中国计算机学会青年计算机科技论坛

CCF Young Computer Scientists & Engineers Forum

CCF YOCSEF 上海

于2014年1月11日(星期日) 下午1:30-5:30

华东师范大学（中山北路3663号）数学馆113报告厅举行

学术报告会，敬请光临

承办单位：华东师范大学数据科学与工程研究院

会议主题

新时期的DBMS

程 序

13:00 签到

13:20 会议开始，介绍会议议程

     周傲英教授，华东师范大学

13:30  特邀讲者：Volker Markl教授，柏林工业大学

14:00 特邀讲者：Asterios Katsifodimos 博士，柏林工业大学

14:30 特邀讲者：于戈教授，东北大学

      演讲题目：大数据高效能存储与管理关键技术研究

15:00 特邀讲者：阳振坤博士 阿里集团高级研究员

      演讲题目：OceanBase --- The Internet Era's Relational Database

15:30 特邀讲者：郑建兵副总经理  江苏移动信息技术中心

      演讲题目：互联网和大数据对运营商IT转型的挑战及相关思考

15:45  特邀讲者：周敏奇副教授，华东师范大学

       演讲题目：分布式事务的前世今生 

16:00  合影和茶歇

16:30  专题讨论Panel：互联网环境下的事务处理系统

           主持嘉宾：杜小勇教授 中国人民大学

           参加嘉宾：TBD

17:30 会议结束

新时期的DBMS

 互联网改变了一切，也改变了信息技术的发展模式。早期互联网发展的典型套路是：通过向人们提供搜索、娱乐、社交等服务，吸引上线，产生流量后再“流量变现”获取收益。这就是所谓的“制造需求”和“眼球经济”。Hadoop是这个阶段数据管理的经典之作。如今，通过营造虚拟空间制造需求的传统互联网已发展到极致，同时移动互联网和位置服务等技术的迅猛发展也为贯通人们线上和线下的生活提供了技术条件，互联网的发展正在进入一个新的阶段，其特点就是备受关注的O2O和反向O2O。当人们的（线上）虚拟空间生活和（线下）现实生活密不可分，新的挑战和机遇也就随之而来。

在人们线下的现实生活中，数据库是信息基础设施的重要组成部分，其本质之一就是支持事务处理（包括数据库恢复和并发控制）。互联网版本的并发控制和事务处理是当前数据管理领域面临的一个挑战，同时也是一个发展机遇。应用需求的变化、硬件技术的发展、互联网企业在数据管理领域的成功探索，改变了数据管理领域长期固守的一些基本假设。面向互联网和面向企业的数据管理逐步走向融合，数据管理技术和系统也随之进入新一轮的探索发展阶段。

执行主席：周傲英 教授，华东师范大学，CCF YOCSEF 荣誉委员

参会回执

 注：填写完上述回执，请于1月7日前回复至会议联系人。

 会议联系人：王长波，  电话：18502160116， Email： cbwang@sei.ecnu.edu.cn

                      刘晓，电话：15801897971， Email： xliu@sei.ecnu.edu.cn

 交通：

上海市普陀区中山北路3663号华东师范大学软件学院数学馆（毛主席像左手边）201会议室。乘轨道交通3号线或4号线至“金沙江路”站，沿金沙江路->中山北路->华东师范大学正门，步行可至。

 会场方位示意图：

 附：演讲嘉宾介绍

 报告介绍

 报告一：

Big data is often defined as any data set that cannot be handled using today’s widely available mainstream techniques and technologies. The challenges of handling big data are often described using 3-Vs (volume, variety and velocity): high volume of data from a variety of data sources arriving with high velocity analyzed to achieve an economic benefit. However, the 3-Vs fail to reflect complexity of “Big Data” in its entirety. The real complexity from a technical perspective stems from the fact that complex predictive and prescriptive analytic methods need to be applied to huge, heterogeneous data sets. However, “Big Data” (or often also called “Smart Data”) has a much wider scope and has challenges and opportunities in 5 dimensions: technology, application, economic, legal and social. In our talk, we give an overview of these five dimensions of Big Data, survey several research challenges and solutions of our past work, in particular with respect to iterative computations, fault-tolerance, and heterogeneous hardware. We also survey the broader research challenges that a team of database researchers, including the speaker, has identified in the context of the Beckman Database Research Self-Assessment Meeting, including scalable big/fast data infrastructures; coping with diversity in the data management landscape; end-to-end processing and understanding of data; cloud services; and managing the diverse roles of people in the data life cycle.

Bio: Volker Markl is a Full Professor and Chair of the Database Systems and Information Management (DIMA) group at the Technische Universität Berlin (TU Berlin). Volker also holds a position as an adjunct full professor at the University of Toronto and is director of the research group “Intelligent Analysis of Mass Data” at DFKI, the German Research Center for Artificial Intelligence. Volker is also director of the Berlin Big Data Center, a collaborative research center bringing together research groups in the areas of distributed systems, scalable data processing, text mining, networking, machine learning and applications in several areas, such as healthcare, logistics, Industrie 4.0, and information marketplaces. His research interests include: new hardware architectures for information management, scalable processing and optimization of declarative data analysis programs, and scalable data science, including graph and text mining, and scalable machine learning. Over the course of his career, has published numerous scholarly papers, filed 18 patents, and has been involved in several startups, as founder or advisor. Volker has garnered many prestigious awards, including the European Information Society and Technology Prize, an IBM Outstanding Technological Achievement Award , an IBM Shared University Research Grant , an HP Open Innovation Award , an IBM Faculty Award, a Trusted-Cloud Award for Information Marketplaces by the German Ministry of Economics and Technology, the Pat Goldberg Memorial Best Paper Award, and a VLDB Best Paper award. Dr. Markl currently serves as the secretary of the VLDB Endowment was recently elected as one of Germany's leading "digital minds" (Digitale Köpfe) by the German Informatics Society (GI).

报告二：

Flink: 下一代数据分析平台

Asterios Katsifodimos 博士，柏林工业大学

Flink: A Next-Generation Data Analytics Platform

Dr. Asterios Katsifodimos, TU Berlin

Abstract: Apache Flink (http://flink.incubator.apache.org ) is a software stack for complex big data analytics, which is a result of the Stratosphere research project coordinated at TU Berlin. Stratosphere and Flink cover a variety of use cases, such as data warehousing, information extraction and integration, data cleansing, graph analysis, and statistical analysis applications. Flink brings together a unique set of features from database systems and MapReduce-like technology that enables expressive, easy, and efficient programming for the development of large-scale analytical applications. Stratosphere features include in situ data processing, multiple language APIs (e.g., for Java and Scala), treatment of user-defined functions (UDFs) as first-class citizens, automatic program parallelization and optimization, support for iterative programs, and a scalable and efficient execution engine. In this talk, I will present an overview of the Stratosphere vision, the Flink platform as well as current and future research activities.

Bio: Asterios Katsifodimos is a Postdoctoral Researcher co-leading the Stratosphere research project at the Technische Universität Berlin. He received his PhD in Computer Science in 2013 from INRIA Saclay and Université Paris-Sud under the supervision of Ioana Manolescu. His thesis focused on materialized view-based techniques for the management of Web Data. Asterios was a member of the High Performance Computing Lab at the University of Cyprus, where he obtained his B.Sc. and M.Sc. degrees in Computer Science. His research interests include query processing, optimization, and massively parallel data analysis.

报告三：

大数据高效能存储与管理关键技术研究

于戈教授，东北大学

Key Techniques of High-Performance Storage and Management for Big Data

Prof. YU Ge, Northeastern University

Abstract: Big data storage is the fundament basis for big data processing and applications, and the related key techniques are to be solved urgently in big data application fields. It has huge application values and important strategic requirements. This talk will present the new solutions to build a high performance big data storage management system based on cloud computing platforms. To raise the utility and capability of the system, the balance and transparency issues on heterogeneous storage devices are addressed. To guarantee reliability and scalability of the system, the data access characteristics sensing and dynamic storage resource scheduling issues on multi-modal data organization and storage management are addressed. Finally, the design of a general purpose high performance big data storage management system to support typical big data processing and analysis including OLTP, OLAP, graph computation, and stream processing is given. The talk will introduce the key techniques in the system: the on-demand customized storage management system architecture, storage-processing-transfer integrated storage resource scheduling mechanism, data access characteristics aware storage model, data routing based multi-modal data reduction method, data aggregation and distribution mechanism for storage-processing-transfer optimization, and benchmark testing method for high performance storage systems.

摘要：大数据存储是大数据处理与应用的核心基础，是当前大数据应用领域中迫切需要解决的关键问题，具有非常巨大的应用价值和战略需求。本报告提出在云计算平台上构建大数据高效能存储与管理系统的新解决方案，通过解决复杂异构存储设备的均衡性和透明性问题, 提升大数据存储与管理系统的整体效能；通过解决多模态大数据组织与存储管理中的存储特征灵敏感知和资源动态调度问题，保证大数据存储与管理的可靠性和可扩展性；实现一个支持典型大数据分析与处理的通用型高效能大数据存储与管理系统。本报告将介绍该系统涉及的关键技术：按需定制大数据高效能存储与管理体系结构、存算传融合的多模态大数据存储调度机制、存储特征感知的大数据高效能存储模型、基于数据路由策略的多模态大数据缩减存储方法、存算传多目标优化的大数据聚散机理、以及高效能存储系统评测标准与方法。

Bio: Dr. YU Ge, Professor at Northeastern University, Director of the Northeastern University Networking Center. He received his Ph.D. degree in computing science from Kyushu University of Japan in 1996. His research interests mainly include distributed and parallel database, OLAP and data warehousing, data integration, transaction management, workflow management, graph data management, real-time and embedded database, etc. He is the director of the Office Automation Technical Committee of China Computer Federation (CCF), the trustee and the outstanding member of CCF, the member of the IEEE Computer Society and ACM. He was the auditor of CCF, the vice director of Database Technology Committee of CCF. He has served as member of program committee of many international conferences (including VLDB, ICDE, CIKM, DASFAA, ADC, WAIM etc.), and now acts as the associate editor of IEEE TKDE, Chinese Journal of Computers, Computer Research and Development, Journal of Software.

于戈，东北大学二级教授，博士生导师，信息学院计算机软件研究所所长, 东北大学计算中心[网络中心]主任。1982年、1986年先后获得东北大学计算机工学学士学位和硕士学位，1996年获得日本九州大学计算机工学博士学位。主要研究领域数据库理论与技术、分布与并行式系统、嵌入式软件与应用等。现兼任中国计算机学会理事、办公自动化专业委员会主任、数据库专委会委员，以及系统软件专委会委员，中国计算机学会沈阳分部主席，美国ACM学会会员、IEEE学会会员，《IEEE TKDE》、《计算机学报》、《软件学报》、《计算机研究与发展》等期刊编委。曾担任第五届、第六届国务院学位委员会学科评议组成员，第十二届、第十三届国家自然科学基金委员会评审专家组成员，以及VLDB, ICDE, CIKM, DASFAA, ADC, WAIM等多届重要国际会议的程序委员会委员。

报告四：

OceanBase ---互联网时代的关系数据库系统

阳振坤博士 阿里集团高级研究员

OceanBase --- The internet era's relational database

Dr. YANG Zhenkun，Senior Researcher, Alibaba Group

Abstract: While a traditional shopping mall can only accommodate at most tens of thousands of customers and brings at most a few thousands of concurrent access to its backend database due to its limited physical building space and very limited cashier counters, a sales promotion of an online shopping website (e.g., Taobao.com and Tmall.com of Alibaba Inc.) can attract tens of millions of customers due to its almost unlimited cyber space and thus brings millions of concurrent access to its backend database. These kind of high concurrent access and corresponding high data volume obsolete usually shared-disk traditional database. This talk will demonstrate how OceanBase, a distributed shared-nothing relational database built from scratch at Alibaba Inc., meets the extremely high performance and high scalability requirement of Taobao.com and Tmall.com as well as Alipay.com, the online payment website which offers secured transaction service for Taobao.com, Tmall.com and many other online companies. 

Bio: Dr. YANG Zhenkun, Senior Researcher with Alibaba. Before joining Alibaba, he was a Senior Scientist with Baidu.com, and a Chief Researcher with Microsoft Research Asia, etc. He received his bachelor and master degrees from the Department of Mathematics, Peking University. After he got his Ph.D. degree from the Department of Computer Science, Peking University, he became a faculty of the Institute of Computer Science and Technology, Peking University and a full professor in computer science in 1997. He received the Cheung Kong Scholarship, in 1999. He was awarded the First Class Award of the National Science and Technology Progress of China in 1995 (the 4th person). He also won the First Class Award of Science and Technology Progress of Beijing Municipality in 1996, National Youth Science and Technology Award of China in 1998, Qiushi Eminent Award of the Chinese Academy of Science and Technology in 1998, and Wusi Youth Award of Beijing Municipality in 2000. In recent years, his research interests are distributed storage and computing system. He is now the chief architect of OceanBase (https://github.com/alibaba/oceanbase), an open source distributed shared-nothing relational database at Alibaba.

阳振坤博士于1984年进入北京大学数学系，获得学士和硕士学位后转入计算机系，1993年获得博士学位并留校，同年破格晋升副教授，1997年破格晋升教授，1999年成为北京大学首批长江教授。近年来主要研究领域为分布式系统和海量数据库系统。获得荣誉包括国家科学技术进步奖一等奖(排名第四)、北京市科学技术进步奖一等奖、第六届中国青年科技奖、第一届中国科协求是杰出青年奖、北京市“五四青年奖章”等。曾先后担任方正研究院副院长、北大计算机研究所副所长、联想研究院首席研究员、微软亚洲研究院主任研究员、百度高级科学家等。近年来主要研究领域为分布式系统和数据库，现为阿里集团高级研究员。

报告五：

Abstract：Internet and big data are changing the development of Information Technology. In particular, it is from IT (Information Technology) to DT (Data Technology), from technical monopolization to de-centralization, from traditional IT cost center to Internet profit center, from Internet for people to Internet of Things. The telecommunication operators are confronted with many challenges. The primary businesses are challenged by novel bypass business model; the operations are challenged by Internet marketing; the daily operation management is challenged by low-cost and quick-response IT support. The possible corresponding strategies include: mashup in terms of technology and crossover in terms of business; data visualization and lowering the barriers for big data utilization; developing cross-industry collaboration to monetize the big data; building centralized multi-purpose operation platform and Internet dissemination platform for digital content.

摘要：互联网和大数据带来了信息技术的发展路线的转变，表现在以下几个方面：从IT时代(Information Technology）向DT时代(Data Technology）的转变；从技术权威垄断时代到技术去中心化时代的转变；从传统的IT成本中心到互联网数据利润中心的转变；以及从人联网时代到万物互联时代的转变。在这种形势下，通信运营商也面临诸多挑战：主营业务被旁路的商业模式挑战；互联网营销的运营方式挑战；低成本快响应的IT工作方式挑战。通信运营商可能的应对策略包括： 技术上混搭，业务上跨界；对内的数据可视化，降低大数据使用门槛；对外的跨行业合作，探索大数据价值变现；对内建立多专业集中运营平台，对外建立数字内容互联网分发平台。

Bio：ZHENG Jianbing, Senior Engineer and Vice General Manager of Information Technology Center at China Mobile Jiangsu. Jianbing has been engaged in planning, building and operation of IT systems for telecommunication operators for almost 20 years. His current interests are focusing on IT system construction for cloud computing and big data, and as well as the exploration of business value of the big data possessed by telecommunication operators.

郑建兵，高级工程师，中国移动江苏公司信息技术中心副总经理，长期从事通信运营商IT系统的规划、建设及运营，目前核心工作方向是云计算、大数据的IT系统建设及进行大数据商业价值发挥的研究与探索。

报告六：

分布式事务的前世今生

周敏奇副教授，华东师范大学

A Retrospective of Distributed Databases (on Transaction)

Associate Prof. Minqi Zhou, East China Normal University

Abstract: Distributed transaction has a long history of research literature, even more 35 years. Nevertheless, only few of the database systems which support distributed transaction are deployed for practical usage, such as VoltDB, Spanner. Distributed transaction systems are amazing, which attracts large amount of attentions both from academy and industry due to its low cost of extendibility, easy deployment and etc., especially in the internet era at present. In this talk, we analyze the primary factors which hinder the performance of distributed transaction from practical usage. However, the emerging of new hardware components nowadays, such QPI, infiniband, which reduce the latency of the network communication by two or three magnitudes, is hopeful in the making the distributed transaction more practical.

Bio: ZHOU Minqi, Associate Professor at East China Normal University. He received his bachelor and master degrees from Nanjing University Sciences & Technology in 2003 and 2005 respectively, and Ph.D. degree in Computer Science from Fudan University in 2009. In 2003 and 2007, he visited University of Queensland, Australia and the SAP China Lab respectively. He acted as member of program committee for many conferences, including ICDE 2011, IUCS 2011, WISA 2011. His research interests mainly include data management in the distributed systems, data-intensive computing, in-memory computing and computational advertising.

周敏奇 华东师范大学副教授。2003、2005年在南京理工大学分别获得学士和硕士学位，2009年在复旦大学获得计算机软件与理论专业博士学位。并曾于2007 年7月-2008年2月和2008年6月-2008年12月间分别在澳大利亚昆士兰大学和SAP中国研究院做短期访学。曾多次担任学术会议的程序委员会委 员，包括ICDE 2011、IUCS 2011、WISA 2011等。研究兴趣主要包括分布式数据管理、数据密集型计算、内存计算、计算广告学等。

互联网和大数据对运营商IT转型的挑战及相关思考

郑建兵 江苏移动信息技术中心副总经理

IT Paradigm Shift in the Internet and Big Data Era for Telecom Operators

Zheng Jianbing, Vice-GM, IT Center at China Mobile Jiangsu