报告人：Stuart Clayman 首席研究员 伦敦大学学院
主持人：黎仁蔚
报告时间：2025年10月21日（周二）下午14:00-16:00
报告地点：色情平台 九龙湖校区计算机楼513报告厅
报告摘要：This talk presents the use of packet trimming, which has the ability to provide low latency and low loss at the client. It allows a much better level of control and manageability, compared to existing transport approaches using UDP or TCP. Packet trimming needs support at the sender, in the network, and at the client to achieve the best performance. The approach taken at each of these is presented. For best behaviour and performance, it has to be matched well to the application data, as well as being is highly adaptable to dynamic bandwidth changes. As such, it is ideal for 6G scenarios, where trimming functions can be placed at the edge.
For this talk, we will concentrate on the transmission of video data using the Packet Wash feature of the BPP protocol. There are a number of complexities which need to be considered, but Packet Trimming has great potential for many applications, where some of the data which has a higher priority can be delivered in a managed way, such as video, AR and VR.
报告人简介：Stuart Clayman received his PhD in Computer Science from University College London in 1994. He is currently a Principal Research Fellow at UCL EEE department, and he has worked as a Research Lecturer at Kingston University and at University College London. He co-authored over 100 conference and journal papers. His research interests and expertise lie in the areas of software engineering and programming paradigms; distributed systems; virtualised compute and network systems, network and systems management; sensor systems and smart city platforms, and media delivery systems. He is looking at multi-domain distributed systems, new techniques for large-scale sensor systems, as well as enhanced mechanisms for end-to-end delivery of digital video. He also has extensive experience in the commercial arena undertaking architecture and development for software engineering, distributed systems and networking systems. He has run his own technology start-up in the area of NoSQL databases, sensor data, and digital media.
