Assoc Prof Qi Zhang, Assoc Prof Alexandros Iosifidis
No more applications being accepted
Funded PhD Project (Students Worldwide)
About the Project
A variety of emerging Internet of Things (IoT) applications, e.g., AR/VR, digital twins, autonomous vehicles, and robotic control, require real-time artificial intelligence decision feedback. Neither Cloud-based nor on-device machine learning (ML) can meet the stringent end-to-end latency and service reliability requirements of these time-critical IoT applications. Edge Intelligence, based on Mobile Edge Computing (MEC), has potential to address these challenges by leveraging the distributed computing resource at the network edge.
The primary goal of this PhD project is to develop an agile MEC framework integrating novel ML models by co-design of communication, computing and ML models. It will enable collaborative inference of IoT devices and edge servers to maximize the inference accuracy within a given delay constraint. This project will take into account the time-varying communication and computation resources, as well as resource contention among multiple IoT devices in the design. Additionally, advanced techniques will be designed to accelerate computation task distribution and basic computational blocks in ML. The applicant is expected to be able to develop a prototype of the designed methods and framework to evaluation and validation the results.
Network Computing, Communications and Storage (NETX) Group operates at the intersection of theory and implementation of communication and computation, machine learning, distributed systems, and Cloud/Edge technologies. For this reason, we encourage applicants with a strong theoretical profile or a strong implementation/programming profile (or ideally both) to apply. Our group also counts with a new and well-funded laboratory to deploy large storage server pods, computing servers, ARM micro-servers for energy efficient edge operations, GPU work station, Jetson TX2 board and a number of end-user devices.
Funding Notes
This is a fully funded PhD position.