Managing Virtualized Networks and Services with Machine Learning

Boutaba, Raouf; Shahriar, Nashid; Salahuddin, Mohammad A.; Limam, Noura

doi:10.1002/9781119675525.ch3

Cited by 5 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and of the potential, but also of the limitations of machine learning techniques are crucial to designing robust, simple and valuable solutions to the administrators of NFVIs. 1,16 Our multivariate, many-to-many LSTM-based VNF resource load prediction approach stands out from other solutions by collecting many time steps of resource usage history of different resource attributes (CPU, memory, I/O bandwidth), from various VNFs in an SFC, in order to leverage their interdependencies. Therefore, the resulting resource usage forecasts of many time steps of different resource attributes from an SFC provide high-accuracy, high-fidelity predictions since they benefit from variations in resource loads of multiple resource attributes that are highly correlated to those targeted resource attributes that we aim to forecast.…”

Section: Ml-based Vnf Resource Usage Predictionmentioning

confidence: 99%

“…Despite this enthusiasm, deep knowledge of several aspects of NFV as a whole (MANO, services, overhead reduction, latency minimization, etc.) and of the potential, but also of the limitations of machine learning techniques are crucial to designing robust, simple and valuable solutions to the administrators of NFVIs 1,16 . Our multivariate, many‐to‐many LSTM‐based VNF resource load prediction approach stands out from other solutions by collecting many time steps of resource usage history of different resource attributes (CPU, memory, I/O bandwidth), from various VNFs in an SFC, in order to leverage their interdependencies.…”

Section: Related Workmentioning

confidence: 99%

“…Among its many benefits, it ensures that TSPs and CSPs efficiently meet their customers' fluctuating resource demands and service level objectives (e.g., delay and availability of highly sensitive applications), surpass service level agreement (SLA), CAPEX, OPEX, and quality of service (QoS) objectives, and significantly reduce latency in an SFC. 1 However, to achieve these goals and bring NFV technology to maturity, new mechanisms for automated VNF deployment must be designed. To this end, many research teams have been looking at ML techniques to efficiently predict future SFC resource usage.…”

Section: Introductionmentioning

confidence: 99%

“…VNF resource scaling allows automated deployment of NFs initially anchored in a physical SFC at various points of a telecom service provider (TSP) or a cloud service provider (CSP) infrastructure such as the core, cloud or edge network. Among its many benefits, it ensures that TSPs and CSPs efficiently meet their customers' fluctuating resource demands and service level objectives (e.g., delay and availability of highly sensitive applications), surpass service level agreement (SLA), CAPEX, OPEX, and quality of service (QoS) objectives, and significantly reduce latency in an SFC 1 …”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

NFVLearn: A multi‐resource, long short‐term memory‐based virtual network function resource usage prediction architecture

2022

View full text Add to dashboard Cite

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.

show abstract

Section: Ml-based Vnf Resource Usage Predictionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations