Search

Next-generation communication networks are expected to exploit recent advances in data science and cutting-edge communications technologies to improve the utilization of the available communications resources. In this article, we introduce an emerging deep learning (DL) architecture, the transformer-masked autoencoder (TMAE), and discuss its potential in next-generation wireless networks. We discuss the limitations of current DL techniques in meeting the requirements of 5G and beyond 5G networks, and how the TMAE differs from the classical DL techniques can potentially address several wireless communication problems. We highlight various areas in next-generation mobile networks which can be addressed using a TMAE, including source and channel coding, estimation, and security. Furthermore, we demonstrate a case study showing how a TMAE can improve data compression performance and complexity compared to existing schemes. Finally, we discuss key challenges and open future research directions for deploying the TMAE in intelligent next-generation mobile networks., Comment: accepted to appear at IEEE Communications Magazine

Cloud radio-access networks (C-RAN) have been proposed as an enabling technology for keeping up with the requirements of next-generation wireless networks. Most existing works on C-RAN consider the uplink or the downlink separately. However, designing the uplink and the downlink jointly may bring additional advantage, especially if message source-destination information is taken into account. In this paper, this idea is demonstrated by considering pairwise message exchange between users in a C-RAN. A multi-pair two-way transmission scheme is proposed which targets maximizing the end-to-end user data rates. In the proposed scheme, a lattice-based computation strategy is used, where the baseband processing unit (BBU) pool decodes integer linear combinations of paired users' codewords instead of decoding linear combinations of individual codewords. The BBU pool then compresses the computed signals and forwards them to the remote radio heads (RRHs), which decompress the signals and send them to the users. Finally, each user decodes its desired message using its own message as side information. The achievable rate of this scheme is derived, optimized, and evaluated numerically. Results reveal that significant end-to-end rate improvement can be achieved using the proposed scheme compared to existing schemes.