Dianxin kexue (Mar 2022)
Study of channel state information feedback based on artificial intelligence
Abstract
Accurate acquisition of CSI (channel state information) is the key to the performance of massive MIMO.In current communication systems, when the reciprocity of uplink and downlink is not ideal, codebook-based CSI feedback is used for downlink CSI acquisition.With the increase of antenna scale, codebook-based CSI feedback needs more and more overhead.The CSI feedback compression method based on AI (artificial intelligence) was presented, and the standardization impact, communication process and challenges of CSI feedback based on AI were analyzed.Besides, evaluation results were provided.The evaluation results show that compared with codebook-based CSI feedback based on frequency domain basis vector compression, CSI feedback based on AI can significantly reduce the feedback cost at the same feedback accuracy.