Short biography

I had my bachelor study in Electrical and Electronics Engineering at the Federal University of Technology Akure, Nigeria (2012 - 2017). Afterwards, I worked as a graduate assistant in the Computer engineering department of the Federal Polytechnic Offa, Nigeria, for a year before undertaking the position of a Network Operation Center (NOC) trainee at Mainone Cable Company. Motivated by my ambition for further studies, in 2019, I joined the Smart Telecoms and Sensing Networks (SMARTNET) Erasmus Masters program fully funded by the European Union. This earned me two master's degrees, MSc in Smart Telecom and Sensing Network from Aston University, UK and MSc in Electrical and Optical Engineering from Institut Polytechnique de Paris, France. My master's thesis research focused on studying meta-learning techniques for fast adaptation of nonlinear equalizers in long-haul optical networks at the Aston Institute of Photonics. My preference for research in the wireless communication aspect of telecoms prompted my decision to apply and accept the 5GSMARTFACT PhD position on Extreme ultra-reliable low latency communication for industrial radio cells towards 6G at Aalborg University, Denmark. I am interested in machine learning techniques for future wireless networks.

Short description of project objectives

The reconfigurable and flexible manufacturing vision of Industry 4.0 requires the replacement of wirelines with highly reliable wireless connectivity. My project aims to study novel interference management techniques for a new industrial radio cell concept termed industrial wireless subnetworks. An industrial wireless subnetwork is a short-range cell consisting of a controller acting as an access point to some sensors and actuators specifically designed to support highly reliable and sub-millisecond latency communication for local control operations within an industrial robot or a production module. Due to the large numbers of robots and production modules and the mobility of such subnetworks in an industrial environment, it is crucial to study real-time interference management techniques to ensure the reliability of the deployed subnetworks.

My project objectives are as follows;

● Development of the system model of industrial wireless subnetworks considering mobility and ultra-density.

● Investigation of the interference challenges for dense deployment of industrial wireless subnetworks.

● Development of centralized/distributed/hybrid data-driven techniques for power control and channel allocation for extremely dense industrial wireless subnetworks deployment.

● Comparative study of the performance and complexity of the developed interference management techniques.

● Analysis of the adaptability of the developed methods in non-ideal scenarios such as measurement errors, estimation errors and signaling delays.

So far, we have considered modeling static deployment of industrial wireless subnetworks considering log-distance path loss channel model and 2D correlated shadowing propagation model. Furthermore, we have been studying self-supervised graph neural network-aided approaches for power control and channel allocation to manage interference in a dense deployment.