High Performance Parallel and Distributed Systems: Resource Management and Data Handling Techniques

高性能并行和分布式系统：资源管理和数据处理技术

• 批准号: RGPIN-2019-04479
• 负责人: Majumdar, Shikharesh
• 金额: $ 2.48万
• 依托单位: Carleton University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=714903
• 关键词: Performance; Parallel; Distributed; Systems; Resource

The proposed research focuses on resource management and data handling techniques on high performance parallel and distributed systems including clusters and clouds. Computation and data intensive BigData analytics applications used in the context of enterprise and social media as well on sensor-based smart systems (e.g. smart bridges, buildings, machinery and health care systems) often require the power of such high performance environments. There are two important challenges currently facing the researchers of such systems: processing and analysis of (i) large volumes of stored data and (ii) streaming data resulting from twitter feeds and continuously generated sensor data for example. Each of these is important in the context of today's data and computation intensive systems. Effective resource management and data handling techniques are crucial for achieving high performance and high quality of experience for the users on such systems. New cost effective techniques are critically needed for harnessing the underlying large resource pools in clouds that are often used to meet the challenges of such data and computation intensive applications and produce results in a timely manner. Proposed research is directed at achieving these required innovations in science and technology. Outcomes & Benefits: Results of the research will be applicable to both researchers and users in two important domains: (a) cloud based data analytics platforms that are crucial for extracting knowledge from BigData and (b) smart systems that are essential components of the newly emerging smart society. The research results will create new knowledge, advance the state of the art and contribute to the achievement of the desired quality of service for system users, adequate revenues for service providers, safe and economically maintained infrastructures and machinery as well as efficient health care systems for the public. Training of students is an important and an integral part of the plan; the research results and trained HQP will aid in establishing Canada as a leader in the global market. I have been researching distributed systems and resource management for many years with recent focus on clouds and data analytics platforms. My contributions are recognized through best paper awards and selection as a Distinguished Visitor for the IEEE Computer Society. My activities in the past 6 years are reflected in my selection as a Fellow of the Institution of Engineering and Technology, 58 refereed contributions in reputed international forums, 4 keynote addresses, 1 plenary address and 13 invited lectures (including 2 tutorials), chairing of an international conference and the organization of several international workshops. Relevance of my research for the public is captured in my media interviews and the featuring of my research in the Scientia magazine.

拟议的研究重点是高性能并行和分布式系统，包括集群和云的资源管理和数据处理技术。在企业和社交媒体以及基于传感器的智能系统（例如智能桥梁、建筑、机械和医疗保健系统）中使用的计算和数据密集型大数据分析应用程序通常需要这种高性能环境的支持。目前，这种系统的研究人员面临着两个重要的挑战：处理和分析（i）大量存储的数据和（ii）例如来自twitter馈送和连续生成的传感器数据的流数据。在当今的数据和计算密集型系统的背景下，这些中的每一个都很重要。有效的资源管理和数据处理技术对于在此类系统上为用户实现高性能和高质量的体验至关重要。迫切需要新的具有成本效益的技术来利用云中的底层大型资源池，这些资源池通常用于应对此类数据和计算密集型应用程序的挑战，并及时产生结果。拟议的研究旨在实现这些所需的科学和技术创新。结果和好处：研究结果将适用于两个重要领域的研究人员和用户：（a）基于云的数据分析平台，这对于从大数据中提取知识至关重要;（B）智能系统，这是新兴智能社会的重要组成部分。 研究成果将创造新的知识，推进最先进的技术水平，并有助于实现系统用户所需的服务质量，服务提供商的充足收入，安全和经济维护的基础设施和机械，以及为公众提供高效的医疗保健系统。学生培训是该计划的重要组成部分;研究成果和训练有素的HQP将有助于建立加拿大作为全球市场的领导者。多年来，我一直在研究分布式系统和资源管理，最近专注于云和数据分析平台。我的贡献通过最佳论文奖和IEEE计算机协会的杰出访问者评选得到认可。我在过去6年中的活动反映在我作为工程和技术研究所的研究员的选择，在著名的国际论坛，4个主题演讲，1个全体会议演讲和13个邀请讲座（包括2个教程），主持国际会议和组织几个国际研讨会的58个参考贡献。我的研究与公众的相关性在我的媒体采访和Scientia杂志上的专题报道中得到了体现。