Abstract
Massive multiple input multiple output (MIMO) has been widely applied in latest wireless communication due to its significant capacity and array gains. In practice, directional antennas rather than omnidirectional ones are used in the large-scale array of base station (BS). And the optimization of its array orientation, i.e., azimuth and tilt angles, becomes the key for realizing massive MIMO gains. In this paper, we first formulate the optimization of BS array orientation for average sum-rate maximization for the channels with hierarchical statistical structure. Via exploiting beamspace statistics to compress the channel statistical representation and employing deep reinforcement learning to relax the requirement on prior channel knowledge, an efficient scheme for azimuth and tilt adjustment is proposed to improve long-term sum-rate performance. Simulations verify that the proposed scheme achieves better performance-complexity tradeoff compared to conventional schemes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.