专题

2017.11.23 学术报告:Data-driven network analytics in SDN-based programmable optical networks

时间:2017-11-23  来源:瞬态室文本大小:【 |  | 】  【打印

报告题目:Data-driven network analytics in SDN-based programmable optical networks
报告人:延双毅 副研究员
报告时间:2017年11月23日下午15:00        
报告地点:瞬态室三楼会议室


报告摘要

    In future dynamic and programmable optical networks, network planning and network optimization require real-time feedbacks from network performance monitoring, to deliver reliable network services. Data analytics over the designed network configuration and monitoring database (CMDB) could enhance current network functions and bring new possibilities in optical networks. In this report, we summarize our recent work in data-driven network analytics for the software-defined network (SDN) based programmable optical networks. For the first time, we demonstrated the machine-learning technology running in the CMDB to predict the unestablished link performance and help to plan network efficiently. The demonstration was done in an optical field-trail testbed, which is comprised of a 436.4-km fiber link.


个人简历

                       
    Dr Shuangyi Yan is a lecturer in High Performance Networks group at department of Electrical & Electronic Engineering, University of Bristol. He received the B.E degree in information engineering from Tianjin University, Tianjin, China in 2004. In 2009, he got the PhD degree in optical engineering from Xi’an Institute of Optics and Precision Mechanics, CAS, Xi’an, China. His doctoral dissertation focused on key technologies in ultra-high-speed optical communication networks, such as ultra-short optical pulse generation, high bandwidth optical signal processing. From 2011 to 2013, He worked on the spectra-efficient long-haul transmission system and low-cost short-range transmission system in Photonics Research Centre, Dept. EIE of the Hong Kong Polytechnic University, Hong Kong. In July 2013, he joined the High Performance Networks Group at University of Bristol as a senior research associate. His research interests include multi-dimensional programmable optical networks for future 5G applications, multi-layer network analytics for network optimization, and next generation data center networks. He is currently working on different national and European projects (e.g., INSIGHT, TOUCAN, COSIGN, The Photonics Hyperhighway). He is the author or co-author of over 50 publications, of which consist 6 patents and several post deadline papers in optical communication related top-level conferences.