PhD Studentship: AI/ML-driven Resource Management Framework for 6G MEC-assisted Industrial IoT Networks

This is a 4-year collaborative studentship which requires the candidate to spend two full years based at Coventry University (UK) and two years based at an A*Star Research Institute (Singapore). The PhD student will spend the first 9 months in Coventry, the following 2 years at an A*Star Research Institute, and the last 15 months in Coventry.

Project details

Industrial internet-of-things (IIoT) use cases (e.g., self-driving cars and Industry 4.0) have stringent requirements (e.g., low-latency and high-reliability) that are out of reach of legacy connectivity solutions (e.g., Wi-Fi and 4G). While the advanced 5G features (e.g., time-sensitive networking (TSN) and ultra-reliable low-latency communication (URLLC)) can meet some of these requirements, they fall short in supporting the most demanding use cases. In this context, three technological enablers can collectively overcome the limits of 5G. First, multi-access edge computing (MEC) allows to move the compute and analytics closer to the data, which reduces latency, alleviate traffic load on transport/core networks, and helps achieve privacy-preserving, enabling the dynamic deployment of applications closer to the edge. Second, Open RAN enables the automated closed-loop optimisation of the RAN, which is currently not possible with MEC. Third, artificial intelligence (AI)/machine learning (ML) can collect and capitalize on the massive amount of data at the edge to achieve an efficient management, automation, and optimization of resources, while maintaining integrity and even ownership. These enablers, albeit useful, are complex and not straightforward to combine. Therefore, this project aims at constructing an AI/ML-driven Resource Management Framework for MEC-assisted IIoT networks, where synergies between these technologies are achieved in the IIoT context.

Candidate Specification

• A bachelor’s (honours) degree in a relevant discipline/subject area, preferably from a well-ranked university, with a minimum classification of 2:1 and a minimum mark of 60% in the project element (or equivalent), or an equivalent award from an overseas institution.
• Language proficiency (IELTS overall minimum score of 7.0 with a minimum of 6.5 in each component, or the TOEFL iBT test with a minimum overall score of 95 with a minimum of 21 in each of the four sections).
• The potential to engage in innovative research and to complete the PhD within 4 years.

For further details please visit: https://www.coventry.ac.uk/research/research-opportunities/research-students/making-an-application/research-entry-criteria/

Additional requirements

• Strong background in wireless communications and networking with detailed knowledge of the protocol stack of 5G and Beyond (5G/B5G) networks and their latest architectural enhancements (e.g., multi-access edge computing (MEC), Open RAN and network slicing).
• Good familiarity with typical Industrial internet-of-things (IIoT) use cases and their associated requirements.
• Excellent programming and prototyping skills using e.g., Python, C/C++, Linux networking and community-based open-source software tools.
• Experience in carrying out link- and system-level simulations of wireless networks using publicly available tools (NS3, OMNeT++ and Matlab). Prior hands-on experience on testbeds based on software-defined radios (SDRs) and open-source tools is an added plus.
• Knowledge of artificial intelligence (AI)/machine learning (ML) techniques. Prior experience implementing AI/ML algorithms using well-known frameworks (e.g., PyTorch and TensorFlow) is an advantage.
• Aspiration to achieve high-quality research contributions and publications in leading conferences and journals. Prior research experience and publications are clear advantages.

How to apply

All applications require a covering letter and a 2000-word supporting statement is required showing how the applicant’s expertise and interests are relevant to the project. To find out more about the project please contact Dr Faouzi Bouali .