Enabling sub-THz Cloud RANs: Distributed Machine-Learning for Early HARQ Feedback Prediction

Abstract

We propose novel HARQ prediction schemes for Cloud RANs (C-RANs) that use feedback over a rate-limited feedback channel (4 and 8 bits) from the Remote Radio Heads (RRHs) to predict at the User Equipment (UE) the decoding outcome at the BaseBand Unit (BBU) ahead of actual decoding.In particular, we propose a novel dual-input denoising autoencoder that is trained in a joint end-to-end fashion over the whole C-RAN setup. In realistic link-level simulations at 100 GHz in the sub-THz band, we show that a combination of the novel dual-input denoising autoencoder and state-of-the-art SNR-based HARQ feedback prediction achieves the overall best performance in all scenarios compared to other proposed and state-of-the-art single prediction schemes. At very low target error rates down to 1.6 • 10 −5 , this combined approach reduces the number of required transmission rounds by up to 50% compared to always transmitting all redundancy. I. INTRODUCTIONThe need for more bandwidth and higher data rates drives the interest to new and even higher frequency bands. The 3rd Generation Partnership Project (3GPP) has responded to that need with a new work item targeting frequencies up to 71 GHz where large frequency bands are available. In particular, recent advances in hardware have paved the way for using these bands.Lately, these advances shift the focus of next generation mobile standards to even higher bands, i.e. the sub-THz and THz bands, which reach from 100 GHz up to 3 THz [1]. However, such