Impact of I/O and execution scheduling strategies on large scale parallel data mining

机译：I / O和执行调度策略对大规模并行数据挖掘的影响

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In the era of “Big Data”, there is an emerging need to process a massive data set using large cluster system. Anyway, without the right strategies to handle the data, it is challenging to gain a good performance from the system. In this paper, many I/O and execution scheduling strategies for parallel data mining application has been investigated. The goal is to discover strategies that balance the data processing load and better utilize a multi-core cluster system for data mining application. Issues that impact the performance have been explored. The simulation results show that a substantial performance improvement can be obtained especially with a multi-core cluster system when a proper I/O and task execution sequence scheduling has been employed.

机译：在“大数据”的时代，存在使用大型集群系统处理大规模数据集的新兴。无论如何，如果没有正确的处理数据的战略，那么从系统中获得良好的表现就会挑战。在本文中，已经研究了许多用于并行数据挖掘应用程序的执行调度策略。目标是发现平衡数据处理负载并更好地利用多核群集系统进行数据挖掘应用程序的策略。探讨了影响性能的问题。仿真结果表明，当采用适当的I / O和任务执行序列调度时，可以获得实质性的性能改进，特别是在多核心集群系统中获得。

著录项

来源
《International Conference on New Trends in Information Science, Service Science and Data Mining》|2012年||共7页
会议地点
作者
Benjamas Nunnapus; Uthayopas Putchong;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类信息与传播理论;
关键词
I/O scheduling; data mining; execution scheduling; multi-core; parallel FI-growth;

机译：I / O调度;数据挖掘;执行调度;多核;并行化;

相似文献

外文文献
中文文献
专利

1. Parallelizing the execution of native data mining algorithms for computational biology [J] . Gianpaolo Coro, Leonardo Candela, Pasquale Pagano, Concurrency and computation: practice and experience . 2015,第17期

机译：并行执行用于计算生物学的本机数据挖掘算法
2. The impact of load balancing to object-oriented query execution scheduling in parallel machine environment [J] . Taniar D., Leung CHC. Information Sciences: An International Journal . 2003,第0期

机译：负载平衡对并行机环境中面向对象的查询执行调度的影响
3. A data-aware scheduling strategy for workflow execution in clouds [J] . Fabrizio Marozzo, Francisco Rodrigo Duro, Javier Garcia Blas, Concurrency, practice and experience . 2017,第24期

机译：一种用于云中工作流执行的数据感知调度策略
4. Impact of I/O and execution scheduling strategies on large scale parallel data mining [C] . Benjamas Nunnapus, Uthayopas Putchong 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining . 2012

机译：I / O和执行调度策略对大规模并行数据挖掘的影响
5. Translation of OpenMP to dataflow execution model for data locality and efficient parallel execution. [D] . Weng, Tien-hsiung. 2003

机译：将OpenMP转换为数据流执行模型，以实现数据局部性和高效的并行执行。
6. Parallel MapReduce: Maximizing Cloud Resource Utilization and Performance Improvement Using Parallel Execution Strategies [O] . Ahmed Abdulhakim Al-Absi, Najeeb Abbas Al-Sammarraie, Wael Mohamed Shaher Yafooz, -1

机译：并行MapReduce：使用并行执行策略来最大程度地利用云资源并提高性能
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％。

Impact of I/O and execution scheduling strategies on large scale parallel data mining

摘要

著录项

相似文献

相关主题

期刊订阅