NFVLearn: A multi‐resource, long short‐term memory‐based virtual network function resource usage prediction architecture. (2nd November 2022)

• Record Type: Journal Article
• Authors: St‐Onge, Cédric; Kara, Nadjia; Edstrom, Claes
• Is Part Of: Software, practice & experience. Volume 53:Number 3(2023)
• Page Start: 555
• Page End: 578
• Publication Date: 2022-11-02
• Subjects: correlation coefficients -- GNN -- input feature selection -- LSTM -- network function virtualization -- resource usage prediction; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.3160
• Languages: English
• ISSNs: 0038-0644

Abstract

Abstract: Virtual resource load prediction in network function virtualization (NFV) is the subject of intense research due to its crucial role in enabling proactive resource adaptation in dynamic NFV environments whose resource demand constantly changes. Several long short‐term memory (LSTM)‐based approaches have been proposed to forecast the resource load of multiple resource attributes of a virtual network function (VNF) in a service function chain (SFC). In this article, we present NFVLearn, a flexible multivariate, many‐to‐many LSTM‐based model which uses different types of resource load history (CPU, memory, I/O bandwidth) from various VNFs of an SFC to predict future loads of multiple resources of a VNF. We then compare four novel automated input selection frameworks for NFVLearn. Simulations on those frameworks based on graph neural networks, Pearson correlation coefficient, Spearman rank correlation coefficient, and Kendall rank correlation coefficient demonstrate that models using lesser, highly correlated input features retain high prediction root mean squared error accuracy and coefficients of determination scores by leveraging resource attribute inter‐dependencies from the SFC. Those results show that resource attribute interdependency‐based input feature selection frameworks can reduce overhead in the control plane while keeping high accuracy and high fidelity resource load prediction of multiple resource attributes.