Quantum machine learning for communication network optimization and security( WD_2020_35_WSCH_4)

Post summary

Applications are invited for a PhD position funded by WIT. The candidate is expected to be highly self-motivated, and willing to work in future emerging topics in Quantum Technology.

Position: Quantum machine learning for communication network optimization and security.

Description: 6G is envisaged to be a massively connected complex network capable of rapidly responding to user requirements through real-time learning of the network state as described by the network edge (base station location and cache content), air interface (spectrum range and propagation channel), and client side (battery life and location of user devices). Optimizing this multi-domain, multi-dimensional network state can be viewed as a quantum uncertainty problem. Real-time optimization of complex networks is most suited to machine learning, and the combination of ‘quantum computing algorithms and machine learning’ (QML). As such, QML can be considered as a novel 6G communication enabler. The main aim of this project is to develop QML for optimization and security for a range of networks including low earth orbit (LEO) satellite and unmanned aerial vehicle (UAV) networks. LEO cubesat constellations offer several advantages such as global coverage, small size, cost-effectiveness, low energy consumption, short development time and rapid deployment. UAVs/drones are operated remotely by automation and fly autonomously. The PhD candidate will identify the most promising QML for classical communication network optimization and security and develop the software to realize it. The candidate will implement QML on real quantum computers using software such as IBM Qiskit, and apply it on classical 5G/6G network testbeds.