Forecasting SDN End-to-End Latency Using Graph Neural Network

Ge, Zhun; Hou, Jiacheng; Nayak, Amiya

doi:10.1109/icoin56518.2023.10048915

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [19] uses GNN to forecast SDN end-to-end latency with SDN, which can enhance the network's routing strategy. In this paper, GNN is utilized in DQN to learn the network state and allocation method based on deep learning.…”

Section: Methodsmentioning

confidence: 99%

Research on QoS Flow Path Intelligent Allocation of Multi-Services in 5G and Industrial SDN Heterogeneous Network for Smart Factory

et al. 2023

View full text Add to dashboard Cite

In this paper, an intelligent multiple Quality of Service (QoS) constrained traffic path allocation scheme with corresponding algorithm is proposed. The proposed method modifies deep Q-learning network (DQN) by graph neural network (GNN) and prioritized experience replay to fit the heterogeneous network, which is applied for production management and edge intelligent applications of smart factory. Moreover, through designing the reward function, the learning efficiency of the agent is improved under the sparse reward condition, and the multi-object optimization is realized. The simulation results show that the proposed method has high learning efficiency, and strong generalization ability adapting the changing of topological structure of network caused by network error, which is more suitable than the compared methods. In addition, it is also verified that combining the field knowledge and deep reinforcement learning (DRL) can improve the performance of the agent. The proposed method can achieve good performance in the network slicing scenario as well.

show abstract

Section: Methodsmentioning

confidence: 99%

Research on QoS Flow Path Intelligent Allocation of Multi-Services in 5G and Industrial SDN Heterogeneous Network for Smart Factory

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Machine learning methods, such as graph convolutional networks, are an effective alternative to traditional approaches for solving network problems. They are a generalization of traditional convolutional networks [89], are very effective in solving network problems [100], especially in the fields of software-defined networks [17], [91], [40] and internet of things [68], [25].…”

Section: Machine Learningmentioning

confidence: 99%

“…They show that an ensemble of 32 models provides higher prediction accuracy and speedup than traditional schedulability analysis. Ge et al [41] aim to predict end-to-end delay in software defined networking through the use of a spatial-temporal graph convolutional network. Their approach, based on graph neural networks, outperforms other models.…”

Section: Machine Learningmentioning

confidence: 99%

Exploring Trade-offs in Concept Design of Integrated Modular Avionic Platform Configurations : Topology Generation, Resource Adequacy, and Dependability

Saar de Moraes

2024

Linköping Studies in Science and Technology. Dissertations

View full text Add to dashboard Cite

Modern aircraft heavily depend on computer systems to carry out various tasks. From managing flight surfaces and engines to processing radar and imagery data and facilitating communication with other aircraft and ground stations, computers are involved in almost every aspect of an aircraft's operation. These computer systems, known as Integrated Modular Avionics (IMA) systems, have long life cycles that span several decades and undergo regular updates. Despite this, a significant portion of the overall life cycle costs is determined very early in the life cycle, in the concept design phase.Thank you, Tâmara and Rodrigo, for your friendship, our ski trips, and for making me feel at home despite being far from our beloved state in southern Brazil. Thank you, Letícia and Natália, for your friendship and for reminding me that I can still feel as young as you are. To my other Brazilian friends, Amanda, André (both), Gustavo, Daiane, Priscila, Fabricio, Carlos, and Bianca, thank you for all the uncountable moments we have shared.To Veronika, Emma, and Irene: I want to express my gratitude for our enjoyable moments. Thank you for providing a much-needed break from my studies and papers.Lastly, I would like to express my gratitude to my friends in Brazil. Despite the great distance, you kept in touch, offered encouragement during difficult times, and were present when I needed you. Thanks to Gabrieli, Camila, Roberta, Giovana, and Gisele for always making the time to meet me when I visit.

show abstract

NeuralGAP: Deep Learning Evaluation of Networked Avionic Architectures

de Moraes,

Nadjm-Tehrani

2024

2024 19th European Dependable Computing Conference (EDCC)

View full text Add to dashboard Cite

Forecasting SDN End-to-End Latency Using Graph Neural Network

Cited by 5 publications

References 22 publications

Research on QoS Flow Path Intelligent Allocation of Multi-Services in 5G and Industrial SDN Heterogeneous Network for Smart Factory

Research on QoS Flow Path Intelligent Allocation of Multi-Services in 5G and Industrial SDN Heterogeneous Network for Smart Factory

Exploring Trade-offs in Concept Design of Integrated Modular Avionic Platform Configurations : Topology Generation, Resource Adequacy, and Dependability

NeuralGAP: Deep Learning Evaluation of Networked Avionic Architectures

Contact Info

Product

Resources

About