Citation

Hussein, Areej and Gan Goh, Gerald Guan and Anbar, Mohammad Ali and Nassr, Mohammad and Semenova, Mariya I. and Aksenova, Tatiana V. (2025) Comparative Evaluation of Machine Learning Models for Time Series Forecasting in Network Traffic Analysis. In: 2025 7th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), 08-10 April 2025, Moscow, Russian Federation.

Text 9.pdf - Published Version Restricted to Repository staff only Download (348kB)

Abstract

Effective network traffic forecasting is essential for optimizing resource allocation and enhancing network management. This study investigates the application of three machine learning models - Long Short-Term Memory (LSTM), Random Forest (RF), and XGBoost (XGB) - for predicting network traffic patterns using real-world time series data. The research analyzes how varying look-back periods (7, 14, and 30 days) influence model performance, specifically examining the impact of historical time steps on forecasting accuracy. The models are rigorously evaluated using performance metrics such as RMSE, MAE, and R2 across multiple data subsets, offering a comprehensive comparison of their strengths and weaknesses. Additionally, a sensitivity analysis reveals the relationship between model performance and the chosen look-back window. The results provide valuable insights into the selection and optimization of machine learning models for network traffic forecasting, with practical recommendations for improving network management and resource allocation.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	network traffic forecasting, time series forecasting, machine learning models, LSTM, random forest, XGBoost, sensitivity analysis.
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Business (FOB)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	26 Jun 2025 08:20
Last Modified:	26 Jun 2025 08:20
URII:	http://shdl.mmu.edu.my/id/eprint/14126

Downloads

Edit (login required)