Academic Journal of Computing & Information Science, 2023, 6(6); doi: 10.25236/AJCIS.2023.060614.
Yijia Yan, Tenglong Xu
School of Electronic Engineering, Xi’an Aeronautical Institute, Xi’an, 710077, China
Nowadays, the development of 5G, edge computing, NFV and other technologies brought by the surge of network traffic will become a new challenge to the refinement, automation, intelligent operation and maintenance and management of the network. In order to meet this challenge, it is necessary to accurately perceive the application-level network traffic at multiple levels, such as edge network, MAN and backbone network. In order to reduce and reduce the error of predicting network flow data, a neural network algorithm prediction model based on machine deep learning, long and short memory network flow prediction model, which can predict the base station flow data according to the periodicity and volatility characteristics of base station flow data. After experimental verification, it shows that compared with the traditional time series prediction model AR model, ARIMA model also has the basic neural network model, that is, the fully connected neural network model. This method has higher accuracy and smaller experimental error in mobile communication traffic prediction. The MAE value is optimized by 21.6%, 33.4% and 12.5%.
Mobile Communication Base Station, Traffic Forecasting, Long-Short-Term Memory Neural Network, Time series analysis
Yijia Yan, Tenglong Xu. Deep learning-based prediction of base station traffic. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 6: 90-95. https://doi.org/10.25236/AJCIS.2023.060614.
[1] Sang A, Li S. A predictability analysis of network traffic [J]. Computer Networks, 2002, 39(4): 329-345.
[2] Wu Bin. Tion based on ARIMA model[J]. Information and Communication, 2018(6): 1-3
[3] Li Ran., He Tigang, Ming, work [J]. Computer Simulation, 2016, 33(10): 153-156
[4] He Yong, Li Yanting. Traffic Prediction of Mobile Communication Base Station Based on Vector Autoregressive Model [J]. Industrial Engineering and Management, 2017, 22(4): 79-84
[5] Chabaa S, Zeroual A, Antar J. Anfis method for forecasting internet traffic time series [C]// Proceeding of the 2009 Mediterrannean Microwave Symposium. Piscataway, IEEE, 2009: 1-4.
[6] Ni Feixiang. Cellular Network Traffic Prediction Based on Improved Wavelet-Elman Neural Network Algorithm [J]. Electronic Design Engineering, 2017, 25(3): 171-175
[7] Lv Xian, Qi Yong, Zhang Weibin. Odel [J]. Journal of Nanjing University of Science and Technology, 2020, 44(1): 26-32+48