Blind modulation format identification using the DBSCAN algorithm for continuous-variable quantum key distribution

Abstract

Advances in adaptive modulation techniques have fueled the growth of classic communication recently, and the modulation format identification (MFI) has been extensively studied in the field of wireless communication, but in order to make Alice and Bob smoothly enter post-processing and develop toward an adaptive network, the MFI concept is worth reviewing for a continuous-variable quantum key distribution (CV-QKD) system. This paper proposes a constellation MFI scheme based on the density-based spatial clustering of applications with noise (DBSCAN) machine learning algorithm, and the MFI process is set at the receiving end of the CV-QKD system. The proposed MFI scheme for 4-QAM, 16-QAM, 64-QAM, and 256-QAM signals can reach high accuracy (>99%) when the signal-to-noise ratio (SNR) is greater than or equal to 23 dB. The simulation results show that using the DBSCAN unsupervised machine learning algorithm can achieve good identification performance. The proposed MFI scheme can be further improved at lower SNR by optimizing the algorithm and increasing the number of samples.