Phase Compensation for Continuous Variable Quantum Key Distribution Based on Convolutional Neural Network

Phase drift extremely limits the secure key rate and transmission distance, which is non-negligible in local oscillation continuous variable quantum distribution (LLO CV-QKD). In order to eliminate impact caused by phase drift, we analyze noise of system propose a compensation method based on convolutional neural network (CNN). Moreover, performed signal according estimated value before coherent detection. numerical simulation, compare performance methods CNN Kalman filter (KF), results show that CNN-based has higher accuracy stability.