Educational bandwidth traffic prediction using non-linear autoregressive neural networks

Abstract

Time series network traffic analysis and forecasting are important for fundamental to many decision-making processes, also to understand network performance, reliability and security, as well as to identify potential problems. This paper provides the latest work on London South Bank University (LSBU) network data traffic analysis by adapting nonlinear autoregressive exogenous model (NARX) based on Levenberg-Marquardt backpropagation algorithm. This technique can analyse and predict data usage in its current and future states, as well as visualise the hourly, daily, weekly, monthly, and quarterly activities with less computation requirement. Results and analysis proved the accuracy of the prediction techniques.

Smoothing-aided long-short term memory neural network-based LTE network traffic forecasting

“…Dyllon et al [19] developed a nonlinear autoregressive exogenous neural (NARX) network model for time series network traffic analysis. The study implemented a neural network model to predict the future trends of the London South Bank University (LSBU) bandwidth data traffic.…”