Premium
Multi‐scale Internet traffic forecasting using neural networks and time series methods
Author(s) -
Cortez Paulo,
Rio Miguel,
Rocha Miguel,
Sousa Pedro
Publication year - 2012
Publication title -
expert systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 38
eISSN - 1468-0394
pISSN - 0266-4720
DOI - 10.1111/j.1468-0394.2010.00568.x
Subject(s) - autoregressive integrated moving average , computer science , artificial neural network , time series , anomaly detection , data mining , the internet , scale (ratio) , series (stratigraphy) , anomaly (physics) , artificial intelligence , machine learning , world wide web , paleontology , physics , quantum mechanics , biology , condensed matter physics
This article presents three methods to forecast accurately the amount of traffic in TCP/IP based networks: a novel neural network ensemble approach and two important adapted time series methods (ARIMA and Holt‐Winters). In order to assess their accuracy, several experiments were held using real‐world data from two large Internet service providers. In addition, different time scales (5 min, 1 h and 1 day) and distinct forecasting lookaheads were analysed. The experiments with the neural ensemble achieved the best results for 5 min and hourly data, while the Holt‐Winters is the best option for the daily forecasts. This research opens possibilities for the development of more efficient traffic engineering and anomaly detection tools, which will result in financial gains from better network resource management.