Computation and Data Intensive Parallel and Distributed Systems: Resource Management and Data Handling Techniques

以合理的成本获得计算和通信系统正在增加并行和分布式系统的使用。一般来说，分布式系统，特别是基于互联网的系统，如云，正在成为现代社会日常生活的一部分。并行和分布式系统的研究人员面临着两个新的重要挑战。它们涉及(I)通常被称为大数据的海量数据的有效处理，以及(Ii)利用新兴的物联网(IoT)技术的基于传感器的设备的高度扩散。提出这项研究的动机是需要找到这些挑战的有效答案。*云中的大型资源池通常用于与大数据和物联网相关的系统中。然而，资源管理和数据处理技术对于利用云的底层资源池是非常必要的。我提出的研究旨在填补关于用于高性能和数据密集型系统这一相对较新的领域的资源管理和数据处理的技术的当前技术状态中的空白。建议对资源管理和数据处理技术进行研究，以用于(I)基于云的数据分析平台，这些平台对于从BigData中提取知识至关重要；以及(Ii)智能系统(例如基于传感器的桥梁、建筑、航空航天机械和智能医疗系统)，这些系统是新兴智能社会的重要组成部分。研究成果将发掘新知识，提高最先进水平，并有助于为系统用户实现所需的服务质量，为服务提供商提供足够的收入，为公众提供安全和经济维护的基础设施和机械，以及高效的医疗保健系统。培训学生是该计划的重要组成部分；研究结果和受过培训的HQP将有助于确立加拿大作为全球市场领导者的地位。*在过去的29年里，我一直在研究分布式系统和资源管理。我的工作包括对多编程并行系统上的并行作业调度的开创性研究，以及用于管理大型异类资源集和处理云上容易出错的用户请求运行时间估计的新技术。我的贡献通过最佳论文/演示文稿奖和被选为IEEE计算机协会杰出参观者而得到认可。在过去的6年里，我的活动体现在15份期刊和1份杂志稿件，4个书籍章节，36篇参考会议论文，3张海报，5次主题演讲和12次特邀讲座，为各种知名会议的计划和指导委员会服务，主持一次国际会议和组织几次国际研讨会。我的研究与公众的相关性在我的媒体采访中得到了捕捉(见CCV)。

The availability of computing and communication systems at a reasonable cost is increasing the use of parallel and distributed systems. Distributed systems in general and internet-based systems such as the cloud in particular are becoming part of the daily life in a modern society. There are two new important challenges facing the researchers of parallel and distributed systems. They concern the effective handling of (i) large volumes of data often referred to as Big Data and (ii) the high proliferation of sensor-based devices that utilize the newly emerging internet of things (IoT) technology. The proposed research is motivated by the need for finding effective answers to these challenges.*** The large resource pools in clouds are often utilized in systems that concern Big Data and IoT. Resource management and data handing techniques are critically needed, however, for harnessing this underlying resource pool of a cloud. My proposed research is directed at filling the gap in the current state of the art concerning techniques for resource management and data handling for this relatively new domain of high performance and data intensive systems. Research is proposed for resource management and data handling techniques for (i) cloud based data analytics platforms that are crucial for extracting knowledge from BigData and (ii) smart systems (e.g. sensor-based bridges, buildings, aerospace machinery and smart health care systems) that are essential components of the newly emerging smart society. The research results will cerate 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 the past 29 years. My work includes pioneering research on parallel job scheduling on multiprogrammed parallel systems and novel techniques for managing a large heterogeneous set of resources and handling error-prone user estimates of request run times on clouds. My contributions are recognized through best paper/presentation awards and selection as a Distinguished Visitor for the IEEE Computer Society. My activities in the past 6 years are reflected in 15 journal and 1 magazine contributions, 4 book chapters, 36 refereed conference papers, 3 posters, 5 keynote addresses and 12 invited lectures, service in various program and steering committees for reputed conferences, 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 (see CCV).