Simulation Execution Time Research Articles

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

Agent scheduling model for adaptive dynamic load balancing in agent-based distributed simulations

Agent-based distributed simulations are confronted with load imbalance problem, which significantly affects simulation performance. Dynamic load balancing can be effective in decreasing simulation execution time and improving simulation performance. The characteristics of multi-agent systems and time synchronization mechanisms make the traditional dynamic load balancing approaches not suitable for dynamic load balancing in agent-based distributed simulations. In this paper, an adaptive dynamic load balancing model in agent-based distributed simulations is proposed. Due to the complexity and huge time consuming for solving the model, a distributed approximate optimized scheduling algorithm with partial information (DAOSAPI) is proposed. It integrates the distributed mode, approximate optimization and agent set scheduling approach. Finally, experiments are conducted to verify the efficiency of the proposed algorithm and the simulation performance under dynamic agent scheduling. The experiments indicate that DAOSPI has the advantage of short execution time in large-scale agent scheduling, and the distributed simulation performance under this dynamic agent scheduling outperforms that under static random agent distribution.

Performance prediction of ocean color Monte Carlo simulations using multi-layer perceptron neural networks

A performance modeling method is presented to predict the execution time of a parallel Monte Carlo (MC) radiative transfer simulation code for ocean color applications. The execution time of MC simulations is predicted using a multi-layer perceptron (MLP) neural network regression model trained with past execution time measurements in different execution environments and simulation cases. On the basis of the MLP performance model, a complementary job-environment mapping algorithm enables an efficient utilization of available high-performance computing resources minimizing the total execution time of the simulation jobs distributed in multiple environments.

Decreasing Communication Latency through Dynamic Measurement, Analysis, and Partitioning for Distributed Virtual Simulations

Communication in distributed simulations is highly relevant due to latencies cumulatively introduced in the execution time of such simulations; these latencies are caused by the transfer of data throughout networks. High-Level Architecture (HLA) is a well-known standard used to organize and keep the consistency of distributed virtual simulations. Nevertheless, although the HLA framework presents solutions to decrease communication overhead for simulations, it does not solve the communication issues that are pertinent to the network distances among federates and the Run-Time Infrastructure (RTI) in large-scale environments. Due to the relevance of load balancing for distributed simulations, many solutions have been proposed, but such approaches just consider communication load partially in their schemes or are limited. To minimize the communication overhead of HLA distributed simulations, a hierarchical dynamic balancing scheme composed of three phases was designed; however, even though the balancing scheme reacts properly to run-time load changes, its load analysis does detect all the imbalances after measuring simulations' communication load. Thus, an extension is proposed to improve the detection of communication imbalances, as well as the redistribution of federates, so the balancing scheme can better react to communication load measurements gathered from each federate. To observe the benefits of the proposed communication balancing scheme and its extension, extensive large-scale experiments were realized. The results show that the scheme reduces considerably the amount of communication overhead, and the extension enables the detection of communication imbalances by modifying the decision-making technique in the balancing system.

Improving decision making in healthcare services through the use of existing simulation modelling tools and new technologies

PurposeThe purpose of this paper is to investigate the viability of using distributed simulation to execute large and complex healthcare simulation models which help government take informed decisions.Design/methodology/approachThe paper compares the execution time of a standalone healthcare supply chain simulation with its distributed counterpart. Both the standalone and the distributed models are built using a commercial simulation package (CSP).FindingsThe results show that the execution time of the standalone healthcare supply chain simulation increases exponentially as the size and complexity of the system being modelled increases. On the other hand, using distributed simulation approach decreases the run time for large and complex models.Research limitations/implicationsThe distributed approach of executing different parts of a single simulation model over different computers is only viable when the model: can be divided into logical parts and the exchange of information between these parts occurs at constant simulated time intervals; is sufficiently large and complicated, such that executing the model over a single processor is very time consuming.Practical implicationsBased on a feasibility study of the UK National Blood Service we demonstrate the effectiveness of distributed simulation and argue that it is a vital technique in healthcare informatics with respect to supporting decision making in large healthcare systems.Originality/valueTo the best of the knowledge, this is the first feasibility study in healthcare which shows the outcome of modelling and executing a distributed simulation using unmodified CSPs and a software/middleware for distributed simulation.

Automatic Partitioning of Large Scale Simulation in Grid Computing for Run Time Reduction

Simulating large-scale systems usually entails exhaustive computational powers and lengthy execution times. The goal of this research is to reduce execution time of large-scale simulations without sacrificing their accuracy by partitioning a monolithic model into multiple pieces automatically and executing them in a distributed computing environment. While this partitioning allows us to distribute required computational power to multiple computers, it creates a new challenge of synchronizing the partitioned models. In this article, a partitioning methodology based on a modified Prim’s algorithm is proposed to minimize the overall simulation execution time considering 1) internal computation in each of the partitioned models and 2) time synchronization between them. In addition, the authors seek to find the most advantageous number of partitioned models from the monolithic model by evaluating the tradeoff between reduced computations vs. increased time synchronization requirements. In this article, epoch- based synchronization is employed to synchronize logical times of the partitioned simulations, where an appropriate time interval is determined based on the off-line simulation analyses. A computational grid framework is employed for execution of the simulations partitioned by the proposed methodology. The experimental results reveal that the proposed approach reduces simulation execution time significantly while maintaining the accuracy as compared with the monolithic simulation execution approach.

Large-Scale Integrated Network System Simulation with DEVS-Suite

Formidable growth of Internet technologies has revealed challenging issues about its scale and performance evaluation. Modeling and simulation play a central role in the evaluation of the behavior and performance of the large-scale network systems. Large numbers of nodes affect simulation performance, simulation execution time and scalability in a weighty manner. Most of the existing simulators have numerous problems such as size, lack of system theoretic approach and complexity of modeled network. In this work, a scalable discrete-event modeling approach is described for studying networks’ scalability and performance traits. Key fundamental attributes of Internet and its protocols are incorporated into a set of simulation models developed using the Discrete Event System Specification (DEVS) approach. Large-scale network models are simulated and evaluated to show the benefits of the developed network models and approaches.

AN ADAPTIVE DYNAMIC LOAD BALANCING TECHNIQUE FOR GRID-BASED LARGE SCALE DISTRIBUTED SIMULATIONS

Dynamic load balancing is a key factor in achieving high performance for large scale distributed simulations on grid infrastructures. In a grid environment, the available resources and the simulation's computation and communication behavior may experience critical run-time imbalances. Consequently, an initial static partitioning should be combined with a dynamic load balancing scheme to ensure the high performance of the distributed simulation. In this paper, we propose a dynamic load balancing scheme for distributed simulations on a grid infrastructure. Our scheme is composed of an online network analyzing service coupled with monitoring agents and a run-time model repartitioning service. We present a hierarchical scalable adaptive JXTA service based scheme and use simulation experiments to demonstrate that our proposed scheme exhibits better performance in terms of simulation execution time. Furthermore, we extend our algorithm from a local intra-cluster algorithm to a global inter-cluster algorithm and we consider the proposed global design through a formalized Discrete Event System Specification (DEVS) model system

Application of a Reduced Method in Compositional Simulation

Summary Simulating gas-injection processes requires a compositional model to predict the fluid properties resulting from mass transfer between reservoir fluid and injection gas. A drawback of compositional simulation is the efficiency and robustness of phase equilibrium calculations. Reduced methods for phase equilibrium calculations have been studied as a potential solution to improve the efficiency of compositional simulation. However, most of those studies have been performed only in standalone calculations, and the robustness and efficiency of a reduced method has not been confirmed in compositional simulation. In this research, we develop a robust and efficient algorithm for a reduced method and validate it in compositional simulation. We examine the efficiency and convergence property of the conventional algorithm for a reduced method and solve several implementation problems in a compositional simulator. The reduced method is implemented in UTCOMP, a compositional implicit-pressure/explicit concentration (IMPEC) simulator, to demonstrate the performance for various numbers of components and degrees of miscibility. The results show that the reduced method enables significant savings in execution time of compositional simulation without loss of accuracy compared to standard methods. Also, we observe that the reduced method exhibits improved robustness, especially for miscible processes where composition paths go near critical regions.

Multi-Level Parallelism for the Cardiac Bidomain Equations

Cardiovascular diseases are associated with high mortality rates in the globe. The development of new drugs, new medical equipment and non-invasive techniques for the heart demand multidisciplinary efforts towards the characterization of cardiac anatomy and function from the molecular to the organ level. Computational modeling has demonstrated to be a useful tool for the investigation and comprehension of the complex biophysical processes that underlie cardiac function. The set of Bidomain equations is currently one of the most complete mathematical models for simulating the electrical activity in cardiac tissue. Unfortunately, large scale simulations, such as those resulting from the discretization of an entire heart, remain a computational challenge. In order to reduce simulation execution times, parallel implementations have traditionally exploited data parallelism via numerical schemes based on domain-decomposition. However, it has been verified that the parallel efficiency of these implementations severely degrades as the number of processors increases. In this work we propose and implement a new parallel algorithm for the solution of cardiac models. By relaxing the coherence of the execution, a new level of parallelism could be identified and exploited: pipelining. A synchronous parallel algorithm that uses both pipelining and data decomposition techniques was implemented and used the MPI library for communication. Numerical tests were performed in two different cluster configurations. Our preliminary results indicated that the proposed algorithm is able to increase the parallel efficiency up to 20% on an 8-core cluster. On a 32-core cluster the multi-level algorithm was 1.7 times faster than the traditional domain decomposition algorithm. In addition, the numerical precision was kept under control (relative errors under 6%) when the relaxed coherence execution was adopted.

Numerical studies of methane production from Class 1 gas hydrate accumulations enhanced with carbon dioxide injection

Class 1 gas hydrate accumulations are characterized by a permeable hydrate-bearing interval overlying a permeable interval with mobile gas, sandwiched between two impermeable intervals. Depressurization-induced dissociation is currently the favored technology for producing gas from Class 1 gas hydrate accumulations. The depressurization production technology requires heat transfer from the surrounding environment to sustain dissociation as the temperature drops toward the hydrate equilibrium point and leaves the reservoir void of gas hydrate. Production of gas hydrate accumulations by exchanging carbon dioxide with methane in the clathrate structure has been demonstrated in laboratory experiments and proposed as a field-scale technology. The carbon dioxide exchange technology has the potential for yielding higher production rates and mechanically stabilizing the reservoir by maintaining hydrate saturations. We used numerical simulation to investigate the advantages and disadvantages of using carbon dioxide injection to enhance the production of methane from Class 1 gas hydrate accumulations. Numerical simulations in this study were primarily concerned with the mechanisms and approaches of carbon dioxide injection to investigate whether methane production could be enhanced through this approach. To avoid excessive simulation execution times, a five-spot well pattern with a 500-m well spacing was approximated using a two-dimensional domain having well boundaries on the vertical sides and impermeable boundaries on the horizontal sides. Impermeable over- and under burden were included to account for heat transfer into the production interval. Simulation results indicate that low injection pressures can be used to reduce secondary hydrate formation and that direct contact of injected carbon dioxide with the methane hydrate present in the formation is limited due to bypass through the higher permeability gas zone.

확률 모델을 이용한 미사일 경고 레이다의 효과도 분석

미사일 경고 레이다의 위협 판단 성능을 분석하기 위해서는 과대응률/미대응률 측면에서 얼마나 효과적으로 위협을 판단하는지를 분석해야 한다. 이러한 효과도 분석을 위해 Monte-Carlo 기법을 이용하여 시뮬레이션을 수행해 왔으나 시뮬레이션 수행 시간이 많이 걸리는 단점이 있었다. 본 논문에서는 단점을 보완하기 위해 확률 모델을 이용한 효과도 분석 기법을 제안하였다. 확률 모델을 설정하는 방법과 실제 시뮬레이션을 통해 전차에 장착한 레이다의 효과도를 분석한 결과를 보인다. 또한, Monte-Carlo 기법과 제안하는 확률 모델 이용 기법에 대한 시뮬레이션 수행 시간의 비교 결과를 제시하고자 한다. To analyze the threat decision performance of MWR(Missile Warning Radar) give analysis on condition that we decide the effective threat using the POC(Probability of Over Countermeasure)/PUC(Probability of Under Countermeasure). Thus, we execute the simulation using the Monte-Carlo method to analyze effect, but the execution time of simulation took longer than we expected. In this paper, the effect analysis is proposed using the probability model to reduce the execution time of simulation. We present the setting method of parameter for probability model and the effect analysis result of MWR using the simulation. Also, we present the comparison result of simulation execution time for Monte-Carlo and probability model.

Facilitating the Analysis of a UK National Blood Service Supply Chain Using Distributed Simulation

In an attempt to investigate blood unit ordering policies, researchers have created a discrete-event model of the UK National Blood Service (NBS) supply chain in the Southampton area of the UK. The model has been created using Simul8, a commercial off-the-shelf (COTS) discrete-event simulation package (CSP). However, as more hospitals were added to the model, it was discovered that the length of time needed to perform a single simulation severely increased. It has been claimed that distributed simulation, a technique that uses the resources of many computers to execute a simulation model, can reduce simulation runtime. Further, an emerging standardized approach exists that supports distributed simulation with CSPs. These CSP Interoperability (CSPI) standards are compatible with the IEEE 1516 standard, the High Level Architecture (HLA), the de facto interoperability standard for distributed simulation. To investigate if distributed simulation can reduce the execution time of NBS supply chain simulation, this paper presents experiences of creating a distributed version of the CSP Simul8 according to the CSPI/HLA standards. It shows that the distributed version of the simulation does indeed run faster when the model reaches a certain size. Further, we argue that understanding the relationship of model features is key to performance. This is illustrated by experimentation with two different protocols implementations (using Time Advance Request (TAR) and Next Event Request (NER)). Our contribution is therefore the demonstration that distributed simulation is a useful technique in the timely execution of supply chains of this type and that careful analysis of model features can further increase performance.

Fully dynamic epoch time synchronisation method for distributed supply chain simulation

A dynamic epoch time synchronisation method for distributed simulation federates is presented. The proposed approach allows federates to advance their local times at full speed to the global safe point, which is dynamically estimated using the look-ahead function for each federate. The simulation then slows for an interaction between federates. This approach aims to reduce the number of time synchronisation occurrences and duration of the conservative phase. The distributed simulation is implemented using the web services technology. The experimental results reveal that the proposed approach reduces simulation execution time significantly while maintaining complete accuracy as compared with two existing methods.

Simulating electrical faults within future aircraft networks

There is a growing need for accurate and time efficient modelling of electrical distribution networks within the aerospace industry, for which power electronic converters are an integral part. Simplifying converter models is necessary to improve simulation execution times, however many existing techniques do not necessarily give accurate results for all types of system level studies. This paper describes an alternative modelling approach to these, which provides accurate results and reduced simulation times for studies of electrical fault analyses.

Large-Scale Sensor Networks Simulation with GTSNetS

This paper presents a highly scalable sensor network simulation environment that allows users to evaluate the effects of different architectural choices and strategies on the lifetime and performance of a sensor network. This tool can also be used to evaluate new approaches (e.g., routing protocols, cooperation algorithms), and compare them with the ones already in place. The simulator incorporates models for the different functional units composing a sensor node and characterizes the energy consumption of each. GTSNetS is designed in a modular and efficient way favoring the ease of use and extension. The simulator also allows the user to choose from different implementations of energy models, accuracy models, communication protocols, application classes and types of sensors. New models can be easily added if necessary. Simulation results from a set of tests are reported to demonstrate some of the capabilities of the simulator. We present a case study using our tool to measure the performance of an existing algorithm that provides fault-tolerance for distributed detection using a wireless sensor network. The simulator gives results that are in accordance with the ones reported in the original paper describing the simulated algorithm. Tests were also performed to evaluate the simulator scalability as the network size increases. In particular, it was found that this tool could simulate sensor networks of several hundred thousand nodes while using less than 2 GB of memory, which exceeds the capabilities of existing simulators by an order of magnitude. The simulation execution time also scales well with the network size.

Conservative Wetting and Drying Methodology for Quadrilateral Grid Finite-Volume Models

Algebraic equations relating fluid volume and the free surface elevation in partially wetted quadrilateral computational cells are derived and incorporated into a Godunov-type, finite-volume, shallow-water model. These equations make it straightforward to reconstruct the free surface elevation based on the volume of fluid in a computational cell, the dependent variable tracked by finite volume models for conservation purposes, regardless of whether the cell is fully or partially wetted. Improvements to the variable reconstruction process streamline the computation of mass and momentum fluxes with approximate Riemann solvers, yielding a model that simulates sub-, super-, and transcritical flows over irregular topography with wetting and drying fronts. Furthermore, the model is free from fluid and scalar mass conservation errors and it eliminates nonphysical distributions of scalars by avoiding artificial concentration and/or dilution at wet/dry interfaces. Use of this wetting and drying methodology adds roughly 10% to the execution time of flow simulations.

Accelerating Missile Threat Simulations Using Personal Computer Graphics Cards

The authors use inexpensive personal computer graphics cards to perform the intensive image-processing computations done in a heat-seeking missile’s tracking systems and thereby dramatically reduce the execution time of missile threat simulations used by military mission planners. Using an innovative processing algorithm, these calculations are accomplished up to 3.5 times faster in graphic cards versus using a conventional CPU. Through a combination of this and other software optimizations, simulation time was reduced by 33%.

A Linux cluster of personal computers for the numerical simulation of natural airflows in greenhouses using a lattice model

Some numerical models need a considerable computational effort to run their simulations. This fact is translated into long execution times delaying the decisions that have to be taken by the modeller in order to obtain the best phenomena description. This situation is also frequent in agronomical modelling, particularly when the subject of study is the fluid flow pattern as happens when simulating the natural airflows in a greenhouse. The knowledge of the effects of different ventilator configurations allows the crop manager to improve the greenhouse's natural ventilation conditions. In this work, a Linux cluster of 10 personal computers (PC) is proposed with the aim of reducing the execution time of the lattice model simulations by means of parallel computing. This model has been used for describing fluid flow patterns in the presence of solid obstacles since the 1990s. The lattice model structure makes them suitable for a straightforward parallel computing implementation. As Jiménez-Hornero et al. [Jiménez-Hornero, F.J., Gutierrez de Ravé, E., Hidalgo, R., Giráldez, J.V., 2005. Numerical study of the natural airflow in greenhouses using a two-dimensional lattice model. Biosyst. Eng. 91, 219–228] show, this model is suitable for simulating the two-dimensional natural airflow in the vertical cross-section of a tropical crop protection structure described by Montero et al. [Montero, J.I., Hunt, G.R., Kamaruddin, R., Antón, A., Bailey, B.J., 2001. Effect of ventilator configuration on wind-driven ventilation in a crop protection structure for the tropics. J. Agric. Eng. Res. 80, 99–107]. The performance metrics clearly show the benefit of using the proposed Linux PC cluster in terms of execution time reduction and speedup with respect to the sequential running in a single PC.

Optimistic Simulations of Physical Systems Using Reverse Computation

Efficient computer simulation of complex physical phenomena has long been challenging due to their multiphysics and multiscale nature. In contrast to traditional time-stepped execution methods, the authors describe an approach using optimistic parallel discrete event simulation (PDES) and reverse computation techniques to execute plasma physics codes. They show that reverse computation-based optimistic parallel execution can significantly reduce the execution time of an example plasma simulation without requiring a significant amount of additional memory compared to conservative execution techniques. The authors describe an application-level reverse computation technique that is efficient and suitable for complex scientific simulations.