End-to-End Delay Prediction by Neural Network Based on Chaos Theory

Sun, Hanlin; Jin, Yuehui; Cui, Yidong; Cheng, Shiduan

doi:10.1109/wicom.2010.5601441

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work in [19] adopted deep learning techniques to estimate the end-to-end delay for a resource allocation scheme in cellular networks, where prior data is used to train a deep neural network capable of predicting the end-to-end delay based on the values of the parameters that regulate the resource allocation. The variation of the end-toend delay, aka jitter, was also estimated in [14] using neural networks for learning the evolution of a chaotic system representing the jitter series of the end-to-end delay. The work in [22] uses deep mixture density networks based on neural networks to estimate the end-to-end delay distribution given the network's state.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The majority of machine learning approaches rely on su-pervised learning techniques [14], [19], [21], [22], which are disadvantageous when the statistical properties of the delay vary over time, requiring the recomputation of the learning parameters. The approaches based on queueing models can be very accurate for specific networks.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Using the CF of the end-to-end delay in (14) the expectation of the end-to-end delay can be computed by…”

Section: B End-to-end Delaymentioning

confidence: 99%

See 2 more Smart Citations

A Novel Packet End-to-End Delay Estimation Method for Heterogeneous Networks

Fadhil

Oliveira

2022

IEEE Access

View full text Add to dashboard Cite

The estimation of the end-to-end delay in modern communication networks is of high importance to support multiple services but also for the management of the network resources. In this paper, we propose an end-to-end delay model and estimation methodology for heterogeneous networks. The estimation method allows the computation of the end-to-end delay distribution parameters when a small number of end-to-end delay samples is available through probe packets. The proposed technique is evaluated for different datasets, including networks operating with multiple access technologies and different upper-layer protocols, so the heterogeneity of the networks and protocols can be taken into account. The evaluation results show that the Generalized Extreme Value distribution can be used to approximate the end-to-end delay and high accuracy is achieved even when only a small number of probe packets is available. Finally, the estimation error confirms the effectiveness of the proposed method for a broad range of network scenarios.

show abstract

Section: Literature Reviewmentioning

confidence: 99%