CAREER: Reliability in Large-Scale Storage

职业：大规模存储的可靠性

• 批准号: 1453121
• 负责人: Arya Mazumdar
• 金额: $ 54万
• 依托单位: University of Minnesota-Twin Cities
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-02-01 至 2016-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1453121&HistoricalAwards=false
• 关键词: CAREER; Reliability; Large; Scale; Storage

With the advent of large scale distributed storage systems, cloud computing and commercial data storage applications, there is a renewed interest in the coding and information theory in reliabile issues data storage. In large networked databases, faster updates and quick repair requirements must be integrated with reliable data storage protocols. These requirements bring new dimensions and parameters to the traditional optimization problem of information theory.In this project we propose, for the first time, a model of large-scale storage that accounts for the topology of storage networks. Previously, storage topology was never a concern of the code designers. Further, we study the update efficiency and local repair (fast recovery) properties of error-correcting codes suitable for storage. For all of these, we will analyze the fundamental limits of systems, as well as propose explicit (fast algorithmic) constructions of codes. Several tools from graph and network theory, combinatorics and optimization theory will be leveraged to find performance limits and devise coding algorithms.By cutting redundancy and allowing faster processing, the codes developed from this project will directly save energy consumption in data centers. Existing and new collaborations of the principal investigator will facilitate industry cooperation and increase the transition to practice of results generated from this project. Elements of this endeavor will be integrated with the courses taught by the principal investigator. The findings will be disseminated through publications in peer-reviewed venues and made available in the form of technical reports for public access on the investigator's webpage. Finally, motivated by practical applications and extending across various disciplines, this project is representative of an intriguing area of engineering science, and will attract a diverse student base including undergraduate students.

随着大规模分布式存储系统、云计算和商业数据存储应用的出现，编码和信息论在可靠性问题数据存储中的兴趣重新燃起。在大型网络数据库中，更快的更新和快速修复要求必须与可靠的数据存储协议相结合。这些需求给传统的信息论优化问题带来了新的维度和参数，在这个项目中，我们首次提出了一个考虑存储网络拓扑结构的大规模存储模型。以前，代码设计人员从来不关心存储拓扑。进一步，我们研究了适用于存储的纠错码的更新效率和局部修复（快速恢复）特性。对于所有这些，我们将分析系统的基本限制，以及提出明确的（快速算法）代码结构。该项目将利用图论和网络理论、组合学和优化理论中的一些工具来寻找性能极限并设计编码算法。通过削减冗余和允许更快的处理，该项目开发的代码将直接节省数据中心的能源消耗。主要研究者的现有和新的合作将促进行业合作，并增加该项目产生的成果向实践的过渡。这一奋进的要素将与主要研究者教授的课程相结合。调查结果将通过同行评审场所的出版物传播，并以技术报告的形式在调查员的网页上供公众访问。最后，该项目以实际应用为动力，跨越各个学科，代表了工程科学的一个有趣领域，将吸引包括本科生在内的多元化学生群体。