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

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 the MFI concept is worth reviewing for free-space continuous variable quantum key distribution (CV-QKD) system because of a variety of turbulence effects, the detector noise, the quantization noise and other added noise. This paper proposes the constellation MFI based on density-based spatial clustering of applications with noise (DBSCAN) machine learning algorithm, which is mainly used in the receiver of CV-QKD system. The proposed MFI scheme for QPSK, 8-QAM, 16-QAM, 32-QAM and 64-QAM signals can delivering high accuracy (99%) when signal-to-noise ratio (SNR) is greater than or equal to 15 dB. The simulation results show that using the proposed DBSCAN unsupervised machine learning algorithm can achieve good identification performance. Our resluts also show that the proposed MFI scheme can be further improved at lower SNR by optimizing the algorithm and increasing the number of samples.