Talk by Shaoduo Gan: Hybrid Content Delivery System: An Efficient Solution for Cloud Storage Service

06.01.2017 10:00
Europe/Zurich

CAB E 72

Talk by Shaoduo Gan: Hybrid Content Delivery System: An Efficient Solution for Cloud Storage Service

Abstract:

Cloud storage service, such as Dropbox, Google Drive, and OneDrive, are increasingly prevalent within the Internet community. According to a recent measurement on Dropbox, it consumed a volume equivalent to around one-third of the YouTube traffic on some days. This tremendous number of users, along with overwhelming Internet traffic, brings the new challenge to the existing cloud storage system. As an attempt to alleviate the pressure of cloud datacenter and, at the same time, upgrade the data retrieving rate for users, we utilize distributed content delivery technique (P2P Network and Content Delivery Network) to propose a new hybrid system of cloud storage service. According to trace-driven simulations, the proposed system can effectively alleviate the datacenter and improve the data retrieving rate for users. In this talk, I will also describe two of my current work about intelligent data system. The first one aims to help medicine researchers to extract and analyze drug-drug interactions in vast amounts of literature with machine learning. The other project is about a novel database architecture, which makes the production system of a leading security company 100x faster. It can answer queries that it was not originally designed for.

Bio:

Shaoduo's research experience mainly includes distributed system, operating system and intelligent data processing. During his master period, he has published four academic papers on international conference proceedings and two of them are recommended by the China Computer Federation (CCF). His current research focuses on investigating effective data systems for data intensive applications. -->