Topology-Aware Prediction of Virtual Network Function Resource Requirements

Network functions virtualization (NFV) continues to gain attention as a paradigm shift in the way telecommunications services are deployed and managed. By separating network function from traditional middleboxes, NFV is expected to lead to reduced capital expenditure and operating expenditure, and to more agile services. However, one of the main challenges to achieving these objectives is how physical resources can be efficiently, autonomously, and dynamically allocated to virtualized network function (VNF) whose resource requirements ebb and flow. In this paper, we propose a graph neural network-based algorithm which exploits VNF forwarding graph topology information to predict future resource requirements for each VNF component (VNFC). The topology information of each VNFC is derived from combining its past resource utilization as well as the modeled effect on the same from VNFCs in its neighborhood. Our proposal has been evaluated using a deployment of a virtualized IP multimedia subsystem, and real VoIP traffic traces, with results showing an average prediction accuracy of 90%, compared to 85% obtained while using traditional feed-forward neural networks. Moreover, compared to a scenario where resources are allocated manually and/or statically, our technique reduces the average number of dropped calls by at least 27% and improves call setup latency by over 29%.

[1]  Zhijia Chen,et al.  Self-Adaptive Prediction of Cloud Resource Demands Using Ensemble Model and Subtractive-Fuzzy Clustering Based Fuzzy Neural Network , 2015, Comput. Intell. Neurosci..

[2]  Wentong Cai,et al.  Network-Aware Server Placement for Highly Interactive Distributed Virtual Environments , 2008, 2008 12th IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications.

[3]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

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

[5]  Paola Grosso,et al.  Linux containers networking: Performance and scalability of kernel modules , 2016, NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium.

[6]  Vincenzo Suraci,et al.  An approximate dynamic programming approach to resource management in multi-cloud scenarios , 2017, Int. J. Control.

[7]  Mohamed Faten Zhani,et al.  Dynamic Heterogeneity-Aware Resource Provisioning in the Cloud , 2013, IEEE Transactions on Cloud Computing.

[8]  Raouf Boutaba,et al.  On orchestrating virtual network functions , 2015, 2015 11th International Conference on Network and Service Management (CNSM).

[9]  Junaid Qadir,et al.  Machine learning based optimized live virtual machine migration over WAN links , 2017, Telecommun. Syst..

[10]  Marin Litoiu,et al.  Cloud Adaptation with Control Theory in Industrial Clouds , 2016, 2016 IEEE International Conference on Cloud Engineering Workshop (IC2EW).

[11]  William A. Kirk,et al.  Banach Spaces: Introduction , 2011 .

[12]  Jeremy Kepner,et al.  Scalability of VM provisioning systems , 2016, 2016 IEEE High Performance Extreme Computing Conference (HPEC).

[13]  Jeff Heaton,et al.  Introduction to Neural Networks for C#, 2nd Edition , 2008 .

[14]  Ah Chung Tsoi,et al.  Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[15]  Franco Scarselli,et al.  A Comparison between Recursive Neural Networks and Graph Neural Networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[16]  Nicola Mazzocca,et al.  The dynamic placement of virtual network functions , 2014, 2014 IEEE Network Operations and Management Symposium (NOMS).

[17]  Joan Serrat,et al.  Management and orchestration challenges in network functions virtualization , 2016, IEEE Communications Magazine.

[18]  Dimiter R. Avresky,et al.  Proactive Cloud Management for Highly Heterogeneous Multi-cloud Infrastructures , 2016, 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).

[19]  Joan Serrat,et al.  Server placement and assignment in virtualized radio access networks , 2015, 2015 11th International Conference on Network and Service Management (CNSM).

[20]  Raouf Boutaba,et al.  On Orchestrating Virtual Network Functions in NFV , 2015, ArXiv.

[21]  J.C. Principe,et al.  Backpropagation through time with fixed memory size requirements , 1993, Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop.

[22]  Otto Carlos Muniz Bandeira Duarte,et al.  Orchestrating Virtualized Network Functions , 2015, IEEE Transactions on Network and Service Management.

[23]  Filip De Turck,et al.  Network Function Virtualization: State-of-the-Art and Research Challenges , 2015, IEEE Communications Surveys & Tutorials.

[24]  Joan Serrat,et al.  Contributions to Efficient Resource Management in Virtual Networks , 2014, AIMS.

[25]  Raouf Boutaba,et al.  A connectionist approach to dynamic resource management for virtualised network functions , 2016, 2016 12th International Conference on Network and Service Management (CNSM).

[26]  Quanyan Zhu,et al.  Dynamic energy-aware capacity provisioning for cloud computing environments , 2012, ICAC '12.

[27]  Filip De Turck,et al.  VNF-P: A model for efficient placement of virtualized network functions , 2014, 10th International Conference on Network and Service Management (CNSM) and Workshop.

[28]  Bin Zhang,et al.  A deep learning approach for VM workload prediction in the cloud , 2016, 2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).

[29]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[30]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .