Deep Reinforcement Learning-Based Routing and Spectrum Assignment of EONs by Exploiting GCN and RNN for Feature Extraction

Xu, Liufei; Huang, Yue-Cai; Xue, Yun; Hu, Xiaohui

doi:10.1109/jlt.2022.3175865

Cited by 19 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optical networks are usually modelled as graphs and so ideally lend themselves as inputs to graph neural networks. Recently there have been works that apply graph neural networks in the context of reinforcement learning (RL) to the RWA problem in optical networks 23,24 . These works however are only compared to heuristics, where sometimes they perform better and sometimes worse.…”

Section: Message Passing Neural Network (Mpnn)mentioning

confidence: 99%

“…This makes it difficult to learn a general relationship between these features and the performance parameters as the structure and physical properties of graphs have a significant impact on overall network performance. More recently there have been many works that look at applying reinforcement learning to solve the RWA problem [20][21][22][23][24] . These works are promising works in applying novel combinatorial optimisation techniques to the RWA problem, however still do not achieve performance comparable to ILP solutions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent design of optical networks: which topology features help maximise throughput in the nonlinear regime?

Bayvel

Luo

Matzner

et al. 2020

2020 European Conference on Optical Communications (ECOC)

View full text Add to dashboard Cite

One of the key performance metrics for optical networks is the maximum achievable throughput for a given network. Determining it however, is an NP-hard optimisation problem, often solved via computationally expensive integer linear programming (ILP) formulations, infeasible to implement as objectives, even on very small node scales of a few tens of nodes. Alternatively heuristics are used, although these too require considerable computation time for large numbers of networks. There is, thus, a need for ultra-fast and accurate performance evaluation of optical networks. For the first time, we propose the use of a geometric deep learning model, message passing neural networks (MPNN), to learn the relationship between, node and edge features, the structure and the maximum achievable throughput of networks. We demonstrate that MPNNs can accurately predict the maximum achievable throughput while reducing the computational time by up to 5-orders of magnitude compared to the ILP for small networks (10-15 nodes) and compared to the heuristic for large networks (25-100 nodes) -proving their suitability for the design and optimisation of optical networks on different time-and distance-scales.

show abstract

Section: Message Passing Neural Network (Mpnn)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Intelligent design of optical networks: which topology features help maximise throughput in the nonlinear regime?

Bayvel

Luo

Matzner

et al. 2020

2020 European Conference on Optical Communications (ECOC)

View full text Add to dashboard Cite

show abstract

“…In [16], they used the Q-routing method to decide how to forward packages in the LEO satellite network. In [17], deep reinforcement learning was used to solve the routing problem; they used the neural network to replace Q-tables to store Q values. They both use centralized routing algorithms that viewed all satellite nodes as the agent that learned packet forwarding policies as it interacted with the network.…”

Section: Introductionmentioning

confidence: 99%

Fast-Convergence Reinforcement Learning for Routing in LEO Satellite Networks

Ding,

Liu,

Tian

et al. 2023

Sensors

View full text Add to dashboard Cite

Fast convergence routing is a critical issue for Low Earth Orbit (LEO) constellation networks because these networks have dynamic topology changes, and transmission requirements can vary over time. However, most of the previous research has focused on the Open Shortest Path First (OSPF) routing algorithm, which is not well-suited to handle the frequent changes in the link state of the LEO satellite network. In this regard, we propose a Fast-Convergence Reinforcement Learning Satellite Routing Algorithm (FRL–SR) for LEO satellite networks, where the satellite can quickly obtain the network link status and adjust its routing strategy accordingly. In FRL–SR, each satellite node is considered an agent, and the agent selects the appropriate port for packet forwarding based on its routing policy. Whenever the satellite network state changes, the agent sends “hello” packets to the neighboring nodes to update their routing policy. Compared to traditional reinforcement learning algorithms, FRL–SR can perceive network information faster and converge faster. Additionally, FRL–SR can mask the dynamics of the satellite network topology and adaptively adjust the forwarding strategy based on the link state. The experimental results demonstrate that the proposed FRL–SR algorithm outperforms the Dijkstra algorithm in the performance of average delay, packet arriving ratio, and network load balance.

show abstract

ENCG-DRL for multicast service oriented energy-efficient DU-CU deployment and RMSA in EON-enabled RAN

Zhang,

Wang,

Wang

et al. 2024

Optical Fiber Technology

View full text Add to dashboard Cite

Deep Reinforcement Learning-Based Routing and Spectrum Assignment of EONs by Exploiting GCN and RNN for Feature Extraction

Cited by 19 publications

References 20 publications

Intelligent design of optical networks: which topology features help maximise throughput in the nonlinear regime?

Intelligent design of optical networks: which topology features help maximise throughput in the nonlinear regime?

Fast-Convergence Reinforcement Learning for Routing in LEO Satellite Networks

ENCG-DRL for multicast service oriented energy-efficient DU-CU deployment and RMSA in EON-enabled RAN

Contact Info

Product

Resources

About