Learning Robust Beamforming for MISO Downlink Systems

This letter investigates a learning solution for robust beamforming optimization in downlink multi-user systems. A base station (BS) identifies efficient multi-antenna transmission strategies only with imperfect channel state information (CSI) and its stochastic features. To this end, we propose training algorithm where deep neural network (DNN), which accepts estimates statistical knowledge of the perfect CSI, is optimized to fit real-world propagation environment. Consequently, trained DNN can provide solutions based on observations actual CSI. Numerical results validate advantages proposed approach compared conventional schemes.