Master thesis Signal denoising for 6G

Location: Kista, Stockholm

Preferred starting date: Jan. 2025

Extent: 1-2 student, 30hp.

About the company

Founded in 1988, Huawei Technologies is one of the fastest growing telecommunications and network solutions providers in the world. At Huawei Technologies, we look for people who share our vision: to enrich life with communication. We are a leading supplier of next generation telecom networks and currently serve 37 of the world’s top 50 operators. Our people are committed to providing innovative products, services and solutions and understand it as their mission to create long-term value and growth potential for our clients.

The Huawei office in Sweden is the leading overseas R&D office in Huawei, and the Wireless Algorithm group at Huawei Sweden drives innovation for the Huawei Wireless RAN product. We work on both advanced receivers and on Radio Resource Management algorithms, for both LTE and 5G.

Thesis description

5G is posing high requirements on data rate and one alternative to achieve this is to increase the number of antennas on both transmitter and receiver, referred as a MIMO system which also increases the amount of data to be processed, and the need to develop fast and efficient is ever increasing. To this end, the objective of the thesis in general is to study and develop efficient algorithms for transceiver systems of 5G and 6G. It would focus of leveraging algorithms from Machine Learning, Optimization, and apply them to problems in Communication such as Channel Estimation, Denoising, and MIMO detection. In particular, the thesis would focus on one of the two following topics.

1. 
   Denoising methods for Wireless Communication data - Denoising is a central task in several inverse problems that arise in Communication and Signal Processing. The thesis would focus on developing novel denoising methods beyond the canonical linear filtering methods (like SVD) and test their performance on standard benchmarks.
   
   
   


2. 
   Variational Autoencoders (VAE) for modelling channel data - VAEs offer a reasonably rich and efficient way to learn the distribution of the channel data in a wireless communication setting. The thesis would focus on utilizing VAEs in the context of channel estimation and challenges therein, benchmark their performance with conventional channel estimation methods.

Qualifications

• Master student in Electrical Engineering or equivalent.


• A solid theoretical background in areas such as Probability Theory, Linear Algebra, and basic understanding of Convex Optimization and Machine Learning


• Experience in programming with Python (preferably with frameworks for training Neural Networks), MATLAB.


• A positive attitude towards learning.

Contact person

Jinliang Huang

[email protected]