One major factor influencing the coverage and capacity in mobile networks is related to the configuration of the antennas and especially the antenna tilt angle. By utilizing antenna tilt, signal reception within a cell can be improved and interference radiation towards other cells can be effectively reduced, which leads to a higher signal-to-interference-plus-noise ratio received by the users and increased sum data rate in the network. In this work, a method for capacity and coverage optimization using base station antenna electrical tilt in mobile networks is proposed. It has the potential to improve network performance while reducing operational costs and complexity, and to offer better quality of experience for the mobile users. Our solution is based on the application of reinforcement learning and the simulation results show that the algorithm improves significantly the overall data rate of the network, as compared to no antenna tilt optimization. The analysis in this paper focuses on the downlink of the cellular system. For the simulation experiments a multicellular and sectorized mobile network in an urban environment and randomly distributed user terminals are considered. The main contribution in this work is related to the development of a learning algorithm for automated antenna tilting.
