Master Thesis : UE characterization using machine learning
This is an opportunity for a Master of Science student to work with algorithms related to massive antenna beamforming which is a keypart of 5G. The massive demand for the high data rate mobile communication has led to the evolution of the mobile communication networks.
The network evolution aims for the improved capacity and high data rate, but it also increases the processing complexity of the communication network (mainly the base station). Some of the main processing complexity increase is due to increase in processing bandwidth, huge number of antenna elements, and need for shorter processing time. With the introduction of 5G the number of antennas and the processing bandwidth will further increase. Also, the number of user equipment (UE or mobiles) in the network to be processed is huge. This introduces the need for intelligent processing in the base station using which the base station can process the signals from mobile in a selective manner.
Apart from the computational complexity, the available resource for the signal transmissions from mobile to the base station is limited. An intelligent means of sharing the available resource among different user equipment would be very beneficial. Recently lots of research has been done on machine learning and objective of this thesis work is to explore if machine learning can be used to mitigate the above mentioned computational complexity problem.
One parameter that would be very helpful is the knowledge about the UE velocity. If the UE is stationary a lot of computations can be avoided. In order to determine this, a machine learning model could be trained using sounding reference signal and simulated labeled data.
One of the application of this model could be in massive MIMO. UEs will send a sounding reference signal to the base station. This will then be used in the beamforming. In order to stack several UEs on top of each other. The orthogonality between all UEs are calculated. If the UE velocity is known, computations for stationary UEs could be sparser.
- Develop a simulation model for UE characterization using machine learning
- The UE characterization to be used to categorize UE in stationary or moving category (possibly extend moving category with different speed category)
- Generate and capture training data generation needed for the simulation model. This includes sounding reference signal data collection for different UE position
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 and wireless communication, good skills in C/C++ and Matlab plus any working knowledge of Machine learning techniques is an advantage.
As person you are fluent in English, have good analytical capability and good social skills.
For more information, please contact
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 || Stud&YP
Req ID: 254920