PhD position: AI-based Resource Management of Deterministic QoS for (beyond) 5G Networks
Updated: 19 Jul 2019
The research is motivated by 5G (and beyond) telecommunications. Those future, mobile networks are being developed to offer innovative services in domains such as Media & Entertainment (virtual 3D reality), Automotive/Mobility, e-Health and Smart Industry (machine-to-machine communications). The plethora of services are characterized by widely varying traffic characteristics and often highly challenging Quality of Service (QoS) requirements in terms of throughput, latency, packet loss and/or reliability. Moreover, a high degree of user/device mobility and arduous propagation conditions further challenge QoS offering per service or traffic flow.
The goal of the project is to design an architecture and self-learning algorithms that can optimise and guarantee deterministic QoS of individual traffic flows whilst maximizing network resource efficiency. The general QoS architecture for end-to-end communication of heterogeneous types of traffic will include routing and scheduling for each traffic type and admission control possibly with QoS renegotiations and with shaping and spacing. Ideally, the performance of the proposed QoS architecture will be evaluated by using stochastic modelling and queuing theory, in addition to simulations that will complement the mathematical analysis. Employing AI/ML methodologies are strongly encouraged.
We are looking for a brilliant PhD student who has experience in AI/machine learning techniques. The ideal candidate is multidisciplinary, well-versed in probability theory, algorithms, network science, with a background in telecommunications. An open mind for a university-company collaboration on this novel 5G theme is an advantage.
TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. An International Children’s Centre offers childcare and an international primary school. Dual Career Services offers support to accompanying partners. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.
As a PhD candidate you will be enrolled in the TU Delft Graduate School. TU Delft Graduate School provides an inspiring research environment; an excellent team of supervisors, academic staff and a mentor; and a Doctoral Education Programme aimed at developing your transferable, discipline-related and research skills. Please visit www.tudelft.nl/phd for more information.
36 - 38 hours per week