Research on Network Traffic Forecast Based on Improved LSTM Neural Network

Luming Bai ； Hui Wang ； Zhibo Zhai

《International Core Journal of Engineering》 6卷6期 (2020/06) Pp. 225-234

https://doi.org/10.6919/ICJE.202006_6(6).0035

摘要

Accurately predicting network traffic can reduce the frequency of network congestion, prevent network crashes, and ensure network smoothness. In order to solve the problem of long short-term memory (LSTM) model predicting network traffic with large prediction errors and low accuracy, this paper proposes a network traffic prediction model based on the combination of particle swarm optimization (PSO) and LSTM neural network. The improved PSO algorithm is used to optimize the initial parameters of the LSTM neural network, and then the trained IPSO_LSTM model is used to predict the network traffic, and compared with the LSTM model and the PSO_LSTM model. The experimental results show that the IPSO_LSTM model converges faster than the LSTM model, and the prediction error of the IPSO_LSTM model is reduced by 4% compared with the PSO_LSTM model.

關鍵字

Network traffic prediction ； Particle swarm optimization ； Long and short memory ； Neural network

參考文獻

Aldhyani T H H, Joshi M R . Integration of time series models with soft clustering to enhance network traffic forecasting[C]// International Conference on Research in Computational Intelligence & Communication Networks. IEEE, 2017:212-214.

Liu Y, Wang R X . Study on network traffic forecast model of SVR optimized by GAFSA[J]. Chaos Solitons & Fractals, 2015, 89(3):153-159.

Li X, Peng L , Yao X , et al. Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation[J]. Environmental Pollution, 2017, 231:997-1004.

Kong W, Dong Z Y , Jia Y , et al. Short-Term Residential Load Forecasting based on LSTM Recurrent Neural Network[J]. IEEE Transactions on Smart Grid, 2017:1-1.

Choi J Y, Lee B . Combining LSTM Network Ensemble via Adaptive Weighting for Improved Time Series Forecasting[J]. Mathematical Problems in Engineering, 2018, 2018(PT.9):2470171.1-2470171.8.