On Transfer Learning for a Fully Convolutional Deep Neural SIMO Receiver

Deep learning has been used to tackle problems in wireless communication including signal detection, channel estimation, traffic prediction, and demapping. Achieving reasonable results with deep learning typically requires large datasets which may be difficult to obtain for every scenario/configuration in wireless communication. Transfer learning (TL) solves this problem by leveraging knowledge and experience gained from one scenario or configuration to adapt a system to a different scenario using smaller dataset. TL has been studied for various stand-alone parts of the radio receiver where individual receiver components, for example, the channel estimator are replaced by a neural network. There has however been no work on TL for receivers where the entire receiver chain is replaced by a neural network. This paper fills this gap by studying the performance of fine-tuning based transfer learning techniques for various configuration mismatch cases using a deep neural single-input-multiple-output(SIMO) receiver. Simulation results show that overall, partial fine-tuning better closes the performance gap between zero target dataset and sufficient target dataset.

Phase Optimization and Relay Selection for Joint Relay and IRS-Assisted Communication

The use of Intelligent Reflecting Surfaces (IRSs) is considered a potential enabling technology for enhancing the spectral and energy efficiency of beyond 5G communication systems. In this paper, a joint relay and intelligent reflecting surface (IRS)-assisted communication is considered to investigate the gains of optimizing both the phase angles and selection of relays. The combination of successive refinement and reinforcement learning is proposed. Successive refinement algorithm is used for phase optimization and reinforcement learning is used for relay selection. Experimental results indicate that the proposed approach offers improved achievable rate performance and scales better with number of relays compared to considered benchmark approaches.

Revisiting Data Recovery Loops in 6G Networks

Mechanisms for data recovery and packet reliability are essential components of the upcoming 6th generation (6G) communication system. In this paper, we evaluate the interaction between a fast hybrid automatic repeat request (HARQ) scheme, present in the physical and medium access control layers, and a higher layer automatic repeat request (ARQ) scheme which may be present in the radio link control layer. Through extensive system-level simulations, we show that despite its higher complexity, a fast HARQ scheme yields > 66 % downlink average user throughput gains over simpler solutions without energy combining gains and orders of magnitude larger gains for users in challenging radio conditions. We present results for the design trade-off between HARQ and higher-layer data recovery mechanisms in the presence of realistic control and data channel errors, network delays, and transport protocols. We derive that, with a suitable design of 6G control and data channels reaching residual errors at the medium access control layer of 5 E-5 or better, a higher layer data recovery mechanism can be disabled. We then derive design targets for 6G control channel design, as well as promising enhancements to 6G higher layer data recovery to extend support for latency-intolerant services.