A Rotation-Based Precoding for MIMO Broadcast Channels With Integrated Services

The problem of merging multiple services over multiple-input multiple-output Gaussian broadcast channels with two receivers is studied. The transmitter provides two independent services: a public (multicast) service with a common message for both users, and a private service with a confidential message intended only for one of the users which is to be kept secret from the other. Under this scenario, a new linear precoding scheme is developed to maximize secrecy-multicast rate region. This scheme decomposes input covariance matrix using rotation matrices and results in a reformulation of the secrecy-multicast capacity region which is easier to be optimized. Next, by finding the distributions to which eigenvalues and rotation angles fit in, a search algorithm is proposed to solve the new capacity expression to find precoding and power allocation matrices. Numerical results illustrate that the proposed precoding method significantly increases the rate region compared to the existing methods.