A parallel scheme for accelerating parameter sweep applications on a GPU

This paper proposes a parallel scheme for accelerating parameter sweep applications on a graphics processing unit. By using hundreds of cores on the graphics processing unit, we found that our scheme simultaneously processes multiple parameters rather than a single parameter. The simultaneous sweeps exploit the similarity of computing behaviors shared by different parameters, thus allowing memory accesses to be coalesced into a single access if similar irregularities appear among the parameters’ computational tasks. In addition, our scheme reduces the amount of off‐chip memory access by unifying the data that are commonly referenced by multiple parameters and by placing the unified data in the fast on‐chip memory. In several experiments, we applied our scheme to practical applications and found that our scheme can perform up to 8.5 times faster than a naive scheme that processes a single parameter at a time. We also include a discussion on application characteristics that are required for our scheme to outperform the naive scheme. Copyright © 2013 John Wiley & Sons, Ltd.     

Performance modeling of parallel applications for grid scheduling

Grids consist of both dedicated and non-dedicated clusters. For effective mapping of parallel applications on grid resources, a grid metascheduler has to evaluate different sets of resources in terms of predicted execution times for the applications when executed on the sets of resources. In this work, we have developed a comprehensive set of performance modeling strategies for predicting execution times of parallel applications on both dedicated and non-dedicated environments. Our strategies adapt to changing network and CPU loads on the grid resources. We have evaluated our strategies on 8, 16, 24 and 32-node clusters with random loads and load traces from a grid system. Our strategies give less than 30% average percentage prediction errors in all cases, which, to our knowledge, is the best reported for non-dedicated environments. We also found that grid scheduling using predictions of execution times from our performance modeling techniques will lead to perfect mapping of applications to resources in many cases.     

Management of a parameter sweep for scientific applications on cluster environments

The GEOsciences Network (GEON, www.geongrid.org ) is a large‐scale collaborative cyberinfrastructure project involving information technology and geoscience researchers from multiple institutions. The GEON infrastructure provides portal, middleware, and data resources to facilitate scientific discovery for domain scientists using applications, tools, and services. It consists of both a service‐oriented Web/Grid framework and application toolkits, using the Web service and portlet programming model to represent applications. Based on those grid environments, we have developed the SYNSEIS (SYNthetic SEISmogram) tool within the GEON infrastructure to support personalized experiments in seismology. In this paper, we present an overview of SYNSEIS from a user point of view, and demonstrate how one can use a simple management scheme to perform a parameter sweep and distribute the work in computational resources, using a scientific application that was not specifically designed to perform parameter sweeps. The performance advantages to be gained by using this scheme with scientific codes for dealing with a large number of jobs on computational grids are very substantial. In particular, we identify the earthquake simulations in the SYNSEIS tool as an example application that can benefit from running jobs on computational resources and subsequently promote the sharing of computational resources among partner sites involved in the GEON project. Finally, we also discuss the parallel scaling behavior of our primary earthquake simulation application. Copyright © 2010 John Wiley & Sons, Ltd.     

Particle filters for state and parameter estimation in batch processes

In process engineering, on-line state and parameter estimation is a key component in the modelling of batch processes. However, when state and/or measurement functions are highly non-linear and the posterior probability of the state is non-Gaussian, conventional filters, such as the extended Kalman filter, do not provide satisfactory results. This paper proposes an alternative approach whereby particle filters based on the sequential Monte Carlo method are used for the estimation task. Particle filters are initially described prior to discussing some implementation issues, including degeneracy, the selection of the importance density and the number of particles. A kernel smoothing approach is introduced for the robust estimation of unknown and time-varying model parameters. The effectiveness of particle filters is demonstrated through application to a benchmark batch polymerization process and the results are compared with the extended Kalman filter.     

Large improvements in application throughput of long‐running multi‐component applications using batch grids

Computational grids with multiple batch systems (batch grids) can be powerful infrastructures for executing long‐running multi‐component parallel applications. In this paper, we evaluate the potential improvements in throughput of long‐running multi‐component applications when the different components of the applications are executed on multiple batch systems of batch grids. We compare the multiple batch executions with executions of the components on a single batch system without increasing the number of processors used for executions. We perform our analysis with a foremost long‐running multi‐component application for climate modeling, the Community Climate System Model (CCSM). We have built a robust simulator that models the characteristics of both the multi‐component application and the batch systems. By conducting large number of simulations with different workload characteristics and queuing policies of the systems, processor allocations to components of the application, distributions of the components to the batch systems and inter‐cluster bandwidths, we show that multiple batch executions lead to 55% average increase in throughput over single batch executions for long‐running CCSM. We also conducted real experiments with a practical middleware infrastructure and showed that multi‐site executions lead to effective utilization of batch systems for executions of CCSM and give higher simulation throughput than single‐site executions. Copyright © 2011 John Wiley & Sons, Ltd.     

Performance of computationally intensive parameter sweep applications on Internet‐based Grids of computers: the mapping of molecular potential energy hypersurfaces

This work focuses on the use of computational Grids for processing the large set of jobs arising in parameter sweep applications. In particular, we tackle the mapping of molecular potential energy hypersurfaces. For computationally intensive parameter sweep problems, performance models are developed to compare the parallel computation in a multiprocessor system with the computation on an Internet‐based Grid of computers. We find that the relative performance of the Grid approach increases with the number of processors, being independent of the number of jobs. The experimental data, obtained using electronic structure calculations, fit the proposed performance expressions accurately. To automate the mapping of potential energy hypersurfaces, an application based on GRID superscalar is developed. It is tested on the prototypical case of the internal dynamics of acetone. Copyright © 2006 John Wiley & Sons, Ltd.     

Redesign of adaptive observers for improved parameter identification in nonlinear systems

We propose a method for redesigning adaptive observers for nonlinear systems. The redesign uses an adaptive law that is based on delayed observers. This increases the computational burden, but gives significantly better parameter identification and robustness properties. In particular, given that a special persistency of excitation condition is satisfied, we prove uniform global asymptotic stability and semi-global exponential stability of the origin of the state and parameter estimation error, and give explicit lower bounds on the convergence rate of both the state and parameter estimation error dynamics. For initial conditions with a known upper bound, we prove tunable exponential convergence rate. To illustrate the use of the proposed method, we apply it to estimate the unmeasured flow rate and the uncertain friction parameters in a model of a managed pressure drilling system. The simulation results clearly show the improved performance of the redesigned adaptive observer compared to a traditional design.     

Adaptive parameter identification of linear SISO systems with unknown time-delay

An adaptive online parameter identification is proposed for linear single-input-single-output (SISO) time-delay systems to simultaneously estimate the unknown time-delay and other parameters. After representing the system as a parameterized form, a novel adaptive law is developed, which is driven by appropriate parameter estimation error information. Consequently, the identification error convergence can be proved under the conventional persistent excitation (PE) condition, which can be online tested in this paper. A finite-time (FT) identification scheme is further studied by incorporating the sliding mode scheme into the adaptation to achieve FT error convergence. The previously imposed constraint on the system relative degree is removed and the derivatives of the input and output are not required. Comparative simulation examples are provided to demonstrate the validity and efficacy of the proposed algorithms.     

Real-time scheduling of batch systems using Petri nets and linear logic

This paper presents an approach to model, design and verify scenarios of real-time systems used in the scheduling and global coordination of batch systems. The initial requirements of a system specified with sequence diagrams are translated into a single p-time Petri net model representing the global behavior of the system. For the Petri net fragments involved in conflicts, symbolic production and consumption dates assigned to tokens are calculated based on the sequent calculus of linear logic. These dates are then used for off-line conflict resolution within a token player algorithm used for scenario verification of real-time specifications and which can be seen as a simulation tool for UML interaction diagrams.     

Optimal activation policies for continuous scanning observations in parameter estimation of distributed systems

The problem of determining an optimal measurement scheduling for identification of unknown parameters in distributed systems described by partial differential equations is discussed. The discrete-scanning observations are performed by an optimal selection of measurement data from spatially fixed sensors. In the adopted approach, the sensor scheduling problem is converted to a constrained optimal control problem. In this framework, the control value represents the selected sensor configuration. Thus the control variable is constrained to take values in a discrete set and switchings between sensors may occur in continuous time. By applying the control parameterization enhancing transform technique, a computational procedure for solving the optimal scanning measurement problem is obtained. The numerical scheme is then tested on a computer example regarding an advection-diffusion problem.     

Output regulation of nonlinear output feedback systems with exponential parameter convergence

This paper revisits the global robust output regulation (GROR) problem of nonlinear output feedback systems with uncertain exosystems by error output feedback control. The problem was conventionally tackled by employing a linear canonical internal model and as a result, suitable adaptive stabilization has to be done for the augmented system to achieve output regulation. Distinguished from that, a novel nonlinear internal model approach is developed in the present study that successfully converts the GROR problem into a robust non-adaptive stabilization problem for the augmented system. The feature of the new approach is two-fold. On one hand, stabilization of augmented system is disentangled from any extra adaptive control law and thus the procedure is simplified. On the other hand, it leads to explicit strict Lyapunov characterization for the closed-loop system and consequently assures exponential parameter convergence.     

Principles for designing data-/compute-intensive distributed applications and middleware systems for heterogeneous environments

The nature of distributed systems is constantly and steadily changing as the hardware and software landscape evolves. Porting applications and adapting existing middleware systems to ever changing computational platforms has become increasingly complex and expensive. Therefore, the design of applications, as well as the design of next generation middleware systems, must follow a set of guiding principles in order to insure long-term “survivability” without costly re-engineering. From our practical experience, the key determinants to success in this endeavor are adherence to the following principles: (1) Design for change; (2) Provide for storage subsystem I/O coordination; (3) Employ workload partitioning and load balancing techniques; (4) Employ caching; (5) Schedule the workload; and (6) Understand the workload. In order to support these principles, we have collected extensive experimental results comparing three middleware systems targeted at data- and compute-intensive applications implemented by our research group during the course of the last decade, on a single data- and compute-intensive application. The main contribution of this work is the analysis of a level playing field, where we discuss and quantify how adherence to these guiding principles impacts overall system throughput and response time.     

Comparisons among robust stability criteria for linear systems with affine parameter uncertainties

This paper is concerned with the problem of comparisons among robust stability criteria for a class of uncertain linear systems, where the system state matrices considered are affinely dependent on the uncertain parameters. At first, a robust stability criterion for the class of systems to be affinely quadratically stable (AQS) is derived based on the vertex separator approach, where affine parameter-dependent Lyapunov functions are exploited to prove stability. Then comparison results between the robust stability criterion and the existing tests for AQS are given in terms of degree of conservatism. A numerical example is given to illustrate the results.     

Methodology for predicting performance of distributed and parallel systems

This paper describes an accurate and efficient method to model and predict the performance of distributed/parallel systems. Various performance measures, such as the expected user response time, the system throughput and the average server utilization, can be easily estimated using this method. The methodology is based on known product form queueing network methods, with some additional approximations. The method is illustrated by evaluating performance of a multi-client multi-server distributed system. A system model is constructed and mapped to a probabilistic queueing network model which is used to predict its behavior. The effects of user think time and various design parameters on the performance of the system are investigated by both the analytical method and computer simulation. The accuracy of the former is verified. The methodology is applied to identify the bottleneck server and to establish proper balance between clients and servers in distributed/parallel systems.     

Analysis of threshold-based batch-service queueing systems with batch arrivals and general service times

Most research concerning batch-service queueing systems has focussed on some specific aspect of the buffer content. Further, the customer delay has only been examined in the case of single arrivals. In this paper, we examine three facets of a threshold-based batch-service system with batch arrivals and general service times. First, we compute a fundamental formula from which an entire gamut of known as well as new results regarding the buffer content of batch-service queues can be extracted. Second, we produce accurate light- and heavy-traffic approximations for the buffer content. Third, we calculate various quantities with regard to the customer delay. This paper thus provides a whole spectrum of tools to evaluate the performance of batch-service systems.     

Soft computing for scheduling with batch setup times and earliness-tardiness penalties on parallel machines

A model for scheduling grouped jobs on identical parallel machines is addressed in this paper. The model assumes that a set-up time is incurred when a machine changes from processing one type of component to a different type of component, and the objective is to minimize the total earliness-tardiness penalties. In this paper, the algorithm of soft computing, which is a fuzzy logic embedded Genetic Algorithm is developed to solve the problem. The efficiency of this approach is tested on several groups of random problems and shows that the soft computing algorithm has potential for practical applications in larger scale production systems.     

Set membership state and parameter estimation for systems described by nonlinear differential equations

This paper investigates the use of guaranteed methods to perform state and parameter estimation for nonlinear continuous-time systems, in a bounded-error context. A state estimator based on a prediction-correction approach is given, where the prediction step consists in a validated integration of an initial value problem for an ordinary differential equation (IVP for ODE) using interval analysis and high-order Taylor models, while the correction step uses a set inversion technique. The state estimator is extended to solve the parameter estimation problem. An illustrative example is presented for each part.     

Model-driven monitoring support for the multi-view performance analysis of parallel embedded applications

This paper describes an approach to carry out performance analysis of parallel embedded applications. The approach is based on measurement, but in addition, the idea of driving the measurement process (application instrumentation and monitoring) by a behavioral model is introduced. Using this model, highly comprehensible performance information can be collected. The whole approach is based on this behavioral model, one instrumentation method and two tools, one for monitoring and the other for visualization and analysis. Each of these is briefly described, and the steps to carry out performance analysis using them are clearly defined. They are explained by means of a case study. Finally, one method to evaluate the intrusiveness of the monitoring approach is proposed, and the intrusiveness results for the case study are presented.     

Industrial applications of type-2 fuzzy sets and systems: A concise review

Data, as being the vital input of system modelling, contain dissimilar level of imprecision that necessitates different modelling approaches for proper analysis of the systems. Numbers, words and perceptions are the forms of data that has varying levels of imprecision. Existing approaches in the literature indicate that, computation of different data forms are closely linked with the level of imprecision, which the data already have. Traditional mathematical modelling techniques have been used to compute the numbers that have the least imprecision. Type-1 fuzzy sets have been used for words and type-2 fuzzy sets have been employed for perceptions where the level of imprecision is relatively high. However, in many cases it has not been easy to decide whether a solution requires a traditional approach, i.e., type-1 fuzzy approach or type-2 fuzzy approach. It has been a difficult matter to decide what types of problems really require modelling and solution either with type-1 or type-2 fuzzy approach. It is certain that, without properly distinguishing differences between the two approaches, application of type-1 and type-2 fuzzy sets and systems would probably fail to develop robust and reliable solutions for the problems of industry. In this respect, a review of the industrial applications of type-2 fuzzy sets, which are relatively novel to model imprecision has been considered in this work. The fundamental focus of the work has been based on the basic reasons of the need for type-2 fuzzy sets for the existing studies. With this purpose in mind, type-2 fuzzy sets articles have been selected from the literature using the online databases of ISI-Web of Science, ScienceDirect, SpringerLink, Informaworld, Engineering Village, Emerald and IEEE Xplore. Both the terms “type-2 fuzzy” and “application” have been searched as the main keywords in the topics of the studies to retrieve the relevant works. The analysis on the industrial applications of type-2 fuzzy sets/systems (FSs) in different topics allowed us to summarize the existing research areas and therefore it is expected be useful to prioritize future research topics. This review shows that there are still many opportunities for application of type-2 FSs for several different problem domains. Shortcomings of type-1 FSs can also be considered as an opportunity for the application of type-2 FSs in order to provide a better solution approach for industrial problems.     

Combined parameter and output estimation of dual-rate systems using an auxiliary model

For a dual-rate sampled-data system, an auxiliary model based identification algorithm for combined parameter and output estimation is proposed. The basic idea is to use an auxiliary model to estimate the unknown noise-free output (true output) of the system, and directly to identify the parameters of the underlying fast single-rate model from the dual-rate input-output data. It is shown that the parameter estimation error consistently converges to zero under generalized or weak persistent excitation conditions and unbounded noise variance, and that the output estimates uniformly converge to the true outputs. An example is included.