Master Thesis: Machine learning technique for Beam Management in 5G NR RAN at mmWave Frequencies
Massive demand for high speed mobile broadband has been the primary motivation for evolution from 4G to 5G. 5G NR Radio Access network (RAN) is expected to provide very high user throughput (>1Gbps) under 3GPP’s NR enhanced mobile broadband (eMBB) use case. Subsequently, to meet higher user throughput demands requires large radio bandwidth. Therefore, the millimetre wave (mmWave) spectrum has been considered as an enabler of the 5G NR bandwidth requirements because of availability of wider bandwidths. One downfall with higher carrier frequency is that the radio propagation conditions become harsher as the distance between transmitter and receiver increase. To deal with this, Analog Beamforming (ABF) was introduced in 5G NR RAN.
ABF usually involves establishing highly directional transmission links between transmitter and receiver, typically using high-dimensional phased array antenna modules (PAAM). Directional links, however, require fine alignment of the transmitter and receiver beams, this is achieved through a set of operations collectively known as Beam Management which usually involves initial beam establishment, beam refinement and beam tracking.
To achieve perfectly aligned transmitter and receiver beams requires an intelligent beam management algorithm in the RAN, which can be modelled through machine learning methodology.
This thesis work will investigate Machine Learning techniques for Beam Management, mostly in Beam Refining and Beam Tracking. In this context, the thesis will propose and evaluate ML approaches for Beam Management in simulated environments like MATLAB and potentially within a testbed setup. The substantial thesis goals will span relative performance and robustness of evaluated ML techniques compared to traditional techniques for Beam Management.
Thus, the thesis work will involve,
- Investigating prior art to identify existing beam management techniques and potential drawbacks with them
- Proposing a ML technique for Beam management to fill up the lacuna
- Developing a simulation model to evaluate prior art and proposed ML technique and simulating various possible scenarios
We are searching for one or two students that is close to finish an M.Sc. degree in Wireless communication, Electrical Engineering, Computer Engineering, or a similar program.
Knowledge in LTE/5G, machine learning, C/C++ and Matlab is an advantage.
As person you are fluent in English, have good analytical capability and good social skills
This is a on sight position, therefor the student is responsible for accommodation.
Are you in?
Then send in your application (CV, current grades and cover letter written in English collated into one document) as soon as possible.
The application deadline is the 20th of January. The process will be ongoing and we will let you know as soon as we can if you move forward. Any questions? Please email Christian.Sperling@ericsson.com
Ericsson provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetics.
Ericsson complies with applicable country, state and all local laws governing nondiscrimination in employment in every location across the world in which the company has facilities. In addition, Ericsson supports the UN Guiding Principles for Business and Human Rights and the United Nations Global Compact.
This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, training and development.
Ericsson expressly prohibits any form of workplace harassment based on race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetic information.
Primary country and city: Sweden (SE) || || Lund || R&D
Req ID: 263278