Parameter optimization and real-time calibration of a measurement-device-independent quantum key distribution network based on a back propagation artificial neural network

Abstract

The parameters choosing (such as probabilities of choosing X-basis or Z-basis, intensity of signal state and decoy state, etc.) and system calibrating will be more challenging when the number of users of a measurement-device-independent quantum key distribution(MDI-QKD) network becomes larger. At present, people usually use optimization algorithms to search the best parameters. This method can find the optimized parameters accurately but may cost lots of time and hardware resources. It's a big problem in large scale MDI-QKD network. Here, we present a new method, using Back Propagation Artificial Neural Network(BPNN) to predict, rather than searching the optimized parameters. Compared with optimization algorithms, our BPNN is faster and more lightweight, it can save system resources. Another big problem brought by large scale MDI-QKD network is system recalibration. BPNN can support this work in real time, and it only needs to use some discarded data generated from communication process, rather than require us to add additional devices or scan the system

Parameter Optimization Based BPNN of Atmosphere Continuous-Variable Quantum Key Distribution

“…Meanwhile, by comparing the two algorithms, we get that a BPNN based CVQKD system furnishes a higher achievable key rate and more efficient parameter optimization. In particular, this approach can be applied to any measurable physical parameter of signals in atmospheric turbulence or fiber channel [ 35 , 39 ].…”

“…Machine learning provides formidable implements for settling matters in many fields, such as estimating parameters, output forecast on the basis of previous input data, data sorting, and pattern identification [ 28 , 29 ]. In recent years, machine learning technology has been diffusely used both in coherent optical communication [ 30 , 31 , 32 , 33 , 34 ] and QKD systems [ 35 , 36 , 37 , 38 , 39 ]. The support vector regression (SVR) is applied to predict the time-along intensity evolutions of the laser light and the LO pulse to improve system performance [ 35 ].…”

“…The support vector regression (SVR) is applied to predict the time-along intensity evolutions of the laser light and the LO pulse to improve system performance [ 35 ]. In addition, for parameter optimization, this has been done with machine learning in measurement-device-independent (MDI) DVQKD [ 38 , 39 ]. Hence, the above-mentioned methods provide an idea for parameter optimization in CVQKD at the atmospheric turbulence channel.…”

Practical issues of twin-field quantum key distribution

“…The number of pulses they both select code mode is NP c 2 and they select decoy mode with intensity x and y respectively is NP P [42,43] is not guaranteed, we choose particle swarm optimization algorithm(PSO) which can optimize the non-smooth function and non-convex function [44] to search the best  v to maximize the R coh .…”

Quantum key distribution and beyond: introduction

“…Novel structures for QKD networks have been presented at access, with wireless functionality [2], and core, featuring reconfigurability [3], layers with Cao et al using software defined networking concepts to design QKD networks [4]. There is also an increasing interest in applying machine learning techniques to optimize the performance of QKD systems [5][6][7]. The security of practical implementations has also been addressed by devising hacking strategies [8][9][10], with their corresponding countermeasures, as well as by accounting for realistic imperfections and finite-key effects in the security analysis [2,11].…”