Traffic matrix estimation: A neural network approach with extended input and expectation maximization iteration

Zhou, Haifeng; Tan, Liansheng; Zeng, Qian; Wu, Chunming

doi:10.1016/j.jnca.2015.11.013

Cited by 38 publications

(22 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a result, the neural network is forced to explore the network routing paths in addition to the relationship between link loads and OD flows inherently. The MNETME method (Moore‐Penrose inverse based neural network approach for the estimation of IP network traffic matrix with extended input and expectation maximization iteration) has made an effort to extend the basic input by considering the Moore‐Penrose pseudoinverse of the routing matrix in order to embed the routing information implicitly.…”

Section: Related Workmentioning

confidence: 99%

“…Traditional attitudes could not estimate OD flows accurately using the tomography model due to the ill‐posed nature of the problem and complex relationships between link loads and OD flows. Recently, neural networks and deep learning techniques have been exploited to decrease the estimation error . The breakthroughs achieved by recent estimators owe the power of deep neural networks to explore linear and nonlinear relations among the input data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new approach for traffic matrix estimation in high load computer networks based on graph embedding and convolutional neural network

Emami

Akbari

Javidan

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In computer networks, transmitted traffic between origin‐destination nodes has been considered a crucial factor in traffic engineering applications. To date, measuring the traffic directly in high load networks is difficult due to high computational costs. On the other hand, accurate estimation of network traffic by means of link load measurements and routing information is currently a challenging problem. In this paper, we propose a new approach to estimate end‐to‐end traffic, inspired by graph embedding. In the proposed approach, we consider a computer network as a time‐varying graph. Our model provides explicit routing information to a convolutional neural network estimator via link load measurements and network topological structure. When explicit routing information is provided, the learning model is only expected to embed the relations between link loads into a traffic estimation vector, instead of figuring out the routing paths. The experimental results showed that the proposed approach outperforms similar estimators in terms of lower estimation error and better tracking the fluctuations.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A new approach for traffic matrix estimation in high load computer networks based on graph embedding and convolutional neural network

Emami

Akbari

Javidan

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…43,44 SRE explains the estimation error of each individual OD flow during the time. Estimation errors can be calculated as the relative estimation error of each OD flow individually during the time, or the relative estimation error of all OD flows in each time slot.…”

Section: Performance Measuresmentioning

confidence: 99%

“…Both measures are very popular in the literature. 43,44 SRE explains the estimation error of each individual OD flow during the time. SRE for the ith OD flow estimation is expressed in Equation 21.…”

Section: Performance Measuresmentioning

confidence: 99%

Evaluation of mathematical models to estimate end‐to‐end traffic in a backbone network

Emami

Akbari

Zamani

2018

Int J Communication

View full text Add to dashboard Cite

End-to-end network traffic analysis is one of the most important factors in design, development, and traffic engineering of large-scale backbone networks. Despite the importance of end-to-end traffic, it is not applicable to measure it directly using protocols such as NetFlow in large-scale networks due to high computational cost. One technique to tackle this problem is estimating endto-end traffic using easily measured neighboring link loads. Tomography model relates these two parameters with linear equations. In this way, the problem turns into an inverse problem. Since the number of link loads is usually smaller than the number of end-to-end flows in a computer network, traffic matrix estimation is considered to be an ill-posed problem. In this paper, we propose two different methods for estimation of end-to-end traffic matrix by means of link load measurements. One of the methods deploys Kalman filter and the other is developed based on Tikhonov regularization with respect to the existence of temporal autocorrelation among traffics. We also propose a best estimation model based on least squares, which explores the temporal autocorrelation in end-to-end traffics. This model is used as the best estimator and has been compared with other methods. We have evaluated the efficiency of the proposed methods using real datasets from Abilene and GÉANT backbone networks. It is worth noting that the proposed methods in this paper also can be used in any inverse problem with temporal autocorrelation

show abstract

“…In networking applications, for example in TME using neural networks [10], the MDFE framework can partition a large-scale TME problem into multiple sub-problems where smaller-size neural networks can be quickly trained to provide sub-space estimate of unknown TMs. Furthermore, the fusion operation in MDFE can be implemented using advanced data fusion techniques [37] [38].…”

Section: Mdfe and Computational Intelligencementioning

confidence: 99%

Parallelizing Under-Determined Inverse Problems for Network Applications

Malboubi

Garrison

Chuah

et al. 2017

IEEE Trans. Emerg. Top. Comput. Intell.

View full text Add to dashboard Cite

Abstract-In this paper, we introduce a new technique for partitioning a large-scale under-determined linear inverse problem into multiple smaller sub-problems that can be efficiently solved independently, and in parallel. When it is impossible or inefficient to solve a large-scale under-determined linear inverse problem, this technique can be used to significantly speed up the computation process without compromising the accuracy of the solution. We present numerical results that show the effectiveness of this approach when applied to network inference problems including traffic matrix estimation and network anomaly detection, both are important for managing large, complex networks and cyber-security. Our proposed framework is applicable to other emerging applications in computational intelligence that can be formulated as UDLI problems.

show abstract

Traffic matrix estimation: A neural network approach with extended input and expectation maximization iteration

Cited by 38 publications

References 25 publications

A new approach for traffic matrix estimation in high load computer networks based on graph embedding and convolutional neural network

A new approach for traffic matrix estimation in high load computer networks based on graph embedding and convolutional neural network

Evaluation of mathematical models to estimate end‐to‐end traffic in a backbone network

Parallelizing Under-Determined Inverse Problems for Network Applications

Contact Info

Product

Resources

About