Deep Learning Based Resource Allocation For Auto-Scaling VNFs

Patel, Yashwant Singh; Verma, Deepak; Misra, Rajiv

doi:10.1109/ants47819.2019.9118065

Cited by 6 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 6 show R 2 scores and RMSE of individual predicted resource usage from each model built using input time step sets of T x = [5,10] and output time step set of T y = [3,5,7]. For instance, subfigures 6a and 6b depict histograms of R 2 scores and RMSE from predicted CPU resource usage, respectively.…”

Section: Resultsmentioning

confidence: 99%

“…Different LSTM-based combinations are tested in Section V-D. For instance, we designed models with NFVLearn or A-NFVLearn, and combined them either with or without AO filtering, for a total of four different combinations. Then, we trained those models with variations in the numbers of input time steps ( [5,10]) and predicted output time steps ( [3,5,7]). In order to compare the prediction accuracy of each setup, the RMSE defined in eq.…”

Section: Comparisonsmentioning

confidence: 99%

See 1 more Smart Citation

Multivariate outlier filtering for A-NFVLearn: an Advanced Deep VNF Resource Usage Forecasting Technique

St‐Onge

Kara

Edstrom

2022

Preprint

View full text Add to dashboard Cite

Virtual Network Function Resource Adaptation (VNF-RA) aims at adequately adapting Network Function Virtualization Infrastructure (NFVI) resources according to the geographical fluctuation of user demand by maximizing the quality of service (QoS) of the offered services and the energy consumption of the NFVI while limiting the risks of Service Level Agreement (SLA) breaches, the CAPEX and OPEX of the cloud operators and their customers. Virtual Network Function (VNF) resource usage forecasting leads therefore a key role in enabling proactive resource adaptation in dynamic Network Function Virtualization (NFV) environments whose resource demand constantly changes. In parallel, Long Short-Term Memory (LSTM)-based prediction has garnered huge interest in the research community and several research teams have therefore proposed different VNF resource usage prediction algorithms based on this machine learning technique. However, current LSTM-based VNF resource usage forecasting techniques lack the flexibility to take several resource attributes of different scales, over many time steps, in order to predict several other resource attributes over many time steps from a Service Function Chain (SFC). In this paper, we push the state of the art forward by presenting A-NFVLearn, a flexible multivariate, LSTM-based model with an attention mechanism which uses different attributes of resource load history (CPU, memory, I/O bandwidth) from various VNFs of an SFC to forecast future load of multiple resources of a VNF. Next, we propose a multivariate outlier filtering scheme at pre-processing based on Adjusted Outlyingness (AO), which improves training time performance of LSTM-based models without impacting prediction accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Comparisonsmentioning

confidence: 99%

Multivariate outlier filtering for A-NFVLearn: an Advanced Deep VNF Resource Usage Forecasting Technique

St‐Onge

Kara

Edstrom

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Proposal of numerous NFV and mobile networking management mechanisms leveraging state-of-the-art machine learning techniques has garnered huge interest in recent years throughout the research community. 2,3,[5][6][7][8][9][10][11][12][13][14][15] 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.…”

Section: Ml-based Vnf Resource Usage Predictionmentioning

confidence: 99%

“…Further, with the massive increase in data availability and the rise of DL and its ability to decipher complex relationships between different features of the data, more elaborate solutions are gradually appearing in the literature. Approaches leveraging RNNs, 8,9,17 LSTM, 3,6,7,10,14,18 and context and aspect embedded attentive target dependent LSTM (CAT-LSTM) 3,10,11 have been particularly appealing in recent years.…”

Section: Ml-based Vnf Resource Usage Predictionmentioning

confidence: 99%

“…Next, among the LSTM and CAT-LSTM solutions, many of those use multivariate, many-to-one mechanisms. 3,6,7,10,11,14 In Reference 3, the approach takes historical resource utilization of VNFs to predict future CPU loads of a VNF and its neighbors and the authors use RMSE as a loss function to evaluate results. On the other hand, the approach proposed in Reference 10 compares RSME loss of prediction models that maximize the benefits of using an SFC.…”

Section: Ml-based Vnf Resource Usage Predictionmentioning

confidence: 99%

See 1 more Smart Citation

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

Parallel bi-state deep reinforcement learning approach for SFC placements and deployments

Khemili,

Saidi,

Hajlaoui

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

Deep Learning Based Resource Allocation For Auto-Scaling VNFs

Cited by 6 publications

References 20 publications

Multivariate outlier filtering for A-NFVLearn: an Advanced Deep VNF Resource Usage Forecasting Technique

Multivariate outlier filtering for A-NFVLearn: an Advanced Deep VNF Resource Usage Forecasting Technique

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

Parallel bi-state deep reinforcement learning approach for SFC placements and deployments

Contact Info

Product

Resources

About