Regressor Relearning Architecture Adapting to Traffic Trend Changes in NFV Platforms

Hirayama, Takahiro; Jibiki, Masahiro; Kafle, Ved P.

doi:10.1109/netsoft48620.2020.9165449

Cited by 4 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is extended version of our previous work presented in IEEE Netsoft'20 [6]. We lastly show that combination of the sparse model with the relearning architecture makes the relearning time about 57% shorter than that of previous work due to simplifying the explanatory variables.…”

Section: Introductionmentioning

confidence: 59%

“…We evaluated the prediction performance for provisioning resources to each VM according to the prediction. The results shown that the total provisioning error is approximately 45% smaller than that of the ARMA model and RNN [6].…”

Section: Prediction Performancementioning

confidence: 90%

“…Secondly, we propose a relearning architecture for traffic prediction framework based on the two-stage relearning processes to adapt to trend changes in short-and longterm scales. Our previous evaluation [6] revealed that the proposed framework can reduce the frequencies of overand under-provisioning by more than 45% in comparison to RNNs and autoregressive moving average (ARMA). However, the relearning process takes a much time especially when it trains multiple regressors to keep up with trend changes in long-term.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse Regression Model-Based Relearning Architecture for Shortening Learning Time in Traffic Prediction

Hirayama

Miyazawa

Jibiki

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Network function virtualization (NFV) enables network operators to flexibly provide diverse virtualized functions for services such as Internet of things (IoT) and mobile applications. To meet multiple quality of service (QoS) requirements against time-varying network environments, infrastructure providers must dynamically adjust the amount of computational resources, such as CPU, assigned to virtual network functions (VNFs). To provide agile resource control and adaptiveness, predicting the virtual server load via machine learning technologies is an effective approach to the proactive control of network systems. In this paper, we propose an adjustment mechanism for regressors based on forgetting and dynamic ensemble executed in a shorter time than that of our previous work. The framework includes a reducing training data method based on sparse model regression. By making a short list of training data derived from the sparse regression model, the relearning time can be reduced to about 57% without degrading provisioning accuracy.

show abstract

Section: Introductionmentioning

confidence: 59%

Section: Prediction Performancementioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sparse Regression Model-Based Relearning Architecture for Shortening Learning Time in Traffic Prediction

Hirayama

Miyazawa

Jibiki

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The model evaluation is based on several criteria: normalized mean squared error, mean absolute percentage error (MAPE), normalized median squared error, and median absolute percentage error. Again, these ML techniques 8,9,17 that depend on univariate resource usage history have the same limitations those stated previously: the predictions of these models are based on same-to-same resource usage attributes. Thus, those techniques do not benefit from historical resource usage interdependencies of multiple highly correlated resource usage attributes.…”

Section: Ml-based Vnf Resource Usage Predictionmentioning

confidence: 97%

“…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%

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

Software Escalation Prediction Based on Deep Learning in the Cognitive Internet of Vehicles

Wang

Zhang

Fortino

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Regressor Relearning Architecture Adapting to Traffic Trend Changes in NFV Platforms

Cited by 4 publications

References 13 publications

Sparse Regression Model-Based Relearning Architecture for Shortening Learning Time in Traffic Prediction

Sparse Regression Model-Based Relearning Architecture for Shortening Learning Time in Traffic Prediction

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

Software Escalation Prediction Based on Deep Learning in the Cognitive Internet of Vehicles

Contact Info

Product

Resources

About