An Unsupervised Deep Unfolding Framework for Robust Symbol-Level Precoding

Abstract

Symbol Level Precoding (SLP) has attracted significant research interest due to its ability to exploit interference for energy-efficient transmission. This paper proposes an unsupervised deep-neural network (DNN) based SLP framework. Instead of naively training a DNN architecture for SLP without considering the specifics of the optimization objective of the SLP domain, our proposal unfolds a power minimization SLP formulation based on the interior point method (IPM) proximal ‘log’ barrier function. Furthermore, we extend our proposal to a robust precoding design under channel state information (CSI) uncertainty. The results show that our proposed learning framework provides near-optimal performance while reducing the computational cost from $\mathcal{O}(n^{7.5})$ to $\mathcal{O}(n^{3})$ for the symmetrical system case where $n=\text {number of transmit antennas}=\text {number of users}$ . This significant complexity reduction is also reflected in a proportional decrease in the proposed approach’s execution time compared to the SLP optimization-based solution.

Keywords

• Symbol level precoding
• constructive interference
• downlink beamforming
• power minimization
• deep neural networks