Quantum key distribution (QKD) parameter optimization is crucial for maximizing secure key rates. However, the commonly used Local Search Algorithm (LSA) exhibits significant limitations in certain protocols due to non-convexity or excessively narrow parameter spaces. To address this, neural network-based approaches have been proposed to shift the computational burden offline, enabling rapid parameter prediction at runtime without repeated optimization. This paper proposes a neural network framework incorporating genetic algorithms (GA) for QKD parameter optimization. We develop a customized GA to generate high-quality training data and employ a multi-head residual neural network. To rigorously evaluate the impact of the optimization algorithm on learning performance, we train separate models using datasets generated by GA and LSA, respectively. Experimental validation demonstrates that GA-based models achieve substantial performance gains, yielding higher$R^{2}$and significantly reducing prediction errors (RMSE and MAE) compared to LSA-based models for both symmetric and asymmetric BB84 protocols.
Quantum key distribution (QKD) parameter optimization is crucial for maximizing secure key rates. However, the commonly used Local Search Algorithm (LSA) exhibits significant limitations in certain protocols due to non-convexity or excessively narrow parameter spaces. To address this, neural network-based approaches have been proposed to shift the computational burden offline, enabling rapid parameter prediction at runtime without repeated optimization. This paper proposes a neural network framework incorporating genetic algorithms (GA) for QKD parameter optimization. We develop a customized GA to generate high-quality training data and employ a multi-head residual neural network. To rigorously evaluate the impact of the optimization algorithm on learning performance, we train separate models using datasets generated by GA and LSA, respectively. Experimental validation demonstrates that GA-based models achieve substantial performance gains, yielding higherR2and significantly reducing prediction errors (RMSE and MAE) compared to LSA-based models for both symmetric and asymmetric BB84 protocols.
Quantum key distribution (QKD) enables two remote users to share a string of key bits with information-theoretical security. Parameter optimization is a crucial step in achieving optimal performance in practical QKD systems. In general, such optimization is implemented using a local search algorithm (LSA). However, LSAs inevitably fail to find out the optimal values when the searched key rate function is nonconvex or has a discontinuity of first-order derivatives and a narrow parameter search space. This paper proposes a genetic algorithm-based method to overcome the limitations of LSAs for QKD parameter optimization. We tested the proposed method with various types of common QKD protocols and found that it has very high parameter optimization performance for QKD with a time consumption comparable to that using a standard LSA. We expect our method to be a valuable optimization tool for quantum information processing tasks.
For a practical quantum key distribution (QKD) system, parameter optimization, the choice of intensities and the probabilities of sending them, is a crucial step in gaining optimal performance, especially when one realistically considers a finite communication time. With the increasing interest in the field to implement QKD over free space on moving platforms, such as drones, handheld systems, and even satellites, one needs to perform parameter optimization with low latency and with very limited computing power. Moreover, with the advent of the internet of things, a highly attractive direction of QKD could be a quantum network with multiple devices and numerous connections, which provides a huge computational challenge for the controller that optimizes parameters for a large-scale network. Traditionally, such an optimization relies on brute-force search or local search algorithms, which are computationally intensive, and will be slow on low-power platforms (which increases latency in the system) or infeasible for even moderately large networks. In this work we present a method that uses a neural network to directly predict the optimal parameters for QKD systems. We test our machine learning algorithm on hardware devices including a Raspberry Pi 3 single-board computer (similar devices are commonly used on drones) and a mobile phone, both of which have a power consumption of less than 5 W, and we find a speedup of up to two to four orders of magnitude when compared to standard local search algorithms. The predicted parameters are highly accurate and can preserve, e.g., over 95%--99% of the optimal secure key rate for a given protocol. Moreover, our approach is highly general and can be applied effectively to various kinds of common QKD protocols.
Abstract As the number of users in quantum key distribution (QKD) networks continues to grow, parameter selection (e.g., probability of X-bases, signal state strength, and decoy state levels) has become increasingly complex. Traditional methods such as local search algorithms (LSA) are commonly employed for parameter optimization but suffer from significant computational overhead, slow execution on low-power platforms, and resultant system delays. These limitations hinder the scalability and real-time requirements of large-scale QKD networks. To address these challenges, this paper proposes an innovative approach that combines Bayesian optimization with XGBoost model to optimize QKD system parameters. The proposed model is evaluated against random forest (RF) and back-propagation neural network (BPNN) models based on three critical metrics: prediction accuracy, model fitting, and training efficiency. Simulation results demonstrate that the proposed model significantly outperforms both RF and BPNN in terms of accuracy and computational efficiency. Notably, while achieving predictive performance comparable to LSA, the proposed method reduces computation time by three orders of magnitude. This research introduces a novel and efficient framework for QKD parameter optimization, providing new insights and directions for enhancing the performance, scalability, and real-time adaptability of QKD systems.
In the continuous-variable quantum key distribution (CV-QKD) system, the secret key rate (SKR) and transmission distance are important factors to evaluate the quality of system. Numerical methods are commonly employed to compute SKR of QKD systems in practice, but it is difficult to find the optimal parameter to enhance SKR. In this paper, we propose a machine learning-based parameter optimization scheme of CV-QKD. The proposed scheme applies the genetic algorithm-back propagation neural network (GA-BPNN) to CV-QKD to learn the mapping relationship between SKR and modulation variance. According to the property that the mapping relationship is a concave function, the optimal modulation variance can be determined by bisection, and then SKR can be enhanced. Simulation results demonstrate that the proposed scheme can enhance SKR and transmission distance.
Abstract For a practical continuous-variable quantum key distribution (CV-QKD) system, the optimization of modulation variance is crucial for promoting protocol performance. The optimization relies on algorithms like local search in general. But the efficiency of local search methods is limited in low latency and limited computing power scenarios due to their high computational consumption. Hence, this optimization approach is infeasible for satellite-based CV-QKD due to satellites’ low power feature. In this paper, a neural network model that directly predicting the optimal modulation variance in nearly real time is proposed for free space gaussian modulated CV-QKD protocols. This work enhances the feasibility of implementing CV-QKD in low-Earth-orbit satellite scenarios, where typical link durations of few seconds demand rapid parameter optimization. Moreover, a simulation platform for free space CV-QKD protocol, which employs the precise orbital model to extract the elevation angle and the transmission length, is designed and developed to generate training sets that make the neural network model more practical. Our work can be used as a foundation to support parameter prediction for future quantum communication satellite missions.
This paper proposes an optimization of Quantum Key Distribution (QKD) Networks using Graph Neural Networks (GNN) framework. Today, the development of quantum computers threatens the security systems of classical cryptography. Moreover, as QKD networks are designed for protecting secret communication, they suffer from multiple operational difficulties: adaptive to dynamic conditions, optimization for multiple parameters and effective resource utilization. In order to overcome these obstacles, we propose a GNN-based framework which can model QKD networks as dynamic graphs and extracts exploitable characteristics from these networks' structure. The graph contains not only topological information but also specific characteristics associated with quantum communication (the number of edges between nodes, etc). Experimental results demonstrate that the GNN-optimized QKD network achieves a substantial increase in total key rate (from 27.1 Kbits/s to 470 Kbits/s), a reduced average QBER (from 6.6% to 6.0%), and maintains path integrity with a slight reduction in average transmission distance (from 7.13 km to 6.42 km). Furthermore, we analyze network performance across varying scales (10 to 250 nodes), showing improved link prediction accuracy and enhanced key generation rate in medium-sized networks. This work introduces a novel operation mode for QKD networks, shifting the paradigm of network optimization through adaptive and scalable quantum communication systems that enhance security and performance.