Yujie TangAssistant Professor, PhD |
 |
My previous research bridges the areas of wireless networking, Internet of Things (IoT), and artificial intelligence (AI). The overarching goal of my research is to develop intelligent networking and computing technologies to support future IoT networks with billions of connected devices and massive data traffic by adopting smart and energy-efficient resource allocation designs. There are three pillars of my research with detailed research topics listed as follows and they are highlighted in the Figure as well:
With the advent of B5G/6G technology, intelligentization will be a crucial solution utilizing data-driven machine learning and artificial intelligence (AI). In the last few years, we have witnessed a growing exploitation of AI solutions in a wide spectrum of communication applications. AI will play a critical role in designing and optimizing B5G/6G architectures, protocols, and operations. Our project will focus on the following topics:
The deployment of IoV requires a combination of various emerging wireless technologies to enable vehicle to everything (V2X) connectivity. In this project, we consider a heterogeneous vehicular connectivity, where vehicles can connect to cellular network base stations (BSs) (wide-area access), roadside units (RSUs) (which can be replaced by small base stations, depending on the infrastructures facilitated in future networks), and other vehicles (peer-to-peer access). Machine learning techniques including model-free reinforcement learning and deep neural networks can be employed. Specifically, we apply AI algorithms to learn a good resource management policy based on the reward/cost feedback by the environment, and quick decisions can be made for a dynamic network once a policy is learned. Moreover, deep neural networks can be adopted to learn the spectrum availability and content popularity, which helps make full use of limited spectrum and cache resources. Ultimately, all the research contributions and outcomes will be integrated into physical IoV networks and smart connected vehicle systems to further advance the engineering of such systems. Our project will focus on the following objectives:
The growth of the IoT, 5G wireless, and AI are all driving the move of computing power to the edge. IoT means more and smarter devices are generating and consuming more data, but in the field far from traditional data centers. There is a huge amount of data that must be collected and analyzed. Sending all the data back to the data center without any edge processing not only adds much latency, but it’s also often too much data to transmit over network connections. Data centers often don’t even have enough room to store all the unfiltered, uncompressed data coming from the edge. Moreover, massive amounts of collected data is required to be online computed in real-time IoT systems. Due to the limited communication, computation, and storage capabilities, it is difficult for IoT devices to complete latency-sensitive computation tasks with their own computing resources. To tackle this issue, edge computing has emerged as an effective solution, which is able to offer intensive computation and storage services at the network edge with relatively light access burden and low transmission delay. Edge computing is promising for computation-intensive applications (such as autonomous and cooperative driving) and storage burdens (video caching) in IoV, and it has been envisioned to pave the way for supporting various applications for road safety, intelligent and green transportation, location-specific services, and in-vehicle Internet access. Our project will focus on the following topics:
