Application of the NARX neural network for predicting a one-dimensional time series

Time series data analysis and forecasting tool for studying the data on the use of network traffic is very important to provide acceptable and good quality network services, including network monitoring, resource management, and threat detection. More and more, the behavior of network traffic is des...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tansaule Serikov, Ainur Zhetpisbayeva, Sharafat Mirzakulova, Kairatbek Zhetpisbayev, Zhanar Ibrayeva, Lyudmila Sobolevа, Arai Tolegenova, Berik Zhumazhanov
Formato:	article
Lenguaje:	EN RU UK
Publicado:	PC Technology Center 2021
Materias:	one-dimensional time series narx model forecasting neural network nonlinear autoregression Technology (General) T1-995 Industry HD2321-4730.9
Acceso en línea:	https://doaj.org/article/3b0ccc5ba187445989e48f4f0c5e537f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3b0ccc5ba187445989e48f4f0c5e537f
record_format	dspace
spelling	oai:doaj.org-article:3b0ccc5ba187445989e48f4f0c5e537f2021-11-04T14:06:45ZApplication of the NARX neural network for predicting a one-dimensional time series1729-37741729-406110.15587/1729-4061.2021.242442https://doaj.org/article/3b0ccc5ba187445989e48f4f0c5e537f2021-10-01T00:00:00Zhttp://journals.uran.ua/eejet/article/view/242442https://doaj.org/toc/1729-3774https://doaj.org/toc/1729-4061Time series data analysis and forecasting tool for studying the data on the use of network traffic is very important to provide acceptable and good quality network services, including network monitoring, resource management, and threat detection. More and more, the behavior of network traffic is described by the theory of deterministic chaos. The traffic of a modern network has a complex structure, an uneven rate of packet arrival for service by network devices. Predicting network traffic is still an important task, as forecast data provide the necessary information to solve the problem of managing network flows. Numerous studies of actually measured data confirm that they are nonstationary and their structure is multicomponent. This paper presents modeling using Nonlinear Autoregression Exogenous (NARX) algorithm for predicting network traffic datasets. NARX is one of the models that can be used to demonstrate non-linear systems, especially in modeling time series datasets. In other words, they called the categories of dynamic feedback networks covering several layers of the network. An artificial neural network (ANN) was developed, trained and tested using the LM learning algorithm (Levenberg-Macwardt). The initial data for the prediction is the actual measured network traffic of the packet rate. As a result of the study of the initial data, the best value of the smallest mean-square error MSE (Mean Squared Error) was obtained with the epoch value equal to 18. As for the regression R, its output ANN values in relation to the target for training, validation and testing were 0.97743. 0.9638 and 0.94907, respectively, with an overall regression value of 0.97134, which ensures that all datasets match exactly. Experimental results (MSE, R) have proven the method's ability to accurately estimate and predict network trafficTansaule SerikovAinur ZhetpisbayevaSharafat MirzakulovaKairatbek ZhetpisbayevZhanar IbrayevaLyudmila SobolevаArai TolegenovaBerik ZhumazhanovPC Technology Centerarticleone-dimensional time seriesnarx modelforecastingneural networknonlinear autoregressionTechnology (General)T1-995IndustryHD2321-4730.9ENRUUKEastern-European Journal of Enterprise Technologies, Vol 5, Iss 4 (113), Pp 12-19 (2021)
institution	DOAJ
collection	DOAJ
language	EN RU UK
topic	one-dimensional time series narx model forecasting neural network nonlinear autoregression Technology (General) T1-995 Industry HD2321-4730.9
spellingShingle	one-dimensional time series narx model forecasting neural network nonlinear autoregression Technology (General) T1-995 Industry HD2321-4730.9 Tansaule Serikov Ainur Zhetpisbayeva Sharafat Mirzakulova Kairatbek Zhetpisbayev Zhanar Ibrayeva Lyudmila Sobolevа Arai Tolegenova Berik Zhumazhanov Application of the NARX neural network for predicting a one-dimensional time series
description	Time series data analysis and forecasting tool for studying the data on the use of network traffic is very important to provide acceptable and good quality network services, including network monitoring, resource management, and threat detection. More and more, the behavior of network traffic is described by the theory of deterministic chaos. The traffic of a modern network has a complex structure, an uneven rate of packet arrival for service by network devices. Predicting network traffic is still an important task, as forecast data provide the necessary information to solve the problem of managing network flows. Numerous studies of actually measured data confirm that they are nonstationary and their structure is multicomponent. This paper presents modeling using Nonlinear Autoregression Exogenous (NARX) algorithm for predicting network traffic datasets. NARX is one of the models that can be used to demonstrate non-linear systems, especially in modeling time series datasets. In other words, they called the categories of dynamic feedback networks covering several layers of the network. An artificial neural network (ANN) was developed, trained and tested using the LM learning algorithm (Levenberg-Macwardt). The initial data for the prediction is the actual measured network traffic of the packet rate. As a result of the study of the initial data, the best value of the smallest mean-square error MSE (Mean Squared Error) was obtained with the epoch value equal to 18. As for the regression R, its output ANN values in relation to the target for training, validation and testing were 0.97743. 0.9638 and 0.94907, respectively, with an overall regression value of 0.97134, which ensures that all datasets match exactly. Experimental results (MSE, R) have proven the method's ability to accurately estimate and predict network traffic
format	article
author	Tansaule Serikov Ainur Zhetpisbayeva Sharafat Mirzakulova Kairatbek Zhetpisbayev Zhanar Ibrayeva Lyudmila Sobolevа Arai Tolegenova Berik Zhumazhanov
author_facet	Tansaule Serikov Ainur Zhetpisbayeva Sharafat Mirzakulova Kairatbek Zhetpisbayev Zhanar Ibrayeva Lyudmila Sobolevа Arai Tolegenova Berik Zhumazhanov
author_sort	Tansaule Serikov
title	Application of the NARX neural network for predicting a one-dimensional time series
title_short	Application of the NARX neural network for predicting a one-dimensional time series
title_full	Application of the NARX neural network for predicting a one-dimensional time series
title_fullStr	Application of the NARX neural network for predicting a one-dimensional time series
title_full_unstemmed	Application of the NARX neural network for predicting a one-dimensional time series
title_sort	application of the narx neural network for predicting a one-dimensional time series
publisher	PC Technology Center
publishDate	2021
url	https://doaj.org/article/3b0ccc5ba187445989e48f4f0c5e537f
work_keys_str_mv	AT tansauleserikov applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT ainurzhetpisbayeva applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT sharafatmirzakulova applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT kairatbekzhetpisbayev applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT zhanaribrayeva applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT lyudmilasoboleva applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT araitolegenova applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries AT berikzhumazhanov applicationofthenarxneuralnetworkforpredictingaonedimensionaltimeseries
_version_	1718444831555977216

Application of the NARX neural network for predicting a one-dimensional time series

Ejemplares similares