Open Access
Research on the Comparison of Time Series Models for Network Traffic Prediction
TLDR
The results show that time series models perform better under the large scale (minute) than under small time scales (millisecond and second), and the performance of self similarity model FARIMA shows no advantage over other models.Abstract:
Network traffic prediction is very important in network protocol designing,network management and high performance routers designing etc.Currently,ARMA and FARIMA time series are the main models used to fit and predict the network traffic.But the relation between time scale and time series models hasn't been studied.The network traffic was modeled according to different time scales using the traffic trace data taken from the Internet traffic archive,and the prediction performance of those models was compared.The results show that time series models perform better under the large scale(minute)than under small time scales(millisecond and second),and the performance of self similarity model FARIMA shows no advantage over other models.read more
Citations
More filters
Journal ArticleDOI
Forecasting short-term data center network traffic load with convolutional neural networks.
TL;DR: It is shown that the convolutional neural network approach can exploit the non-linear regularities of network traffic, providing significant improvements with respect to the mean absolute and standard deviation of the data, and outperforming ARIMA by an increasingly significant margin as the forecasting granularity is above the 16-second resolution.
Journal ArticleDOI
Automatic Traffic Accident Detection Based on the Internet of Things and Support Vector Machine
TL;DR: This paper proposes an overall framework of intelligent transportation, and proposes a Support Vector Machine (SVM) modified by Ant Colony Algorithm (ACA) as the solution for traffic accident detection in the IoT platform.
Proceedings ArticleDOI
Network Traffic Prediction Based on Neural Network
TL;DR: The aim of this article is to explore a new network model in order to describe and predict the network character accurately and the results show the proposed scheme has good performance.
Journal ArticleDOI
A Network Traffic Hybrid Prediction Model Optimized by Improved Harmony Search Algorithm
TL;DR: The simulation results verified that the proposed network traffic hybrid prediction model based on improved harmony search algorithm has higher prediction accuracy.
Journal ArticleDOI
Prediction method for network traffic based on Maximum Correntropy Criterion
TL;DR: The simulation results show that the accuracy of the prediction based on MCC is superior to the results of the Elman neural network with MSE, and the overall performance is improved by about 0.0131.