Dai, Yafei
Professor
Research Interests: Distributed system, cloud storage
Office Phone: 86-10-6276 5815-8007
Email: dyf@pku.edu.cn
Dai, Yafei is a professor in the School of Computer Science. She obtained her B.Sc. from Harbin Institute of Technology in 1982, and Ph.D. from Harbin Institute of Technology in 1993 respectively. Her research interests include networking and distributed system, graph computing system and cloud storage system.
Dr. Dai has published more than 100 research papers, and some of them are published in top-tier journals, such as TPDS, TOC, TKDE, TKDD, TWEB, TDSC, TOIT and TCC. Many of them are published in top-tier conferences, such as ATC, INFORCOM, SOCC, HPDC, ICDCS, MSST and so on. She has served in the Technical Program Committee of various international conferences including WWW, ICDCS, MSST, ICPP, P2P, APSys and so on.
She was awarded the Outstanding Teacher of Beijing City in 2011 and the course which she is in charge of achieved National Superfine Course.
Dr. Dai has more than ten research projects including NSFC, 973 programs, 863 project, etc. Her research achievements are summarized as follows:
1) In graph computing system: Graph processing systems have been widely used in enterprises like online social networks to process their daily jobs. With the fast growing of social applications, they have to efficiently handle massive concurrent jobs. However, due to the inherent design for a single job, existing systems incur great inefficiency in terms of memory usage, execution and fault tolerance. Motivated by this issue, Dr. Dai guide her students designed and implemented a novel graph processing system that enables eficient job-level parallelism. The new design allows multiple concurrent jobs to share graph structure data in memory, which fundamentally increases job-level concurrency and reduces fault tolerance overhead which significantly outperforms popular systems in both memory usage and job completion time, when executing concurrent graph jobs.
2) In distributed system: Dr. Dai and her Ph.D student Zhenhua LI published a book “Content Distribution for Mobile Internet: A Cloud-based Approach ” in which through comprehensive real-world measurements, they show their observation that existing content distribution techniques often exhibit poor performance under the settings of cloud computing and mobile Internet. To address the issue, this book investigates content distribution for mobile Internet with a cloud-based approach, by designing novel traffic-saving, energy-efficient, high-speed, and delay-tolerant content distribution techniques and frameworks that automatically adapt to mobile scenarios.
3) In cloud storage system: Dr. Dai and her research group have caught this research for several years. Supported by 973 project, they achieved many results in this area. Recently, Dai and her group have paid more concerns on cost of cloud storage system. They analyze the critical problems encountered by both cloud storage service providers and users from the aspect of cost-efficiency and power-efficiency and presented several solutions for the design of low cost cold and archival storage system for data centers, the design of power-proportional storage cluster, cost-efficient multi-cloud data hosting scheme, and the design of high efficient cloud-based incremental data synchronization system. For each of these problems, they designed the corresponding systems and schemes, and evaluated and analyzed them comprehensively.
