Master thesis: Behavioral Modeling of Power Amplifiers and Digital Predistortion With Modern Machine
In a commercial radio network, Radio Unit serve as an important link between physical layer and higher layers of the communication network.
Modern wireless communication systems such as 4G/5G and 802.11 based systems utilize nonconstant-envelope I/Q modulated signals such as OFDM. Due to the high PAPR, such signals will naturally excite the nonlinearities of the TX chain, especially of the power amplifier. In order to compensate for this nonlinear behavior, different techniques can be applied in the transmitter digital domain, with digital predistortion (DPD) being the most popular. In this context, behavioral modeling techniques predicting the nonlinearity of the power amplifier (PA) and DPD solutions are of particular interest.
This thesis will firstly investigate a behavioral modeling scheme for RF PAs employing modern machine learning (ML) techniques and then, possible ML applications will be considered in DPD solutions. The performance of different ML methods such as decision tree, random forest, gradient boosting, k-nearest neighbor and neural network will be evaluated with measured data from different commercial base-station (Ericsson) PAs excited with wideband 5G NR signals. Finally, we will compare their performance to conventional memory polynomial (MP) and look-up-table (LUT) based techniques in terms of normalized mean squared error (NMSE) and adjacent channel error power ratio (ACEPR), considering wideband 5G new radio (NR) waveforms.
During your time at Ericsson, you will be assigned to a research project, aligned with your individual interests, background, and skills. For Master theses, these projects are usually assigned for five months. You will work together with experienced Engineers in a truly international team.
- You will work on topics at the forefront of technology developing new concepts and related to radio, algorithms and architecture solutions for Ericsson Radio.
- You will work on exciting projects considering new uses cases in the industrial or automotive domain.
- You will help to develop world-leading concepts and solutions for current and future Radios systems which will turn the visions of the Networked Society and the Internet of Things (IoT) into reality.
- The student is expected to submit a comprehensive thesis report at the end of the thesis. Also, the complete source code used for carrying out the thesis work will be treated as Ericsson intellectual property.
- Enrolled as Master student in Electrical Engineering, Computer Science, or a related field
- Must have knowledge of data analysis techniques.
- Interest in wireless communication technology.
- Eager to learn, self-driven and open-minded as well as very good team working skills
- Computer and programming skills, e.g. MATLAB, python etc.
- Fluency in English
- Applications should include a short motivation letter, a CV (in English) and a record of transcript. Please mention also the position reference in your motivation letter.
- The position can only be offered to students currently enrolled in a university program.
- For more information, please contact the Recruitment Specialist, Sylwia Kwiecien at firstname.lastname@example.org
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) || || Stockholm || Stud&YP
Req ID: 288526