Scheduling for MIMO broadcast channels with linear receivers and partial channel state information

In multiple-input multiple-output (MIMO) broadcast channels, multiuser diversity is exploited by scheduling data transmission to users with best channel conditions. To find the best set of users, the base station requires knowledge of user channels, which for the case of non-reciprocal uplink and downlink channels will lead to a great increase in feedback overhead. On the other hand, scheduling based on partial channel state information (CSI) often results in a great loss in system throughput. In this paper, a multiuser MIMO technique is presented for MIMO broadcast channels which only requires partial CSI at the base station and achieves a relatively high system throughput. The proposed scheme is a combination of MIMO point-to-point eigenmode transmission with zero-forcing (ZF) linear processing at the receivers. Spatial multiplexing is considered and the optimum number of data streams assigned to each of these two schemes in order to maximize the sum-rate is derived. The results show that with a negligible increase in feedback overhead compared to the case where only ZF linear receiver processing is adopted, the proposed scheme leads to a significant increase in the sum-rate.