Deep Learning Network Traffic Prediction based on Bayesian Algorithm Optimization

Yuantao Lv

doi:10.54097/hset.v39i.6857

Authors

Yuantao Lv

DOI:

https://doi.org/10.54097/hset.v39i.6857

Keywords:

5G; Network Traffic Prediction; Bayesian Optimization Algorithm; Convolutional Neural Network; Long Short-Term Memory Neural Network.

Abstract

In order to solve the problem of low prediction accuracy caused by artificial determination of hyperparameters of network traffic prediction model, this paper applies Bayesian optimization algorithm (BOA) to the determination of hyperparameters of neural network, and proposes a CNN-LSTM network traffic prediction model based on Bayesian optimization algorithm. The local features and long-term development trends of the data are mined by combining the Convolutional Neural Network (CNN) and the Long Short-Term Memory Neural Network (LSTM), and the Bayesian optimization algorithm is used to calibrate the hyperparameters. This paper uses real network traffic data to test and compare with LSTM, GRU and other models. Experimental results demonstrate that the proposed BOA-CNN-LSTM model reduces the RMSE and MAE by 21.17% and 27.52%, compared to the traditional network traffic prediction model. The results presented in this paper show that the Bayesian optimization algorithm can more quickly and accurately calibrate the hyperparameters of the model, which provides a new method for predicting network traffic time series data in the future.

Downloads

Download data is not yet available.

References

ITU-RM 2083-0.IMT vision, framework and overall objectives of the future development of IMT for 2020 and beyond. ITU-R, Document 5/199-E, 2015.

SANG A, LI S. A predictability analysis of network traffic. Computer Networks,2002,39(4): 329-345.

Xiong Hao, Liu Jiayong, Wang Junfeng. Network traffic prediction based on neural network and autoregressive model. Computer Applications, 2021, 41 (S1): 180-184.

Zou Baixian, Liu Qiang. Network traffic prediction based on ARMA model. Computer Research and Development, 2002 (12): 1645-1652.

Wu Wenqing, Zhao Liming, Liu Jiakun. Network traffic BP neural network prediction based on chaos theory. Computer Engineering and Application, 2005 (17): 3-6.

Zhang Chuanting. Urban-scale wireless traffic prediction based on deep learning. Jinan: Shandong University, 2019.

Kang Mengxuan, Song Junping, Fan Pengfei, Gao Bowen, Zhou Xu, Li Zhuo. Research on network traffic prediction based on deep learning. Computer Engineering and Applications, 2021, 57 (10): 1-9.

Lu Haipeng, Yang Fan. A network traffic prediction model based on wavelet transformation and LSTM network // Proc of the 9th IEEE International Conference on Software Engineering and Service Science. Piscataway, NJ: IEEE Press,2018:1131-1134.

Liang Sisheng, Nguyen L, Jin Fang. A multi-variable stacked long-short term memory network for wind speed forecasting/ /Proc of International Conference on Big Data. Piscataway, NJ: IEEE Press,2018:4561-4564.

Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation,1997,9(8):1735-1780.

Zhang Song. Research on network traffic prediction based on improved gated recurrent neural network. Changsha: Hunan University, 2019.

Li Jiayue, Zhao Bo, Li Xiang, Liu Hui, Liu Yifan, Zou Jianwen. Network traffic anomaly prediction method based on deep learning. Computer Engineering and Application, 2020, 56 (06): 39-50.

Zhou Feiyan, Jin Linpeng, Dong Jun. Review of convolutional neural network research. Journal of Computer Science, 2017, 40 (06): 1229-1251.

Huang Lin, Wang Diangang, Liu Xiao and so on. LSTM-based network traffic prediction method. Computer Application Research, 2020, 37 (S1): 264-265 + 272.

Guo Niangrong, Gan Haoyu, Chen Lifeng, Lai Yue. A 5G traffic prediction model based on CNN-GRU network. Modern Computer, 2022, 28 (04): 76-81.

Zhu Jun, Hu Wenbo. Review of Bayesian machine learning. Computer Research and Development, 2015, 52 (01): 16-26.

Gelman A, Carlin J, Stern H, et al. Bayesian Data Analysis. Boca Raton: CRC Press, 2013.

Pan Shaowei, Li Hui, Wang Yaling, et al. LSTM neural network crude oil price forecast. Computer technology and development, 2021, 31 (05): 180-185.

Xue Yang, Wang Lin, Wang Shu, et al. An ultra-short-term wind power prediction model combining CNN and GRU network. Renewable energy, 2019, 37 (03): 456-462.