Accelerating Virtual Network Embedding with Graph Neural Networks

Virtual Network Embedding (VNE) is an essential component of network virtualization technology. Prior works on VNE mainly focused on resource efficiency and did not address the scalability as a first-grade objective. Consequently, the ever-increasing demand and size render them less-practical. The few existing designs for mitigating this problem either do not extend to multi-resource settings or do not consider the physical servers and network simultaneously. In this work, we develop GraphViNE, a parallelizable VNE solution based on spatial Graph Neural Networks (GNN) that clusters the servers to guide the embedding process towards an improved runtime and performance. Our experiments using simulations show that the parallelism of GraphViNE reduces its runtime by a factor of 8. Also, GraphViNE improves the revenue-to-cost ratio by about 18%, compared to other simulated algorithms.

[1]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[2]  P. Erdos,et al.  On the evolution of random graphs , 1984 .

[3]  Ahmad Khonsari,et al.  DeepViNE: Virtual Network Embedding with Deep Reinforcement Learning , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[4]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[5]  Edoardo Amaldi,et al.  On the computational complexity of the virtual network embedding problem , 2016, Electron. Notes Discret. Math..

[6]  Lei Guo,et al.  Virtual Network Embedding for Multi-Domain Heterogeneous Converged Optical Networks: Issues and Challenges , 2020, Sensors.

[7]  R. L. Thorndike.  Who belongs in the family? , 1953 .

[8]  Hui He,et al.  RLS-VNE: Repeatable Large-Scale Virtual Network Embedding over Substrate Nodes , 2019, 2019 IEEE Global Communications Conference (GLOBECOM).

[9]  Wolfgang Kellerer,et al.  NeuroViNE: A Neural Preprocessor for Your Virtual Network Embedding Algorithm , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[10]  Wolfgang Kellerer,et al.  Boost online virtual network embedding: Using neural networks for admission control , 2016, 2016 12th International Conference on Network and Service Management (CNSM).

[11]  Haipeng Yao,et al.  A Continuous-Decision Virtual Network Embedding Scheme Relying on Reinforcement Learning , 2020, IEEE Transactions on Network and Service Management.

[12]  B. Bollobás.  The evolution of random graphs , 1984 .

[13]  Fatemeh Hosseini,et al.  Probabilistic Virtual Link Embedding Under Demand Uncertainty , 2019, IEEE Transactions on Network and Service Management.

[14]  Kunli Zhang,et al.  DROI: Energy-efficient virtual network embedding algorithm based on dynamic regions of interest , 2020, Comput. Networks.

[15]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[16]  Tong Li,et al.  Automatic Virtual Network Embedding: A Deep Reinforcement Learning Approach With Graph Convolutional Networks , 2020, IEEE Journal on Selected Areas in Communications.

[17]  Haipeng Yao,et al.  A novel dynamic programming inspired algorithm for embedding of virtual networks in future networks , 2020, Comput. Networks.

[18]  Yonggang Wen,et al.  Toward profit-seeking virtual network embedding algorithm via global resource capacity , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[19]  Panagiotis Papadimitriou,et al.  Network Service Embedding with Multiple Resource Dimensions , 2020, NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium.

[20]  Feng Tian,et al.  NoViSec: Novel Virtual Network Mapping Framework for Secure Software-Defined Networking , 2020, 2020 IEEE Wireless Communications and Networking Conference Workshops (WCNCW).

[21]  Chengqi Zhang,et al.  Learning Graph Embedding With Adversarial Training Methods , 2019, IEEE Transactions on Cybernetics.