MSc thesis: Channel prediction algorithms design in the presence of non-coherent phase jump from UE

Stockholm, SE
den 19 november 2021
den 1 december 2021
Övriga jobb
As the tech firm that created the mobile world, and with more than 54,000 patents to our name, we've made it our business to make a mark. When joining our team at Ericsson you are empowered to learn, lead and perform at your best, shaping the future of technology. This is a place where you're welcomed as your own perfectly unique self, and celebrated for the skills, talent, and perspective you bring to the team. Are you in?

Come, and be where it begins.

Our Exciting Opportunity

Background and Thesis Objectives

The "curse of mobility" for massive MIMO systems has been recently studied in both academic and internally in Ericsson, which targets on the capacity enhancement in the scenarios where UE is moving fast. It has been observed from both simulations and field tests that the throughput of the system degrades significantly in the TDD massive MIMO network. Channel aging serves as the main problem. Therefore, a reliable channel prediction algorithm has its significant practical meaning.

In academic, prior work focuses on techniques ranging from classical signal processing approach such as Kalman filter to various machine learning techniques such as generative learning. A popular line of thought for channel prediction is to model the channel dynamics based on auto-regressive models, which serves as the basis for classical channel prediction algorithms such as Kalman filter. However, a critical problem arises when consider practical UE antenna RF implementations, that a non-coherent phase occurs every time when UE switches from DL reception and to UL transmission. This non-coherent phase jump breaks the AR modeling on channel dynamics so that the direct application of prior art is foreseen to fail. Other prior works inspired by computer vision techniques focus on predicting channels as images based on generative learning.

The impact of non-coherent phase jump is not clear yet. In practice, the phase jump can be modelled as a scalar random variable. Therefore, its impact disappears when the sample covariance matrix of the MIMO channel serves as the interested feature, for example in the precoding/beamforming applications. Predicting the sample covariance or the eigenvectors associated with it requires further investigation in the massive MIMO system.

In the proposed study topic, this problem will be studied using either new exploration/invention of classic signal processing techniques or machine learning based algorithms.

Research Questions

This thesis project seeks answers to the following research questions:
  • How to design an algorithm that can conquer the negative impact of non-coherent phase jump on channel predictions?
  • Which channel feature should be used in the prediction so that beamforming gain can be achieved?
  • If the phase jump may be modeled as a scalar random variable (or a process) with different distributions, what performance can the designed algorithm achieve? Will there be any performance bound?

Examination Method

The thesis project aims to
  • propose new algorithms targeting the described problem in the massive MIMO systems,
  • implement the proposed algorithm in a MATLAB and/or Python environment and
  • extensively evaluate and compare its performance with benchmark algorithms.

  • The evaluation will be based on the novelty and performance of the proposed algorithm and the clarity of the thesis report.

    The thesis report is expected to contain persuasive arguments and numerical results that clearly show that the proposed algorithm performs close or outperform benchmarking algorithms without unreasonable complexity increase of existing schemes.

    What is available at Ericsson Research (ER)

    At ER, there is an extensively used wireless network simulator, which will be used in the project. There is also related prior work/code/report on this problem. There also exists real world data set that can help algorithms training.

    What´s in it for you?

    Here at Ericsson, our culture is built on over a century of courageous decisions. With us, you will no longer be dreaming of what the future holds - you will be redefining it! You won't develop for the status quo, but will build what replaces it. Joining us is a way to move your career in any direction you want; with hundreds of career opportunities in locations all over the world, in a place where co-creation and collaboration are embedded into the walls. You will find yourself in a speak-up environment where empathy and humanness serve as cornerstones for how we work, and where work-life balance is a priority. Welcome to an inclusive, global company where your opportunity to make an impact is endless!

    What happens once you apply?

    To prepare yourself for next steps, please explore here:

    Location: Kista, Sweden

    Please submit your application in English as soon as possible - we are working continuously with candidate selection.

    For specific questions please reach out to the responsible recruiter: Sylwia Kwiecien

    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 || [[mfield2]]

    Req ID: 617322

    Liknande jobb

    Liknande jobb