End-to-End Learning for Symbol-Level Precoding and Detection with Adaptive Modulation

Conventional symbol-level precoding (SLP) designs assume fixed modulations and detection rules at the receivers for simplifying the transmit precoding optimizations, which greatly limits the flexibility of SLP and the communication quality-of-service (QoS). To overcome the performance bottleneck of these approaches, in this letter we propose an end-to-end learning based approach to jointly optimize the modulation orders, the transmit precoding and the receive detection for an SLP communication system. A neural network composed of the modulation order prediction (MOP-NN) module and the symbol-level precoding and detection (SLPD-NN) module is developed to solve this mathematically intractable problem. Simulations verify the notable performance improvement brought by the proposed end-to-end learning approach.

Deep Reinforcement Learning based Joint Active and Passive Beamforming Design for RIS-Assisted MISO Systems

Owing to the unique advantages of low cost and controllability, reconfigurable intelligent surface (RIS) is a promising candidate to address the blockage issue in millimeter wave (mmWave) communication systems, consequently has captured widespread attention in recent years. However, the joint active beamforming and passive beamforming design is an arduous task due to the high computational complexity and the dynamic changes of wireless environment. In this paper, we consider a RIS-assisted multi-user multiple-input single-output (MU-MISO) mmWave system and aim to develop a deep reinforcement learning (DRL) based algorithm to jointly design active hybrid beamformer at the base station (BS) side and passive beamformer at the RIS side. By employing an advanced soft actor-critic (SAC) algorithm, we propose a maximum entropy based DRL algorithm, which can explore more stochastic policies than deterministic policy, to design active analog precoder and passive beamformer simultaneously. Then, the digital precoder is determined by minimum mean square error (MMSE) method. The experimental results demonstrate that our proposed SAC algorithm can achieve better performance compared with conventional optimization algorithm and DRL algorithm.

Deep Learning based Efficient Symbol-Level Precoding Design for MU-MISO Systems

The recently emerged symbol-level precoding (SLP) technique has been regarded as a promising solution in multi-user wireless communication systems, since it can convert harmful multi-user interference (MUI) into beneficial signals for enhancing system performance. However, the tremendous computational complexity of conventional symbol-level precoding designs severely hinders the practical implementations. In order to tackle this difficulty, we propose a novel deep learning (DL) based approach to efficiently design the symbol-level precoders. Particularly, in this correspondence, we consider a multi-user multi-input single-output (MU-MISO) downlink system. An efficient precoding neural network (EPNN) is introduced to optimize the symbol-level precoders for maximizing the minimum quality-of-service (QoS) of all users under the power constraint. Simulation results demonstrate that the proposed EPNN based SLP design can dramatically reduce the computing time at the price of slight performance loss compared with the conventional convex optimization based SLP design.