Graph Neural Network-based Virtual Network Function Management

Kim, Heegon; Park, Suhyun; Lange, Stanislav; Lee, Do-Young; Heo, DongNyeong; Choi, Heeyoul; Yoo, Jae‐Hyoung; Hong, James Won‐Ki

doi:10.23919/apnoms50412.2020.9237002

Cited by 6 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study extends our previous work 7 in a number of directions. First, we predict the optimal number of VNF instances, rather than the changes in the number of VNF instances.…”

Section: Introductionsupporting

confidence: 86%

Graph neural network‐based virtual network function deployment optimization

et al. 2021

Self Cite

View full text Add to dashboard Cite

Summary Software‐defined networking (SDN) and network function virtualization (NFV) help reduce the operating expenditure (OPEX) and capital expenditure (CAPEX) as well as increase the network flexibility and agility. However, since the network is more dynamic and heterogeneous than before, operators have problems to cope with the increased complexity of managing virtual networks and machines. This complexity is paired with strict time requirements for making management decisions; traditional mechanisms that rely on, for example, integer linear programming (ILP) models are no longer feasible. Machine learning has emerged as one of the possible solution to address network management problems to get near‐optimal solutions in a short time. However, applying machine learning to network management is also not simple and has many challenges. Especially, understanding the network environment is an important problem for designing a machine learning model. In this paper, we proposed to use graph neural network (GNN) for virtual network function (VNF) management. The proposed model solves the complex VNF management problem in a short time and gets near‐optimal solutions. We developed a model by taking into account various network environment conditions so that it can be applied in the actual network environment. Also, through in‐depth experiments, we suggested the direction of the machine learning‐based network management method.

show abstract

“…This study extends our previous work 7 in a number of directions. First, we predict the optimal number of VNF instances, rather than the changes in the number of VNF instances.…”

Section: Introductionsupporting

confidence: 86%

Graph neural network‐based virtual network function deployment optimization

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…To efficiently solve this problem, a bunch of heuristic algorithms are proposed in the literature. Recently, graph-based models have also been used for this problem [69,33,67,38,68,44,19], which can get near-optimal solutions in a short time. To predict future resource requirements for VNFs, a GNN-based algorithm using the VNF forwarding graph topology information is proposed in [69,33].…”

Section: Gnn-basedmentioning

confidence: 99%

“…Similarly, GNN-based algorithms are proposed for VNF resource prediction and management in a series of studies [67,38,44]. On another aspect, DRL is often combined with GNNs for automatic virtual network embedding [48,25,54,13].…”

Section: Gnn-basedmentioning

confidence: 99%

“…GE [85] VNE [25] DRL with GCN GCN [88] VNF Deployment Prediction [67,38] GNN-based Algorithm GNN [82] VNF Management [44] GNN-based Algorithm GNN [82] VNF Placement [19] DRL with GNN GN [91] VNF Resource Prediction [48] Asynchronous DRL enhanced GNN GNN [82] VNF Resource Prediction [69,33] GNN-based Algorithm GNN [82] compared with traditional methods.…”

Section: Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Graph-based Deep Learning for Communication Networks: A Survey

Jiang

2021

Preprint

View full text Add to dashboard Cite

Communication networks are important infrastructures in contemporary society. There are still many challenges that are not fully solved and new solutions are proposed continuously in this active research area. In recent years, to model the network topology, graph-based deep learning has achieved state-of-the-art performance in a series of problems in communication networks. In this survey, we review the rapidly growing body of research using different graph-based deep learning models, e.g. graph convolutional and graph attention networks, in various problems from different communication networks, e.g. wireless networks, wired networks, and software-defined networks. We also present a well-organized list of the problem and solution for each study and identify future research directions. To the best of our knowledge, this paper is the first survey that focuses on the application of graph-based deep learning methods in communication networks. To track the follow-up research, a public GitHub repository is created, where the relevant papers will be updated continuously.

show abstract

“…However, this study only determined the number of VNF instances without considering VNF placement. Thus, the placement of VNF instances was determined by using various approaches 36‐38 based on a graph neural network (GNN) 39 . These studies used a GNN to predict the processing time of VNFs running on each server.…”

Section: Background and Related Workmentioning

confidence: 99%