Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Physica Scripta

Deep reinforcement learning-based multi-objective routing and resource allocation strategy in quantum key distribution optical networks

Li Liu, Zhenjiang Feng, Wenbin Ke, Tingting Song

Published Jul 10, 2026• 0 citations
Publisher

Abstract

Abstract Quantum key distribution (QKD) optical networks, relying on the information-theoretic security guaranteed by the fundamental laws of quantum physics, have become a core solution for ensuring data transmission security in critical fields such as finance and energy. However, QKD optical networks have inherent characteristics like severe resource constraints, dynamic changes in network environments. The collaborative optimization of routing, wavelength, and time-slot assignment (RWTA) has thus become a key bottleneck restricting their practical deployment. Traditional algorithms suffer from high complexity and poor adaptability in large-scale dynamic networks, while existing deep reinforcement learning (DRL) schemes insufficiently consider network security states, failing multi-objective co-optimization. Therefore, this paper proposes a multi-objective secure proximal policy optimization algorithm (MOS-PPO) based on DRL to solve the routing, wavelength, and time slots assignment problem in QKD optical networks. The MOS-PPO algorithm expands the state space by introducing a network security state vector that includes quantum bit error rate, risk coefficient, node capacity, and processing capability. It designs a multi-objective reward function, and establishes a security constraint mechanism to achieve the collaborative optimization of blocking probability (BP), resource utilization (RU), and security performance. Simulations on NSFNET and UBN24 topologies show MOS-PPO outperforms DRL-PPO algorithm, Security-aware Load balancing, first fit algorithm, and random fit algorithm. On NSFNET, average BP drops by 20.4%, 22.1%,28.4%, 36.7% and RU rises by 4.0%,3.9%, 22.2%, 31.0%, on UBN24, BP decreases by 9.3%, 11.4%, 18.8%, and 27.4% and RU increases by 3.8%, 21.2%, 10.3%, and 29.5%, with higher stable security margins. This study verifies the high adaptability and multi-objective optimization ability of the MOS-PPO algorithm in dynamic network environments, providing an efficient RWTA solution for the practical deployment of QKD optical networks.

DOI
10.1088/1402-4896/ae8942

Related papers

Deep reinforcement learning‐based routing and resource assignment in quantum key distribution‐secured optical networks

Purva Sharma, Shubham Gupta, Vimal Bhatia +1 more

Abstract In quantum key distribution‐secured optical networks (QKD‐ONs), constrained network resources limit the success probability of QKD lightpath requests (QLRs). Thus, the selection of an appropriate route and the efficient utilisation of network resources for establishment of QLRs are the essential and challenging problems. This work addresses the routing and resource assignment (RRA) problem in the quantum signal channel of QKD‐ONs. The RRA problem of QKD‐ONs is a complex decision making problem, where appropriate solutions depend on understanding the networking environment. Motivated by the recent advances in deep reinforcement learning (DRL) for complex problems and also because of its capability to learn directly from experiences, DRL is exploited to solve the RRA problem and a DRL‐based RRA scheme is proposed. The proposed scheme learns the optimal policy to select an appropriate route and assigns suitable network resources for establishment of QLRs by using deep neural networks. The performance of the proposed scheme is compared with the deep‐Q network (DQN) method and two baseline schemes, namely, first‐fit (FF) and random‐fit (RF) for two different networks, namely The National Science Foundation Network (NSFNET) and UBN24. Simulation results indicate that the proposed scheme reduces blocking by 7.19%, 10.11%, and 33.50% for NSFNET and 2.47%, 3.20%, and 19.60% for UBN24 and improves resource utilisation up to 3.40%, 4.33%, and 7.18% for NSFNET and 1.34%, 1.96%, and 6.44% for UBN24 as compared with DQN, FF, and RF, respectively.

IET Quantum Communication•Jun 26, 2023•29 citations

Distance-Aware DRL-Based Routing Strategies in QKD-ONs

Shailendra Raghuwanshi, Suman Palrecha, Vimal Bhatia +2 more

Resource constraints in quantum key distribution-secured optical networks (QKD-ONs) frequently prevent successful quantum light-path request (QLR) fulfillment. This work introduces a routing and resource assignment (RRA) strategy prioritizing minimal transmission distance to address this limitation. The proposed scheme employs a metric evaluating fiber length to determine optimal quantum signal paths. By minimizing cumulative (photon) travel distance, the proposed approach improves resource efficiency. The proposed distance-aware deep reinforcement learning (DA-DRL) based scheme’s performance is evaluated against first-fit (FF) and random-fit (RF) methods, across two network topologies NSFNET and UBN24. Simulation results show that, for NSFNET, the proposed approach scheme reduces blocking by 6.18% and 9.18% and for UBN24, by 2.71% and 3.41%, when compared to FF and RF respectively.

Asia Communications and Photonics Conference•Nov 5, 2025•0 citations

Routing Based on Deep Reinforcement Learning in Quantum Key Distribution-secured Optical Networks

Purva Sharma, Vimal Bhatia, Shashi Prakash

Routing is a challenging problem in quantum key distribution (QKD)-secured optical networks (QKD-ONs) and involves the selection of an appropriate route that establishes a secure path between the QKD nodes for secret key distribution. Deep reinforcement learning (DRL) is a promising approach for solving decision-making problems in complex networking environments such as QKD-ONs. By leveraging the capabilities of DRL algorithms, the routing decisions can be optimized to enhance network performance. This paper proposes a DRL-based solution for routing in QKD-ONs that enables the routing agent to learn and adapt to changing network conditions by understanding the networking environment. The performance of the proposed scheme is compared with the baseline schemes on NSFNET in terms of blocking probability. Simulation results indicate that compared to the baseline schemes (shortest path (SP) and hop count (HC)), the proposed DRL-based routing scheme reduces the blocking by 14.31% and 8%, respectively.

IEEE International Conference on Advanced Networks and Telecommunications Systems•Dec 17, 2023•4 citations

Dynamic Security-Aware Resource Allocation in Quantum Key Distribution-Enabled Optical Networks

Vimal Bhatia, Adolph Timothy Kasegenya, Bowen Chen

The demand for secure communication in the age of quantum technologies has driven progress in quantum key distribution (QKD) techniques for optical networks. This research addresses the issues of high blocking probabilities (BPs) and the proper utilization of quantum resources in varying network loads by introducing a novel heuristic approach, termed dynamic security-aware quantum resource allocation (D-SQRA), designed for dynamic resource allocation in QKD-enabled optical networks. We propose two D-SQRA algorithms to employ an adaptive resource assignment (RA) strategy that concurrently addresses routing, wavelength, and time-slot selection while dynamically modifying security levels according to the real-time network load and resource availability. We evaluate the proposed D-SQRA performance against two conventional methods, namely, fixed security quantum resource allocation (F-SQRA) and baseline quantum resource allocation (B-QRA). We discuss the results for NSFNET and UBN24 topologies for network security performance metrics such as network security performance (NSP), BP, quantum key utilization (QKU), and time-slot utilization. The results show that the proposed D-SQRA algorithms provide significant improvement with respect to conventional techniques in addressing proper resource utilization and management by reducing BPs of the new incoming connection requests.

Photonics•Jun 25, 2025•6 citations

Routing and Scheduling of Key Assignment in Optical Networks secured by Quantum Key Distribution

Purva Sharma, Vimal Bhatia, Shashi Prakash

Quantum key distribution (QKD) has potential of providing long-term security as it is based on the fundamental principles of quantum mechanics. Security of information transmitted through optical networks has attracted attention recently due to its vulnerability to attacks post quantum computers. Hence, the integration of QKD into optical networks can significantly improve the security of existing and future optical networks. In QKD-secured optical networks, the quantum channel and the classical channel are integrated into a single optical fiber to reduce the deployment cost of the network infrastructure. However, due to limited network resources in a single optical fiber, the efficient provisioning of network resources (wavelengths and time slots) and blocking are two major issues in such networks. In this work, a resource assignment strategy with scheduling, namely, resource assignment with scheduling (RA-WS) has been proposed for utilization of network resources efficiently. In the RA-WS strategy, the QKD lightpath requests (QLPRs) have been served according to the proposed scheduling criterion. Moreover, the proposed scheduling criterion for routing, wavelength and time-slot assignment (RWTA) can reduce the effect of QLPRs blocking because of the limited network resources. The performance of the proposed RA-WS strategy has been analyzed in terms of blocking probability (BP), success probability of update secret key ($SP_{USK}$), and time-slot utilization ratio (TSUR) with different reserved wavelengths for quantum signal channel (QSCh), i.e.,$W_{Q}$and different time slots ($n_{tr}$). Simulations performed on NSFNET network topology indicate that the RA-WS strategy performs better than the baseline strategy, i.e., resource assignment without scheduling (RA-WOS) in terms of all the considered metrics.

IEEE International Conference on Advanced Networks and Telecommunications Systems•Dec 13, 2021•5 citations

Multi-Dimensional Routing, Wavelength, and Timeslot Allocation (RWTA) in Quantum Key Distribution Optical Networks (QKD-ON)

Xiaosong Yu, Xian Ning, Qingcheng Zhu +4 more

Currently, with the continuous advancement of network and communication technology, the amount of data carried by the optical network is very huge. The security of high-speed and large-capacity information in optical networks has attracted more and more attention. Quantum key distribution (QKD) provides information-theoretic security based on the laws of quantum mechanics. Introducing QKD into an optical network can greatly improve the security of the optical network. In order to reduce the cost of deployment on QKD infrastructure, quantum signals in QKD and classical signals in optical networks are multiplexed in the same fiber by wavelength-division manner. Moreover, due to the limited wavelength resources in an optical fiber, time-division technology is adopted to construct different kinds of channels in QKD system for efficient utilization of wavelength resources. Under such situation, how to satisfy the security requirements of service requests and complete the efficient scheduling of multi-dimensional resources, i.e., wavelengths and timeslots, is a challenging problem. This paper addresses this problem by considering multi-dimensional routing, wavelength, and timeslot allocation (RWTA) in short-distance quantum key distribution optical networks (QKD-ON), in which any two nodes can directly establish a quantum channel, and the maximum distance between any two nodes is less than the distance that can carry out point-to-point quantum key distribution process. While accommodating services with security requirements in QKD optical networks, to avoid the wavelength time-slot fragmentation caused by the constraints of wavelength consistency and time-slot continuity, we propose a time-window-based security orchestration strategy as well as relative-loss of time continuous compactness based RWTA strategy. We conducted the simulations under various scenarios, e.g., different key updating periods and different distributions on wavelength resources, etc., and the results show that the proposed strategy can achieve better performance compared with the baselines in terms of key success rate, key-updating delay, and blocking probability.

Applied Sciences•Dec 31, 2020•23 citations
Abstract Quantum key distribution (QKD) optical networks, relying on the information-theoretic security guaranteed by the fundamental laws of quantum physics, have become a core solution for ensuring data transmission security in critical fields such as finance and energy. However, QKD optical networks have inherent characteristics like severe resource constraints, dynamic changes in network environments. The collaborative optimization of routing, wavelength, and time-slot assignment (RWTA) has thus become a key bottleneck restricting their practical deployment. Traditional algorithms suffer from high complexity and poor adaptability in large-scale dynamic networks, while existing deep reinforcement learning (DRL) schemes insufficiently consider network security states, failing multi-objective co-optimization. Therefore, this paper proposes a multi-objective secure proximal policy optimization algorithm (MOS-PPO) based on DRL to solve the routing, wavelength, and time slots assignment problem in QKD optical networks. The MOS-PPO algorithm expands the state space by introducing a network security state vector that includes quantum bit error rate, risk coefficient, node capacity, and processing capability. It designs a multi-objective reward function, and establishes a security constraint mechanism to achieve the collaborative optimization of blocking probability (BP), resource utilization (RU), and security performance. Simulations on NSFNET and UBN24 topologies show MOS-PPO outperforms DRL-PPO algorithm, Security-aware Load balancing, first fit algorithm, and random fit algorithm. On NSFNET, average BP drops by 20.4%, 22.1%,28.4%, 36.7% and RU rises by 4.0%,3.9%, 22.2%, 31.0%, on UBN24, BP decreases by 9.3%, 11.4%, 18.8%, and 27.4% and RU increases by 3.8%, 21.2%, 10.3%, and 29.5%, with higher stable security margins. This study verifies the high adaptability and multi-objective optimization ability of the MOS-PPO algorithm in dynamic network environments, providing an efficient RWTA solution for the practical deployment of QKD optical networks.
Abstract In quantum key distribution‐secured optical networks (QKD‐ONs), constrained network resources limit the success probability of QKD lightpath requests (QLRs). Thus, the selection of an appropriate route and the efficient utilisation of network resources for establishment of QLRs are the essential and challenging problems. This work addresses the routing and resource assignment (RRA) problem in the quantum signal channel of QKD‐ONs. The RRA problem of QKD‐ONs is a complex decision making problem, where appropriate solutions depend on understanding the networking environment. Motivated by the recent advances in deep reinforcement learning (DRL) for complex problems and also because of its capability to learn directly from experiences, DRL is exploited to solve the RRA problem and a DRL‐based RRA scheme is proposed. The proposed scheme learns the optimal policy to select an appropriate route and assigns suitable network resources for establishment of QLRs by using deep neural networks. The performance of the proposed scheme is compared with the deep‐Q network (DQN) method and two baseline schemes, namely, first‐fit (FF) and random‐fit (RF) for two different networks, namely The National Science Foundation Network (NSFNET) and UBN24. Simulation results indicate that the proposed scheme reduces blocking by 7.19%, 10.11%, and 33.50% for NSFNET and 2.47%, 3.20%, and 19.60% for UBN24 and improves resource utilisation up to 3.40%, 4.33%, and 7.18% for NSFNET and 1.34%, 1.96%, and 6.44% for UBN24 as compared with DQN, FF, and RF, respectively.
Resource constraints in quantum key distribution-secured optical networks (QKD-ONs) frequently prevent successful quantum light-path request (QLR) fulfillment. This work introduces a routing and resource assignment (RRA) strategy prioritizing minimal transmission distance to address this limitation. The proposed scheme employs a metric evaluating fiber length to determine optimal quantum signal paths. By minimizing cumulative (photon) travel distance, the proposed approach improves resource efficiency. The proposed distance-aware deep reinforcement learning (DA-DRL) based scheme’s performance is evaluated against first-fit (FF) and random-fit (RF) methods, across two network topologies NSFNET and UBN24. Simulation results show that, for NSFNET, the proposed approach scheme reduces blocking by 6.18% and 9.18% and for UBN24, by 2.71% and 3.41%, when compared to FF and RF respectively.
Routing is a challenging problem in quantum key distribution (QKD)-secured optical networks (QKD-ONs) and involves the selection of an appropriate route that establishes a secure path between the QKD nodes for secret key distribution. Deep reinforcement learning (DRL) is a promising approach for solving decision-making problems in complex networking environments such as QKD-ONs. By leveraging the capabilities of DRL algorithms, the routing decisions can be optimized to enhance network performance. This paper proposes a DRL-based solution for routing in QKD-ONs that enables the routing agent to learn and adapt to changing network conditions by understanding the networking environment. The performance of the proposed scheme is compared with the baseline schemes on NSFNET in terms of blocking probability. Simulation results indicate that compared to the baseline schemes (shortest path (SP) and hop count (HC)), the proposed DRL-based routing scheme reduces the blocking by 14.31% and 8%, respectively.
The demand for secure communication in the age of quantum technologies has driven progress in quantum key distribution (QKD) techniques for optical networks. This research addresses the issues of high blocking probabilities (BPs) and the proper utilization of quantum resources in varying network loads by introducing a novel heuristic approach, termed dynamic security-aware quantum resource allocation (D-SQRA), designed for dynamic resource allocation in QKD-enabled optical networks. We propose two D-SQRA algorithms to employ an adaptive resource assignment (RA) strategy that concurrently addresses routing, wavelength, and time-slot selection while dynamically modifying security levels according to the real-time network load and resource availability. We evaluate the proposed D-SQRA performance against two conventional methods, namely, fixed security quantum resource allocation (F-SQRA) and baseline quantum resource allocation (B-QRA). We discuss the results for NSFNET and UBN24 topologies for network security performance metrics such as network security performance (NSP), BP, quantum key utilization (QKU), and time-slot utilization. The results show that the proposed D-SQRA algorithms provide significant improvement with respect to conventional techniques in addressing proper resource utilization and management by reducing BPs of the new incoming connection requests.
Quantum key distribution (QKD) has potential of providing long-term security as it is based on the fundamental principles of quantum mechanics. Security of information transmitted through optical networks has attracted attention recently due to its vulnerability to attacks post quantum computers. Hence, the integration of QKD into optical networks can significantly improve the security of existing and future optical networks. In QKD-secured optical networks, the quantum channel and the classical channel are integrated into a single optical fiber to reduce the deployment cost of the network infrastructure. However, due to limited network resources in a single optical fiber, the efficient provisioning of network resources (wavelengths and time slots) and blocking are two major issues in such networks. In this work, a resource assignment strategy with scheduling, namely, resource assignment with scheduling (RA-WS) has been proposed for utilization of network resources efficiently. In the RA-WS strategy, the QKD lightpath requests (QLPRs) have been served according to the proposed scheduling criterion. Moreover, the proposed scheduling criterion for routing, wavelength and time-slot assignment (RWTA) can reduce the effect of QLPRs blocking because of the limited network resources. The performance of the proposed RA-WS strategy has been analyzed in terms of blocking probability (BP), success probability of update secret key (SPUSKSP_{USK}SPUSK​), and time-slot utilization ratio (TSUR) with different reserved wavelengths for quantum signal channel (QSCh), i.e.,WQW_{Q}WQ​and different time slots (ntrn_{tr}ntr​). Simulations performed on NSFNET network topology indicate that the RA-WS strategy performs better than the baseline strategy, i.e., resource assignment without scheduling (RA-WOS) in terms of all the considered metrics.
Currently, with the continuous advancement of network and communication technology, the amount of data carried by the optical network is very huge. The security of high-speed and large-capacity information in optical networks has attracted more and more attention. Quantum key distribution (QKD) provides information-theoretic security based on the laws of quantum mechanics. Introducing QKD into an optical network can greatly improve the security of the optical network. In order to reduce the cost of deployment on QKD infrastructure, quantum signals in QKD and classical signals in optical networks are multiplexed in the same fiber by wavelength-division manner. Moreover, due to the limited wavelength resources in an optical fiber, time-division technology is adopted to construct different kinds of channels in QKD system for efficient utilization of wavelength resources. Under such situation, how to satisfy the security requirements of service requests and complete the efficient scheduling of multi-dimensional resources, i.e., wavelengths and timeslots, is a challenging problem. This paper addresses this problem by considering multi-dimensional routing, wavelength, and timeslot allocation (RWTA) in short-distance quantum key distribution optical networks (QKD-ON), in which any two nodes can directly establish a quantum channel, and the maximum distance between any two nodes is less than the distance that can carry out point-to-point quantum key distribution process. While accommodating services with security requirements in QKD optical networks, to avoid the wavelength time-slot fragmentation caused by the constraints of wavelength consistency and time-slot continuity, we propose a time-window-based security orchestration strategy as well as relative-loss of time continuous compactness based RWTA strategy. We conducted the simulations under various scenarios, e.g., different key updating periods and different distributions on wavelength resources, etc., and the results show that the proposed strategy can achieve better performance compared with the baselines in terms of key success rate, key-updating delay, and blocking probability.