Compression of the Channel State Information with Deep Learning

This paper proposes the use of deep autoencoders to compress the channel information in a multiple input and multiple output (MIMO) system. Although autoencoders perform lossy compression, they still have adequate usefulness when applied to MIMO system channel state information (CSI) compression. To demonstrate their impact on the CSI, we measure the performance of the system under two different channel models for different compression ratios. We show through simulation that the run-time complexity of this deep autoencoder is irrelative to the compression ratio and that useful compression ratios depend on the channel model and the signal to noise ratio.