• PDF / 1,772,311 Bytes
• 14 Pages / 595.276 x 790.866 pts Page_size
• 81 Downloads / 227 Views

DOWNLOAD

REPORT

---

(0123456789().,-volV) (0123456789().,-volV)

Network traffic prediction based on INGARCH model Meejoung Kim1

Ó Springer Science+Business Media, LLC, part of Springer Nature 2020

Abstract In this paper, we introduce the integer-valued generalized autoregressive conditional heteroscedasticity (INGARCH) as a network traffic prediction model. As the INGARCH is known as a non-linear analytical model that could capture the characteristics of network traffic such as Poisson packet arrival and long-range dependence property, INGARCH seems to be an adequate model for network traffic prediction. Based on the investigation for the traffic arrival process in various network topologies including IoT and VANET, we could confirm that assuming the Poisson process as packet arrival works for some networks and environments of networks. The prediction model is generated by estimating parameters of the INGARCH process and predicting the Poisson parameters of future-steps ahead process using the conditional maximum likelihood estimation method and prediction procedure, respectively. Its performance is compared with those of three different models; autoregressive integrated moving average, GARCH, and long short-term memory recurrent neural network. Anonymized passive traffic traces provided by the Center for Applied Internet Data Analysis are used in the experiment. Numerical results show that the proposed model predicts better than the three models in terms of measurements used in prediction models. Based on the study, we can conclude the followings: INGARCH can capture the characteristics of network traffic better than other statistic models, it is more tractable than neural networks (NNs) overcoming the black-box nature of NNs, and the performances of some statistical models are comparable or even superior to those of NNs, especially when the data is insufficient to apply deep NNs. Keywords Network traffic  Prediction procedure  Integer-valued generalized autoregressive conditional heteroscedasticity  Long short-term memory recurrent neural network

1 Introduction Analysis and predictive modeling of network traffic have become more important than ever because of the rapid growth of network traffic due to the evolution of smart devices. For fast, accurate, and secure communications, accurate prediction of network traffic is essential in many areas, including congestion control, admission control, and network management [1–3]. The occurrence of network traffic can be regarded as a stochastic process over time and its predictive models should be able to capture the characteristics of the traffic. Based on numerous Internet traffic analysis studies over the last several decades, Internet

& Meejoung Kim [email protected] 1

Research Institute for Information and Communication Technology, Korea University, Seoul, Korea

traffic has been perceived as having self-similarity and long-range dependence (LRD) characteristics. Accordingly, the network traffic model has been considered to reflect the self-similarity and LRD characteristics