|
Journal of Zhejiang University SCIENCE C
ISSN 1869-1951(Print), 1869-196x(Online), Monthly
2014 Vol.15 No.1 P.13-30
Activity-based simulation using DEVS: increasing performance by an activity model in parallel DEVS simulation
Abstract: Improving simulation performance using activity tracking has attracted attention in the modeling field in recent years. The reference to activity has been successfully used to predict and promote the simulation performance. Tracking activity, however, uses only the inherent performance information contained in the models. To extend activity prediction in modeling, we propose the activity enhanced modeling with an activity meta-model at the meta-level. The meta-model provides a set of interfaces to model activity in a specific domain. The activity model transformation in subsequence is devised to deal with the simulation difference due to the heterogeneous activity model. Finally, the resource-aware simulation framework is implemented to integrate the activity models in activity-based simulation. The case study shows the improvement brought on by activity-based simulation using discrete event system specification (DEVS).
Key words: Activity tracking, Activity enhanced modeling, Discrete event system specification (DEVS), Resource-aware simulation framework
创新方法:已有的仿真性能优化方法专注于对性能运行结果的“盲”挖掘,而忽略了模型本身可以提供的性能信息。本文利用活跃度的概念在建模阶段就提取模型的性能信息,用于在仿真阶段指导计算资源的分配。此外,利用活跃度元模型和模型变换方法,研究在任意领域进行活跃度建模的方法,基于DEVS仿真引擎提出仿真中活跃度模型异质的解决方法。
研究手段:利用CPU占用率和内存使用量来量化模型的活跃度,解决了活跃度模型的计算问题。设计了增强式活跃度建模方法,提供了一系列特定接口对特定领域上的模型活跃度进行构造。提出了资源敏感型的建模与仿真框架,为活跃度建模定义了一整规范,选择DEVS作为通用仿真形式化方法,方便用户构造各种类型的领域活跃度模型。
重要结论:对如何利用活跃度进行仿真性能优化进行了研究,利用计算机资源占用的方法量化了模型的活跃度,提供了一种在特定领域中定义活跃度的增强式活跃度建模方法,利用活跃度元模型和模型变换方法解决了仿真异质问题,设计了资源敏感型建模与仿真框架为在仿真应用中构造和使用活跃度模型提供了标准规范。
关键词组:
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/jzus.C1300121
CLC number:
TP312
Download Full Text:
Downloaded:
3384
Download summary:
<Click Here>Downloaded:
2132Clicked:
9634
Cited:
2
On-line Access:
2024-08-27
Received:
2023-10-17
Revision Accepted:
2024-05-08
Crosschecked:
2013-12-16