Reflector-assisted cell-free large-scale MIMO network intelligent joint beamforming method

Abstract

The invention relates to the technical field of wireless communication, discloses a reflector-assisted cell-free large-scale MIMO network intelligent joint beamforming method, and solves the problems in the prior art that the optimization design complexity is relatively high, the calculation consumption is relatively large, and real-time optimization solution is difficult to carry out according to the change of an environment channel state. According to the method, based on a deep reinforcement learning method, optimization design of a beamforming vector of a base station and a reflection coefficient matrix of an intelligent reflection surface is carried out according to global channel state information observed in an environment. According to the deep reinforcement learning algorithm designed by the invention, the sum rate of users in the system can be greatly improved, and once the deep neural network after training convergence is obtained, time for optimization solution and computing resource overhead do not exist any more, and rapid and real-time response can be made to the change of the channel state in the environment.

Description

technical field [0001] The invention relates to the technical field of wireless communication, in particular to an intelligent joint beamforming method for a large-scale MIMO (Multi-Input-Multi-Output) network assisted by a reflecting surface. Background technique [0002] In the cellular mobile communication system, due to the attenuation characteristics of electromagnetic waves when propagating in space and the mutual interference between adjacent cells, the communication rate that the cellular network can provide in different locations in space has great differences. The cell-free network (a new type of mobile communication network structure in which each user is served by multiple base stations) can effectively suppress the interference between users and provide a balanced high-speed network coverage within the network coverage through the coordinated service between the base stations. Therefore, it has great application potential in the next generation mobile communicat...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to propose a reflective surface-assisted intelligent joint beamforming method for large-scale MIMO networks without cells, which solves the problem of high complexity of optimization design in the prior art, large calculation consumption, and difficulty in optimizing the beamforming method according to the environment channel. The problem of real-time optimization and solution for state changes

Images