End-to-End Key Generation Method in Quantum Key Distribution Networks for Minimizing Session Blocks Using Deep Reinforcement Learning

Journal of Advanced Technology Research, Vol. 9, No. 1, pp. 13-16, Jun. 2024
10.11111/JATR.2024.9.1.013, Full Text:
Keywords: Quantum Key Distribution, Deep Reinforcement Learning, End-to-End Key Generation, Session Block Minimization, GAT, LSTM
Abstract

The advancement of quantum computers and quantum algorithms poses a threat to traditional cryptographic systems. Consequently, Quantum Key Distribution (QKD) technology, which ensures secure communications by leveraging the principles of quantum physics, is gaining attention for securing network communications. However, the generated cryptographic keys in QKD systems are limited in usage and cannot be reused, necessitating efficient key management. In this paper, we propose an optimization technique for QKD key generation and allocation by combining Graph Attention Networks (GAT) and Long Short-Term Memory (LSTM) with Deep Reinforcement Learning (DRL). This approach aims to minimize session block occurrences in QKD networks. Furthermore, we demonstrate through comparative evaluation that this method manages key resources more effectively and reduces blocking occurrences more efficiently than the greedy algorithm.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
Y. Seok, J. Kim, Y. Han, "End-to-End Key Generation Method in Quantum Key Distribution Networks for Minimizing Session Blocks Using Deep Reinforcement Learning," Journal of Advanced Technology Research, vol. 9, no. 1, pp. 13-16, 2024. DOI: 10.11111/JATR.2024.9.1.013.

[ACM Style]
Yeongjun Seok, Ju-Bong Kim, and Youn-Hee Han. 2024. End-to-End Key Generation Method in Quantum Key Distribution Networks for Minimizing Session Blocks Using Deep Reinforcement Learning. Journal of Advanced Technology Research, 9, 1, (2024), 13-16. DOI: 10.11111/JATR.2024.9.1.013.