Multi-Objective DNN-Based Precoder for MIMO Communications

This paper introduces a unified deep neural network (DNN)-based precoder for two-user multiple-input multiple-output (MIMO) networks with five objectives: data transmission, energy harvesting, simultaneous wireless information and power transfer, physical layer (PHY) security, multicasting. First, rotation-based is developed to solve the above problems independently. Rotation-based precoding new allocation scheme that beats existing solutions PHY security multicasting reliable in different antenna settings. Next, DNN-based designed unify solution all objectives. The proposed DNN concurrently learns given by conventional methods, i.e., analytical or solutions. A binary vector as an input feature distinguish Numerical results demonstrate that, compared solutions, reduces on-the-fly computational complexity more than order of magnitude while reaching near-optimal performance (99.45% averaged optimal solutions). also robust variations numbers antennas at receivers.