Individual Aircraft Tracking Program(IATP).     

Adaptive Resource Allocation in a Spatial Spectral Processor

A method for achieving an optimal allocation of fixed computational resources in a spatial/spectral filtering system is developed. Specifically, clock cycles per unit time for a given processor are to be optimally allocated. The system is a cascade of three subsystems: an adaptive beamformer, a bandpass filter, and a spectral whitener. Each subsystem has adjustable parameters which are related to required arithmetic operations. A gradient projection algorithm is used to find a best allocation according to specified criteria. Two simulation examples are presented to show how the algorithm operates and to indicate the kind of improvement that is possible in a system design.     

VXI or PXI test system improvement using DSP

The results of a study into the use of distributed digital signal processing (DSP) at the instrument level in a VXI and PXI based test system and the effects on test time. One of the limiting factors in testing mixed signal or analog devices using standard bus based instruments is the transfer speed from the instrument to the controlling computer of large amounts of waveform data. This is important as these types of tests use non-deterministic, quantized signals that must be mathematically processed to extract test information. This processing can either be done at the instrument or at the central controller. If the processing is done at the instrument then only the results are transferred to the controller. If the controller does the processing then the raw data must be transferred to and from the instrument. Using two instruments, one in VXI and one in PXI, this paper measures the effects of typical tests contesting the measurements as done in the central processor as opposed to a distributed DSP processor in each instrument For each acquisition instrument, tests were implemented by capturing the data and moving it to the controlling computer where it was processed to extract test results, or by using the instruments on-board DSP so only the final test results were set to the controlling computer. The study results show that a significant improvement in test time can be made by selecting "smart" instruments for the test system when using PXI or VXI based instruments.     

网格远程调度系统的设计与实现

阐明了在多集群的网格中，资源调度和任务的分配受到网络和通信延迟的限制。采用元调度机制有效的将作业分配到不同集群计算机中，进一步，义采用动态绑定机制来减少作业分配的延迟。这一机制是绑定相似的请求来组成复合请求分配到网格资源。在不同的服务负载下应用了这些机制，结果显示这些机制能够帮助获得负载均衡和减少作业分配的延迟，同时也能减少程序的运行时间。     

Distributed binary integration

A distributed radar detection system that employs binary integration at each local detector is studied. Local decisions are transmitted to the fusion center where they are combined to yield a global decision. The optimum values of the two thresholds at each local processor are determined so as to maximize the detection probability under a given probability of false alarm constraint. Using an important channel model, performance comparisons are made to determine the integration loss     

Quickest detection for sequential decentralized decision systems

Quickest detection procedures are techniques used to detect sudden or abrupt changes (also called disorders) in the statistics of a random process. The goal is to determine as soon as possible that the change occurred, while at the same time minimizing the chance of falsely signaling the occurrence of a disorder before the change. In this work the distributed quickest detection problem when the disorder occurs at an unknown time is considered. The distributed local detectors utilize a simple summing device and threshold comparator, with a binary decision at the output. At the fusion center, the optimal maximum likelihood (ML) procedure is analyzed and compared with the more practical Page procedure for quickest detection. It is shown that the two procedures have practically equivalent performance. For the important case of unknown disorder magnitudes, a version of the Hinkley procedure is also examined. Next, a simple method for choosing the thresholds of the local detectors based on an asymptotic performance measure is presented. The problem of selecting the local thresholds usually requires optimizing a constrained set of nonlinear equations; our method admits a separable problem, leading to straightforward calculations. A sensitivity analysis reveals that the resulting threshold settings are optimal for practical purposes. The issue of which sample size to use for the local detectors is investigated, and the tradeoff between decision delay and communication cost is evaluated. For strong signals, it is shown that the relative performance deteriorates as the sample size increases, that is, as the system cost decreases. Surprisingly, for the weak signal case, lowering the system cost (increasing the sample size) does not necessarily result in a degradation of performance     

航空发动机静不定转子支撑载荷的有限元分析

应用平面应力单元和傅立叶环单元耦合的有限元法对航空发动机静不定转子支撑惯性载荷进行计算,解决了传统的材料力学方法求解静不定转子支撑惯性载荷时的两个缺陷,即当支座和轴承的耦合刚度不可忽略时,很难建立正确的变形协调条件以及当转子不存在明显的轴的特征时,采用梁的弯曲理论将导致较大的误差,同时,该方法将复杂的三维问题转化为二维问题,计算工作量小,速度快,精度及效率高.      

低空突防实时航迹规划计算机方案设计研究

地形跟踪/地形回避、威胁回避(TF/TA2)实时航迹规划计算机是综合TF/TA2低空突防系统的控制核心.系统按照由它产生的最优航迹产生制导指令,并控制飞行器按此最优航迹完成突防任务.本文提出了一种实时航迹规划计算机的设计方案.该方案采用由共享存储器耦合的三个智能模块(即智能总线接口、航迹规划处理机和数据处理机)并行运行的结构,以提高系统的运行速度,满足低空突防对航迹规划计算机的实时性要求.其中,航迹规划处理机和数据处理机的双机互备份降级运行方式提高了系统的可靠性.此外,以闪存为存储介质的内存数据库使系统检索和读取机载数据的速度大大提高,且闪存的非易失性保证了机载数据的可靠性.     

空战中机群编队分层优化算法

针对机群编队优化计算复杂的问题,提出了一种分层优化算法。根据敌我双方的距离、角度、速度以及飞机导弹、雷达的性能,建立了多机协同任务分配模型。根据空战中常用的基本飞机队形,对敌方机群编队进行分层,对每层分别计算己方对选取各种基本队形时的任务分配结果和队形优化优势值,通过比较得到己方机群编队的每层最优队形,当得到己方每层的最优队形之后,将己方每层最优队形进行组合解码就可得到己方机群编队的最优队形。仿真结果表明该方法能有效地解决机群编队队形优化问题,并且该算法具有较好的实时性。     

负荷条件下注意力分配策略对情境意识的影响

为探究负荷条件下不同注意力分配策略对情境意识（SA）的影响，招募22名被试开展了3种注意力分配策略（平均分配、主次分配、多级分配）×2种脑力负荷（低负荷、高负荷）条件下的被试内双因素设计的实验任务，记录情境意识全面测量技术（SAGAT）、行为绩效、眼动和脑电（EEG）指标为因变量。实验结果表明，在不同脑力负荷下，相较于多级注意力分配策略和主次注意力分配策略，平均注意力分配策略的SAGAT得分和绩效正确率均更低、最小近邻指数（NNI）更大；在高脑力负荷下，相较于多级注意力分配策略，主次注意力分配策略的SAGAT得分更高、绩效反应时间更短并且NNI值更低；SAGAT得分与平均注视时间、NNI、θ相对功率和α相对功率均存在显著低度相关。本研究结果提示，在不同脑力负荷条件下，采用平均注意力分配策略可能导致作业人员的注意力更为分散，从而产生更差的工作绩效和更低的SA水平；而在高脑力负荷条件下，相比于多级注意力分配策略，主次注意力分配策略更有助于作业人员提取关键信息并维持更好的SA水平，但同时可能存在SA丧失的风险；眼动的平均注视时间和NNI指标以及EEG的θ和α相对功率指标具有较好的表征SA的潜力。     

网络连接机群上CFD计算的一种负载平衡方法

讨论在网络连接的分布式存储并行机群上进行CFD计算的一种负载平衡方法和相关问题。当数值计算的方法是区域分解法时,各节点机上的负载与其处理的子区域的网格节点数成正比,所以同样大小的子区域可保证负载平衡。采用负载再分配即区域再剖分的方法来达到动态负载平衡,构造了一种对多块网格(每块内为结构网格但各块间的连接关系可以是非结构的)进行近似平均分划的方法,并用一种数据结构和算法保证了剖分出的多个子区之间正确的互联和边界信息传递关系。给出了用这种剖分算法对常见多块网格进行分划的例子,并对三维流场进行了实际计算。结果证明本文方法是正确的,能有效地均衡计算负载,达到较理想的并行效率。