活动时间： 2018年3月12日 下午3:30-5:30

活动地点： 延长校区 Ⅳ101

报告题目1:面向智慧物联网的关键技术

报告人: Prof. Jiannong Cao,The Hong Kong Polytechnic University

报告摘要：As the Internet becomes increasingly ubiquitous, it is evolving into the communication medium for objects that are embedded in the physical world. The coupling between such objects and a worldwide standard-based communication infrastructure constitutes the Internet of Things (IoT) and is characterized by machine-to-machine (M2M) communications. IoT has many applications including smart cities, logistics, industrial control and healthcare. However, the Internet of Things is still maturing. Currently, IoT technologies still largely focus on the networking aspect of connecting and controlling the things. As the IoT continues to develop, further potential can be realized by a combination with related technology approaches such as Cloud computing, Big Data, and AI. In this talk, I will discuss the current challenges and future development of IoT that adds intelligence to the interconnected objects and their interactions in performing functions and making smart decisions. Such a Smart IoT will facilitate a sustainable platform empowering advanced applications. I will also summarize our research in the past years along this direction.

报告题目2:协作边缘计算中的数据驱动资源管理

报告人: Prof. Song Guo,The Hong Kong Polytechnic University

报告摘要：When accessing cloud-hosted modern applications, users often suffer a significant latency due to the long geo-distance to the central cloud. Edge computing thus emerges as an alternative paradigm that can reduce this latency by deploying services close to users. As data are usually generated on geo-distributed edges, services require the collaboration among them. Allocation of various resources, such as computation units, data and bandwidth between edges, is becoming important. In this talk, we will present our recent studies on data driven resource management among collaborative edges. We will start with our works on cross-cloud resource management, and then propose the new approach on using spatial-temporal request patterns for big data analytics in geo-distributed edges. Some preliminary research results on data-driven data-task joint scheduling will be discussed as well.