Learning-based multi-criteria user selection method of amorphous cell

The invention relates to a learning-based multi-criteria user selection method of an amorphous cell, and belongs to the technical field of wireless communication. According to the method, users having access to a secondary cell are selected and transmitting power of the users is designed, so that interference between a primary cell and the secondary cell is restrained within certain threshold values; then, the multi-criteria user selection method with high flexibility is used for selecting served secondary users, so that the coverage area of the secondary cell is changed, meanwhile, the system capacity of the secondary cell is maximized, and design of the amorphous cell is achieved. Dynamic adjustment of the shape of the cell can be achieved, meanwhile, the system capacity of the secondary cell is maximized, and a compromise between user fairness and system performance is obtained.