EXPPO: EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service

机译：EXPPO：CPS协同仿真即服务的执行性能分析和优化

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

A co-simulation may comprise several heterogeneous federates with diverse spatial and temporal execution characteristics. In an iterative time-stepped simulation, a federation exhibits the Bulk Synchronous Parallel (BSP) computation paradigm in which all federates perform local operations and synchronize with their peers before proceeding to the next round of computation. In this context, the lowest performing (i.e., slowest) federate dictates the progression of the federation logical time. One challenge in co-simulation is performance profiling for individual federates and entire federations. The computational resource assignment to the federates can have a large impact on federation performance. Furthermore, a federation may comprise federates located on different physical machines as is the case for cloud and edge computing environments. As such, distributed profiling and resource assignment to the federation is a major challenge for operationalizing the co-simulation execution at scale. This paper presents the Execution Performance Profiling and Optimization (EXPPO) methodology, which addresses these challenges by using execution performance profiling at each simulation execution step and for every federate in a federation. EXPPO uses profiling to learn performance models for each federate, and uses these models in its federation resource recommendation tool to solve an optimization problem that improves the execution performance of the co-simulation. Using an experimental testbed, the efficacy of EXPPO is validated to show the benefits of performance profiling and resource assignment in improving the execution runtimes of co-simulations while also minimizing the execution cost.

机译：协同仿真可以包括具有不同的空间和时间执行特征的几个异构联合体。在迭代的分步仿真中，联盟展示了批量同步并行（BSP）计算范式，其中所有联盟在执行下一轮计算之前都执行本地操作并与它们的对等方进行同步。在这种情况下，性能最低的联盟（即最慢的联盟）决定联盟逻辑时间的进展。联合仿真中的一项挑战是对单个联盟和整个联盟的性能分析。分配给联盟的计算资源可能会对联盟性能产生很大影响。此外，联合可以包括位于不同物理机器上的联合，就像云和边缘计算环境一样。因此，对联合应用程序进行分布式配置和资源分配是大规模实施协同仿真执行的主要挑战。本文介绍了执行性能分析和优化（EXPPO）方法，该方法通过在每个模拟执行步骤以及联盟中的每个联盟使用执行性能分析来解决这些挑战。 EXPPO使用概要分析来学习每个联盟的性能模型，并在其联盟资源推荐工具中使用这些模型来解决优化问题，从而提高协同仿真的执行性能。使用实验性测试平台，EXPPO的有效性得到了验证，以显示性能分析和资源分配在改善协同仿真的执行时间以及最小化执行成本方面的优势。

著录项

来源
《IEEE International Symposium on Real-Time Distributed Computing》|2020年|184-191|共8页
会议地点
作者
Yogesh D. Barve; Himanshu Neema; Zhuangwei Kang; Hongyang Sun; Aniruddha Gokhale; Thomas Roth;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
cyber-physical systems; distributed simulation; cloud computing; latency; performance; resource management; gang scheduling;

机译：网络物理系统;分布式仿真;云计算;延迟;性能;资源管理;帮派调度;

相似文献

外文文献
中文文献
专利

1. Effects of Dietary Supplementation of Bacteriophage CP on Growth Performance, Nutrient Digestibility, Blood Profiles, Carcass Characteristics and Fecal Microflora in Broilers [J] . Hee Yeob Baek, Jae Won Kim, Jung Un Kim, Korean Journal of Poultry Science . 2013,第4期

机译：膳食中添加噬菌体CP对肉鸡生长性能，营养消化率，血型、,体特性和粪便菌群的影响
2. Techniques for the execution profile analysis and optimization of computational chemistry programs [J] . Gomes André S. P., Martins Lucimara R., Universidade Estadual de Campinas Campinas, Quimica nova . 2002,第3期

机译：执行配置文件分析和计算化学程序优化的技术
3. Facilitating program performance profiling via evolutionary symbolic execution [J] . Aquino Andrea, Braione Pietro, Denaro Giovanni, Software Testing, Verification and Reliability . 2020,第2期

机译：通过演化符号执行促进程序性能分析
4. EXPPO: EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service [C] . Yogesh D. Barve, Himanshu Neema, Zhuangwei Kang, IEEE International Symposium on Real-Time Distributed Computing . 2020

机译：EXPPO：执行CPS共模 - AS-Service的执行性能分析和优化
5. Leveraging profile-selected execution patterns for optimized code execution in resource-constrained systems. [D] . Badea, Carmen Tatiana. 2010

机译：利用配置文件选择的执行模式在资源受限的系统中优化代码执行。
6. Challenges and Solutions in Optimizing Execution Performance of a Clinical Decision Support-Based Quality Measurement (CDS-QM) Framework [O] . Tyler J Tippetts, Phillip B Warner, Polina V Kukhareva, 2015

机译：基于临床决策支持的质量度量（CDS-QM）框架的执行性能优化中的挑战和解决方案
7. We develop a sequential trade model of Iceberg order execution in a limit order book. The Iceberg-trader has the freedom to expose his trading intentions or (partially) shield the true order size against other market participants. Order exposure can cause drastic market reactions (“market impact”) in the end leading to higher transaction costs. On the other hand the Iceberg trader faces a loss-in-priority when he hides his intentions, as most electronic limit order books penalize the usage of hidden liquidity. Thus the Iceberg-trader is faced with the problem to find the right trade-off. Our model provides optimal exposure strategies for Iceberg traders in limit order book markets. In particular, we provide a range of analytical statements that are in line with recent empirical findings on the determinants of trader’s exposure strategies. In this framework, we also study the market impact also market impact of limit orders. We provide optimal exposure profiles for a range of hightech stocks from the US SP500 and how they scale with the state-of-the-book. We finally test the Iceberg’s performance against the limit orders and find that Iceberg orders can significantly enhance trade performance by up to 60. [O] . Gökhan Cebiro˜glu, Ulrich Horst 100

机译：我们在限价订单簿中开发了冰山订单执行的顺序交易模型。 Iceberg-trader可以自由地揭露他的交易意图，或者（部分）屏蔽其他市场参与者的真实订单规模。订单暴露最终会导致市场反应激烈（“市场影响”），导致交易成本上升。另一方面，冰山交易员在隐藏他的意图时面临优先权损失，因为大多数电子限价订单都会惩罚隐藏流动性的使用。因此，冰山商人面临着找到正确权衡的问题。我们的模型为限额订单市场中的冰山交易者提供了最佳的风险敞口策略。特别是，我们提供了一系列分析性陈述，这些陈述与最近关于交易者暴露策略决定因素的实证研究结果一致。在此框架下，我们还研究了市场影响以及限价订单的市场影响。我们为来自美国标准普尔500指数的一系列高科技股票提供最佳曝光配置文件，以及它们如何随着本书的规模扩展。我们最终根据极限订单测试了冰山的表现，发现冰山订单可以显着提升贸易业绩高达60％。

EXPPO: EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service

摘要

著录项

相似文献

相关主题

期刊订阅