一种基于实测的高维动态负载平衡方法

针对大规模科学计算中的强非规则结构负载问题,作者开发出一种基于实测的动态负载平衡方法．首先,将由规则结构化网格组成的模拟区域剖分成多块;其次,把块的高维坐标转换成一维Hilbert空间填充曲线（HSFC）索引;然后,基于实测信息采用多层均权法剖分按一维HSFC索引排列的块;最后根据剖分信息重分配块以平衡负载．它把仅适用于一维的多层均权法扩展到二维和三维,并引入更多的实测信息和块数据结构．与ISP方法相比,该方法在64个CPU上提高负载平衡效率10％,在某MPP的500个CPU上模拟强非规则结构负载问题时,获得了88％的负载平衡效率和84％的并行效率．     

一种基于主负载信息表的动态负载平衡模型及其均衡算法研究

1.引言对于静态和动态负载平衡算法的研究,国际上已经有了30多年的历史。特别是近年来随着一些高速网络的兴起(如ATM),对于它的研究仍然方兴未艾。但是因为一些并行任务之间的互相依赖关系和通讯量的大小很难在编译时就进行确定,所以人们更加倾向于研究动态负载平衡。虽然目前国内外在这方面产生了不少各有特色的算法,譬如Hui等人就在理     

Dynamic Load Balancing and Job Replication in a Global-Scale Grid Environment: A Comparison

Global-scale grids provide a massive source of processing power, providing the means to support processor intensive parallel applications. The strong burstiness and unpredictability of the available processing and network resources raise the strong need to make applications robust against the dynamics of grid environments. The two main techniques that are most suitable to cope with the dynamic nature of the grid are dynamic load balancing (DLB) and job replication (JR). In this paper, we analyze and compare the effectiveness of these two approaches by means of trace-driven simulations. We observe that there exists an easy-to-measure statistic Y and a corresponding threshold value Y*, such that DLB consistently outperforms JR when Y > Y*, whereas the reverse is true for Y < Y*. Based on this observation, we propose a simple and easy-to-implement approach, throughout referred to as the DLB/JR method, that can make dynamic decisions about whether to use DLB or JR. Extensive simulations based on a large set of real data monitored in a global-scale grid show that our DLB/JR method consistently performs at least as good as both DLB and JR in all circumstances, which makes our DLB/JR method highly robust against the unpredictable nature of global-scale grids.     

基于应用级监控的动态负载均衡系统

设计并实现新型动态负载均衡系统。该系统在Linux服务器集群系统的基础上进行扩展,完善了B/S管理界面,能监控应用级服务,有4层高可用性保证。设计专门的算法,通过历史信息预测负载以达到动态负载均衡,提高了曙光4000A服务器集群的吞吐量和利 用率。     

A solution approach based on beam search algorithm for disassembly line balancing problem

The disassembly line balancing (DLB) problem is the process of allocating a set of disassembly tasks to an ordered sequence of workstations in such a way that optimizes some performance measures (e.g., cycle time, number of stations). Since DLB problems belong to the class of NP hard, many heuristic and meta-heuristic algorithms are applied to cope with the complexity of the DLB problems in order to obtain acceptable solutions in a reasonable amount of time. In this study, a beam search (BS) based approach for the DLB problem is proposed. Minimization of number of workstations is used as the performance measure. The proposed algorithm is compared with the optimal solutions of well-known real cases and generated test problems. The results indicate that the proposed approach based on BS is a very competitive and promising tool for further researches.     

A novel dynamic load balancing scheme for parallel systems

Adaptive mesh refinement (AMR) is a type of multiscale algorithm that achieves high resolution in localized regions of dynamic, multidimensional numerical simulations. One of the key issues related to AMR is dynamic load balancing (DLB), which allows large-scale adaptive applications to run efficiently on parallel systems. In this paper, we present an efficient DLB scheme for structured AMR (SAMR) applications. This scheme interleaves a grid-splitting technique with direct grid movements (e.g., direct movement from an overloaded processor to an underloaded processor), for which the objective is to efficiently redistribute workload among all the processors so as to reduce the parallel execution time. The potential benefits of our DLB scheme are examined by incorporating our techniques into a SAMR cosmology application, the ENZO code. Experiments show that by using our scheme, the parallel execution time can be reduced by up to 57% and the quality of load balancing can be improved by a factor of six, as compared to the original DLB scheme used in ENZO.     

基于NB的双级分类模型在邮件过滤中的研究

使用朴素的贝叶斯（NB）分类模型对邮件进行分类，是目前基于内容的垃圾邮件过滤方法的研究热点。朴素的贝叶斯在参数之间联系不强的时候分类效果简单而有效。但是朴素的贝叶斯分类模型中对特征参数的条件独立假设无法表达参数之间在语义上的关系，影响分类性能。在朴素的贝叶斯分类模型的基础上，我们提出了一种双级贝叶斯分类模型（DLB，Double Level Bayes），既考虑到了参数之间的影响又保留了朴素的贝叶斯分类模型的优点。同时时DLB模型与朴素的贝叶斯分类模型的性能进行比较。仿真实验表明，DLB分类模型在垃圾邮件过滤应用中的效果在大部分条件下优于朴素的贝叶斯分类模型。     

A Dynamic Load Balancing Mechanism for Distributed Systems

It is desirable in a distributed system to have the system load balanced evenly among the nodes so that the mean job response time is minimized.In this paper,we present a dynamic load balancing mechanism(DLB).It adopts a cntralized approach and is network topology independent.The DLB mechanism employs a set of threscholds which are automatically adjusted as the system load changes.It also provides a simple mechanism for the system to switch between periodic and instantaneous load balancing policies with ease.The performance of the proposed algorithm is evaluated by intensive simulations for various parameters.Te simulation results show that the mean job response time in a system implementing DLB algorithm is significantly lower than the same system without load balancings.Furthermore,compared with a previously proposed algorithm,DLB algorithm demonstrates improved performance,especially when the system is heavily loaded and the load is unevenly distributed.     

Strategies for dynamic load balancing on highly parallel computers

Dynamic load balancing strategies for minimizing the execution time of single applications running in parallel on multicomputer systems are discussed. Dynamic load balancing (DLB) is essential for the efficient use of highly parallel systems when solving non-uniform problems with unpredictable load estimates. With the evolution of more highly parallel systems, centralized DLB approaches which make use of a high degree of knowledge become less feasible due to the load balancing communication overhead. Five DLB strategies are presented which illustrate the tradeoff between 1) knowledge - the accuracy of each balancing decision, and 2) overhead - the amount of added processing and communication incurred by the balancing process. All five strategies have been implemented on an Inter iPSC/2 hypercube     

大规模并行粒子模拟中基于主从架构的负载平衡策略研究与实现

粒子方法作为一种直观而且普适的模拟方法,在化工、材料、生物等领域得到了广泛的应用。本文采用主从(Master／Slave)并行模型,基于正交递归对分法(recursive coordinate bisection,RCB)和规则网格,设计出一种适用于具有多种复杂粒子的粒子系统并行模拟的负载平衡方法。应用该方法,在集群系统上采用离散元方法模拟了某钢铁公司滚筒系统。模拟采用4个节点,根据是否利用负载平衡模块分别进行测试,计算结果分析表明采用本文的负载平衡策略,计算效率提高了约14％。本文的算法具有较好的通用性,可以方便地应用于其它粒子方法的大规模并行计算问题。     

A Fuzzy Neural Network Based Dynamic Data Allocation Model on Heterogeneous Multi-GPUs for Large-scale Computations

The parallel computation capabilities of modern graphics processing units (GPUs) have attracted increasing attention from researchers and engineers who have been conducting high computational throughput studies. However, current single GPU based engineering solutions are often struggling to fulfill their real-time requirements. Thus, the multi-GPU-based approach has become a popular and cost-effective choice for tackling the demands. In those cases, the computational load balancing over multiple GPU “nodes” is often the key and bottleneck that affect the quality and performance of the real-time system. The existing load balancing approaches are mainly based on the assumption that all GPU nodes in the same computer framework are of equal computational performance, which is often not the case due to cluster design and other legacy issues. This paper presents a novel dynamic load balancing (DLB) model for rapid data division and allocation on heterogeneous GPU nodes based on an innovative fuzzy neural network (FNN). In this research, a 5-state parameter feedback mechanism defining the overall cluster and node performance is proposed. The corresponding FNN-based DLB model will be capable of monitoring and predicting individual node performance under different workload scenarios. A real-time adaptive scheduler has been devised to reorganize the data inputs to each node when necessary to maintain their runtime computational performance. The devised model has been implemented on two dimensional (2D) discrete wavelet transform (DWT) applications for evaluation. Experiment results show that this DLB model enables a high computational throughput while ensuring real-time and precision requirements from complex computational tasks.     

Scalable and dynamically balanced shared-everything OLTP with physiological partitioning

Scaling the performance of shared-everything transaction processing systems to highly parallel multicore hardware remains a challenge for database system designers. Recent proposals alleviate locking and logging bottlenecks in the system, leaving page latching as the next potential problem. To tackle the page latching problem, we propose physiological partitioning (PLP). PLP applies logical-only partitioning, maintaining the desired properties of sharedeverything designs, and introduces a multi-rooted B+Tree index structure (MRBTree) that enables the partitioning of the accesses at the physical page level. Logical partitioning and MRBTrees together ensure that all accesses to a given index page come from a single thread and, hence, can be entirely latch free; an extended design makes heap page accesses thread private as well. Moreover, MRBTrees offer an infrastructure for easy repartitioning and allow us to have a lightweight dynamic load balancing mechanism (DLB) on top of PLP. Profiling a PLP prototype running on different multicore machines shows that it acquires 85 and 68%fewer contentious critical sections, respectively, than an optimized conventional design and one based on logical-only partitioning. PLP also improves performance up to almost 50 % over the existing systems, while DLB enhances the system with rapid and robust behavior in both detecting and handling load imbalances.     

MF-DLB: Multimetric forwarding and directed acyclic graph-based load balancing for geographic routing in FANETs

Flying ad hoc network (FANET) comprising unmanned aerial vehicles (UAVs) emerges as a promising solution for numerous military and civil applications. Transferring data collected from the environment to the ground station (GS) is a primary concern for meeting the communication demands of most of these applications. However, the highly mobile UAVs with limited communication range, resulting in frequent topology change and intermittent connectivity, make data routing challenging. In such scenarios, geographic routing is a viable solution due to its scalability and robustness. However, the basic forwarding mechanism of geographic routing favors the neighboring UAV nearest to the destination, impacted substantially by link failures and routing holes in a dynamic environment. Additionally, routing decisions ignoring the current load over UAVs contribute to performance degradation due to the high concentration of data traffic near the GS. Thus, to address these issues, a geographic routing protocol named MF-DLB comprising multimetric forwarding (MF) and a directed acyclic graph-based load balancing (DLB) scheme is proposed to enhance packet forwarding in FANETs. MF takes account of multiple metrics related to connectivity, geographic progress, link lifetime, and residual energy to select the next hop with a stable communication link while effectively bypassing the routing holes. The second scheme, DLB, focuses on proactively maintaining routing paths near GS for load distribution among underutilized nodes to address the congestion problem. Simulations performed in network simulator ns-3 confirm the outperformance of MF-DLB over other related routing schemes in terms of different performance metrics.     

基于混合预测模型的VBR流拥塞控制机制

针对VBR多媒体流量的数字特征,在混合网络流量预测模型的基础上,结合小波分析和卡尔曼滤波,提出一种多媒体流自适应带宽分配算法,以合理分配网络带宽,利用双重漏桶控制网络流量。在NS网络仿真平台上进行的仿真实验表明,该算法能有效避免网络拥塞,降低网络传输时延和数据丢包率,提高带宽利用率。     

Standard-independent I/Q imbalance estimation and compensation scheme inOFDM

Direct-conversion transceivers are gaining increasing attention due to their low power consumption. However, they suffer from a serious in- and quadrature-phase (I/Q) imbalance problem. The I/Q imbalance can severely limit the achievable operating signal-to-noise ratio (SNR) at the receiver and, consequently, the supported constellation sizes and data rates. In this paper, we first investigate the effects of I/Q imbalance on orthogonal frequency division multiplexing (OFDM) receivers, and then propose a new I/Q imbalance compensation scheme. In the proposed method, a new statistic, which is robust against channel distortion, is used to estimate the I/Q imbalance parameters, and then the I/Q imbalance is corrected in the frequency domain. Simulations are performed to verify the effectiveness of the proposed method for I/Q imbalance compensation. The results show that the proposed I/Q imbalance compensation method can achieve bit error rate (BER) performance close to that in the ideal case without I/Q imbalance in additive white Gaussian noise (AWGN) or multipath environments. Furthermore, because no pilot information is required, this method can be applied in various standard communication systems.     

并行分治计算中的一种Work-stealing策略

在机群尤其是共享式多用户机群环境中提高非规则问题的并行计算效率是一项具有挑战性的工作.给出了一种适于多核处理器节点构成的机群的层次Work-stealing负载均衡策略(简称HWS),它能够有效利用节点的动态变化的可用计算资源.分析了分治计算问题中的动态性与非规则性,并使用HWS策略对分治计算问题进行了动态负载均衡(DLB)实验.实验表明,HWS在加速比、CPU利用率和负载分布等性能指标上均优于Work-sharing和Satin-CRS策略.     

弹用速率积分陀螺浮子静平衡方法研究

根据速率积分陀螺浮子的结构特点,提出用陀螺在 IA和-IA位置的零位电压之差与陀螺在 SA和-SA位置的零位电压之差来控制激光去重仪在浮子IA轴向和SA轴向的光照电流,使浮子达到完全静平衡状态的闭环工作平衡法;并采用减小力矩器刻度因数来提高浮子的静平衡精度.这种方法的平衡精度高于传统方法1～2个数量级,且平衡效率高、一致性好.     

QPSK信号IQ不平衡的角度统计盲补偿方法

针对直接变频接收机四相相移键控( QPSK) 信号的 IQ 不平衡问题,提出了一种角度统计的盲补偿方法。首先利用仿射坐标变换理论建立了实际的 IQ 信号与理想 IQ 信号的坐标旋转以及伸缩关系,然后通过坐标旋转的角度统计方法进行 IQ 不平衡系数的估计,从而实现 QPSK 信号的 IQ 不平衡补偿。仿真实验表明,相比其他的 IQ 不平衡盲补偿算法,该方法在降低误码率( BER) 的同时,减少了计算复杂度。     

A multivariate strategy to measure and test global imbalance in observational studies

This paper presents the development of the data driven approach first introduced in Camillo and D’Attoma (2010) and D’Attoma (2009), which enabled one to obtain a global measure of comparability between treatment groups within a non-experimental framework. This paper points to better formalize the global measure of imbalance reported in Camillo and D’Attoma (2010) and D’Attoma (2009) and to introduce a multivariate imbalance test. We consider the global measure of imbalance and the multivariate imbalance test as tools for investigating the dependence relationship between categorical covariates and the assignment-to-treatment indicator variable within a more complex strategy whose final aim is to find balanced groups. We will show in simulated data how the strategy works in practice.     

Effects of natural posture imbalance on posture deviation caused by load carriage

PurposeThe purpose of this study was to explore posture deviation variability caused by load carriages depending on natural posture imbalance to provide information about a carrying habit exaggerating an individual's posture imbalance. All people exhibit some imbalance from the standard anatomical pose which assumes alignment with the frontal and median planes. In this study natural posture imbalance is the starting point for determining posture deviation which is posture imbalance resulting from an activity, carrying an item.MethodsSeventeen female participants, 19–37 years old, were recruited from university staff, faculty members, and students. Participants were each scanned wearing their own underwear (bra and panties) in: (a) the anatomical pose (P1) face forward and feet placed at shoulder width without carrying an item, (b) carrying a backpack (P2), (c) carrying a shoulder bag on the right shoulder (P3R) and the left shoulder (P3L), (d) carrying a bag cross-body with a strap placed on the left shoulder to place the weight at the hip level on the right side (P4R) and the strap and handbag placed in the opposite direction (P4L), and (e) carrying a bag with the right hand (P5R) and the left hand (P5L). The bag weight was approximately 10% of a participant's body weight. Five body angles were obtained in each scanning position (eight positions total) for all participants and statistical analyses were conducted for posture assessment. Three statistical test methods were used: (a) Paired t-test to determine posture changes in each loaded position compared to natural posture in P1. (b) Paired t-test to identify differences of the degree of posture changes between right-side load (R) and left-side load (L) positions to determine a posture deviation tendency with asymmetrical load carriages. (c) Bivariate (Pearson) correlation test to examine how natural posture imbalance and posture deviation co-vary.Results(a) Asymmetrical load positions exhibited greater changes on shoulder and spine posture than a symmetrical load position, exhibiting obvious changes in P3 and P4 rather than P5. (b) The degrees and directions of posture deviation resulting from an asymmetrical load carriage varied depending on those of an individual's natural posture imbalance. When a participant exhibited great posture imbalance in P1, significant differences of posture deviation on the shoulder and spine between R and L positions were observed in P3 and P4. (c) Significant correlations between natural posture imbalance and posture deviation resulting from load carriages were found for most body angles.ConclusionsPeople need to be aware of their natural posture imbalance and try to avoid carrying heavy handbags or any type of carriages making their posture imbalance worse to prevent possible further distortion.Relevance to IndustryAlthough this study used handbags and a backpack as the load carrying devices, the way a person carries a load of any type is relevant in many industries and in the military.