首页> 外文期刊>Annales Mathematicae et Informaticae >Probabilistic model checking on HPC systems for the performance analysis of mobile networks
【24h】

Probabilistic model checking on HPC systems for the performance analysis of mobile networks

机译:用于移动网络性能分析的HPC系统上的概率模型检查

获取原文
           

摘要

We report on the use of HPC resources for the performance analysis of the mobile cellular network model described in "A New Finite-Source Queue- ing Model for Mobile Cellular Networks Applying Spectrum Renting" by Tien Van Do et al. That paper proposed a new finite-source retrial queueing model with spectrum renting that was analyzed with the MOSEL-2 tool. Our re- sults show how this model can be also appropriately described and analyzed with the probabilistic model checker PRISM, although at some cost consid- ering the formulation of the model; in particular, we are able to accurately reproduce most of the analytical results presented in that paper and thus increase the confidence in the previously presented results. However, we also outline some discrepancies which may hint to deficiencies of the original anal- ysis. Moreover, by applying a parallel computing framework developed for this purpose, we are able to considerably speed up studies performed with the PRISM tool. The investigations are illustrated by figures and conclusions are drawn.
机译:我们在Tien Van Do等人的“使用频谱租用的移动蜂窝网络的新有限源排队模型”中介绍了使用HPC资源进行移动蜂窝网络模型的性能分析的情况。该论文提出了一种新的带有频谱租用的有限源重试排队模型,并使用MOSEL-2工具对其进行了分析。我们的结果表明,尽管可能需要花费一定的成本来考虑模型的建立,但是也可以使用概率模型检查器PRISM适当地描述和分析该模型。特别是,我们能够准确地重现该论文中介绍的大多数分析结果,从而增加对先前介绍的结果的信心。但是,我们也概述了一些差异,这可能暗示了原始分析的不足。此外,通过应用为此目的开发的并行计算框架,我们可以大大加快使用PRISM工具进行的研究。调查通过数字说明,并得出结论。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号