Channel Estimation for Reconfigurable Intelligent Surface-aided 6G NOMA Systems using CNN-based Quantum LSTM Model

With the rapid development of communication applications, the integration of reconfigurable intelligent surface (RIS) and non-orthogonal multiple access (NOMA) techniques has emerged as a promising approach to enhance connectivity and data transmission rate in future wireless networks. To successfully deploy RIS-NOMA aided 6G network, an accurate channel estimation is a crucial task. Quantum machine learning (QML) is a novel approach showing potential computational advantages in various problems of 6G wireless communications. However, its application, particularly in channel estimation, remains largely theoretical rather than adopted in practice. We propose a hybrid quantum-classical neural network model based on convolutional neural network (CNN) and quantum long short-term memory (QLSTM) for channel estimation in RIS-aided 6G NOMA system. Our results show that the proposed CNN-QLSTM model has a better channel prediction compared to its classical counterpart with regard to root mean square error (RMSE) and mean absolute error (MAE).