Vehicular traffic simulations are useful in applications such as emergency management and homeland security planning tools. High speed of traffic simulations translates directly to speed of response and level of resil...
详细信息
ISBN:
(纸本)9780769531595
Vehicular traffic simulations are useful in applications such as emergency management and homeland security planning tools. High speed of traffic simulations translates directly to speed of response and level of resilience in those applications. Here, a parallel traffic simulation approach is presented that is aimed at reducing the time for simulating emergency vehicular traffic scenarios. Three unique aspects of this effort are: (1) exploration of optimistic simulation applied to vehicular traffic simulation (2) addressing reverse computation challenges speck to optimistic vehicular traffic simulation (3) achieving absolute (as opposed to self-relative) speedup with a sequential speed equal to that of a fast, de facto standard sequential simulator for emergency traffic. The design and development of the parallelsimulation system is presented, along with a performance study that demonstrates excellent sequential performance as well as parallel performance.
The modelling and simulation of autonomous pedestrians has important applications in real-time crowd and crisis simulations. With the increase in processing powers and dedicated graphics cards, more processing powers ...
详细信息
ISBN:
(纸本)9780769531595
The modelling and simulation of autonomous pedestrians has important applications in real-time crowd and crisis simulations. With the increase in processing powers and dedicated graphics cards, more processing powers can now be allocated for the generation of realistic behaviours for individuals within the crowd. We have proposed a representation for autonomous agents that is aimed to generate some human-like behaviours. In particular, to generate smooth and realistic navigational behaviour such as human-like collision avoidance, we have also proposed a two tier navigation model for autonomous agents. Using the proposed model, a scene in a typical shopping mall has been created. Behaviours such as crowd avoidance and lane following have been observed from the simulation.
We adapt a scalable layered intelligence technique from the game industry, for agent-based crowd simulation. We extend this approach for planned movements, pursuance of assignable goals, and avoidance of dynamically i...
详细信息
ISBN:
(纸本)9780769531595
We adapt a scalable layered intelligence technique from the game industry, for agent-based crowd simulation. We extend this approach for planned movements, pursuance of assignable goals, and avoidance of dynamically introduced obstacles/threats, while keeping the system scalable with the number of agents. We exploit parallel processing for expediting the pre-processing step that generates the path-plans offline. We demonstrate the various behaviors in a hall-evacuation scenario, and experimentally establish the scalability of the frame-rates with increasing number of agents.
We propose a new simulation method, called interval branching, which aims to facilitate efficient simulation studies of systems that involve temporal uncertainty. The method uses interval timestamps for events and exp...
详细信息
ISBN:
(纸本)9780769531595
We propose a new simulation method, called interval branching, which aims to facilitate efficient simulation studies of systems that involve temporal uncertainty. The method uses interval timestamps for events and explores different execution orders of overlapping events by branching the simulation. We first present a sequential version of interval branching, and then extend it to parallelsimulation using the logical process paradigm. The parallel interval branching algorithm uses the logical-process cloning technique for efficient computation of branches. Our preliminary experiments show its potential as an efficient method for discrete-event simulation studies.
Lookahead is a critical factor in conservative parallelsimulation. Greater lookahead usually brings better performance. However, in the simulation of computer networks, lookahead is usually determined by the minimal ...
详细信息
ISBN:
(纸本)9780769531595
Lookahead is a critical factor in conservative parallelsimulation. Greater lookahead usually brings better performance. However, in the simulation of computer networks, lookahead is usually determined by the minimal delay of the border links between any two subnets that simulated by different sequential logical processes (LPs), which is too small to get good performance. Traditionally, the lookahead exploitation usually only reflects the parallelism among LPs, which possibly wastes the potential parallelism inside each LP, especially, in the case that each LP simulates thousands of entities. Here we present a simple method called micro-synchronization to exploit the parallelism inside each LP. Different from the previous work, such as lookahead accumulation and local time warp, we keep the traditional usage of lookahead among LPs unchanged, and however, we impose the relaxed sequential event scheduling inside each LP, which can indirectly improve the lookahead We also present a state causality model to prove the correctness of our method, which means that there is no risk in the relaxed sequential execution. Finally, the experiment evaluates our method and shows that it can improve the performance of conservative parallelsimulation of computer networks to some extent.
The performance of any mobile network is highly influenced by the mobility patterns of nodes in the network. In fact mobility behavior is the most important environmental factor that determines performance and influen...
详细信息
ISBN:
(纸本)9780769531595
The performance of any mobile network is highly influenced by the mobility patterns of nodes in the network. In fact mobility behavior is the most important environmental factor that determines performance and influences network design. Thus it is important that we develop models that 1. accurately capture the mobility of nodes, while at the same time 2. are amenable to mathematical analysis and/or efficient simulation. In the past, the wireless networking community relied on simple models such as random walk [3] and random waypoint [2]. However, the first of these models was found to be too simplistic although very useful in analysis and simulation. The latter, on the other hand was widely accepted and used in simulations. However, recently it was disvcovered that practitioners had severely misued it in simulations [4]. That and the growing appreciation that random waypoint is unrealistic has led to significant activities recently focusing on the development of parsimonious and accurate models describing the movement of nodes in mobile wireless networks. These have included efforts to model connectivity within sparse mobile networks associated with people and vehicles, and with the movement of units in miliatary settings. This talk will provide some of the early history in modeling mobility, including some of the failures described above. The talk will then describe the more recent application of a wide range of techniques to account for mobility. These range from Markov chains to ODE-based fluid models [6], from the use of exponetial, lognormal, and heavy-tailed distributions [1]to geometric weighted Gaussian distributions for intercontact times [5], and from the use of discrete state models to continuous state PDE-based models. The goal of the talk is to provide a better understanding of the issues underlying the accurate modeling of mobiltiy, recent progress in addressing these issues and the challenges that different approaches place on simulation.
The paper presents an approach for achieving better performance of Monte Carlo simulation by implementing the process in a distributed computing environment. The simulation process is analyzed and sub processes, suita...
详细信息
ISBN:
(纸本)9789549641523
The paper presents an approach for achieving better performance of Monte Carlo simulation by implementing the process in a distributed computing environment. The simulation process is analyzed and sub processes, suitable for parallel execution are defined. The proposed approach is demonstrated by applying Monte Carlo simulation for evaluating the market risk of a financial position in an experimental distributed computing environment. Comparison data, obtained by carrying out the same simulation in an environment with one computer and in distributed environment, are presented and analyzed.
Remote network emulation is an approach that utilizes a remote parallel simulator to improve the scale and accuracy of network emulation for general users with no local access to high performance computing facilities....
详细信息
ISBN:
(纸本)9780769531595
Remote network emulation is an approach that utilizes a remote parallel simulator to improve the scale and accuracy of network emulation for general users with no local access to high performance computing facilities. The remote network emulation approach involves using a large scale detailed packet level simulation at a remote site in conjunction with a local network emulation to quickly provide QoS predictions to real time applications. Model update algorithms are needed to keep the remote simulator and local emulator updated with each other's status, while keeping the amount of communication required to an acceptable level. In this paper two adaptive model update algorithms are explored for triggering network status updates. The first algorithm dynamically adjusts update frequency according to the real network status between the remote simulator and emulator. The second algorithm triggers updates whenever the prediction error of the network emulation exceeds a pre-set threshold. Preliminary experimental results show that the two algorithms can improve emulation accuracy compared with a fixed update algorithm for the scenarios that were tested.
In this paper we describe web-based distributed system suitable for acceleration of fault simulation in digital circuits. Framework has three-tier client server concept. Java applets are used for user interfaces. Java...
详细信息
ISBN:
(纸本)9781424422760
In this paper we describe web-based distributed system suitable for acceleration of fault simulation in digital circuits. Framework has three-tier client server concept. Java applets are used for user interfaces. Java servlet on master server supports communication, task partitioning, user tracking, data management, etc. HTTP protocol based solution is used, since it is well established and flexible in firewall-protected environments. Reuse of existing test tools by encapsulation into Java agents extends the lifecycle and value of these tools. Considerable fault simulation speedup was gained in experiments. Two types of fault set partitioning were tried: adjacent fault selection and random fault selection. The latter is able to ensure more equal execution times for subtasks and therefore contributes to overall shorter parallelsimulation time.
暂无评论