Master Thesis presentation by Simon Svensson and Axel Lundberg

Examiner: Giuseppe Durisi

Opponent: Sena Bayraktaroglu

Abstract:
Aligning beams in the initial access of beam management is a challenging and time-
consuming process. Especially, when the number of antenna elements grow large
to compensate for high path loss of millimeter waves. Machine learning methods
have successfully been applied to the problem of beam selection and perform much
better than traditional methods like exhaustive search. In this thesis, some different
machine learning approaches are investigated: decision tree, random forest, Adap-
tive Boosting (AdaBoost), Support Vector Machine (SVM), Multi-level Perceptron
(MLP), Q-learning, Deep Q Learning (DQN) and Double Deep Q Learning (DDQN).
Each model is adapted to specific scenarios with different pre-processing steps. A
total of three scenarios are explored which have been defined by 3rd Generation
Partnership Project (3GPP): Urban Micro (UMi), Urban Macro (UMa) and Rural
Macro (RMa). UMi and UMa are both implemented with an explicit city layout con-
taining static receivers. RMa is uniformly distributed and divided into two datasets:
one for static receivers and one for dynamic receivers along tracks. Each scenario has
been generated by QuaDRiGa which is a stochastic channel model. The aim of the
thesis is to provide a fair comparison of machine learning models by testing them on
data from one simulator. Results show that random forest and AdaBoost perform
best overall on all datasets with up to 90 % accuracy when predicting the optimal
beam pair, which suggests that the search space can be significantly reduced.

Welcome!
Simon, Axel and Giuseppe