Inter-Mode-Interference-Aware OAM Detector via Deep Learning

Increasing communication bandwidth is a highly effective method for improving communication system throughput. However, the sub-6GHz frequency band is already heavily utilized, which has led to the exploration of higher frequency bands such as sub-terahertz (sub-THz) communication as a key technology for the upcoming 6G era. Unfortunately, sub-THz channels tend to have only line-of-sight (LoS) components due to reflection losses, making it challenging to achieve multiplexing gain through spatial dimension. This paper investigates the practical implications of using orthogonal angular momentum (OAM) signals for multiplexing in LoS scenarios. While being a well-known fact that independent transmit signals conveyed on orthogonal OAM modes keep independence at the receiver side under a perfectly aligned system, here we focus on misaligned system in which inter-mode-interference (IMI) breaks such independence. Inspired by recent advancements in MIMO detection, particularly deep soft interference cancellation (DeepSIC), we propose a hybrid model-based/data-driven detector for misaligned OAM system that aims at achieving minimal symbol error rate via mitigating IMI. Experimental results demonstrate that the proposed detector, named OAM-DeepSIC, outperforms conventional detectors with minimal computational cost.