A New Algorithm For Prediction WIMAX Traffic Based On Artificial Neural Network Models

DAW, ABDULSALAM ALI DAW and KAMARUZZAMAN, BIN SEMAN and MADIHAH BINT, MOHD SAUDI (2014) A New Algorithm For Prediction WIMAX Traffic Based On Artificial Neural Network Models. In: International Conference on Advances In Applied Science and Environmental Engineering - ASEE 2014, 02 - 03 August, 2014, Kuala Lumpur, Malaysia.

20141118_102501.pdf - Published Version

Download (728kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/3...


In this paper, WIMAX traffic forecasting system for predicting traffic time series based on the traffic data recorded (TRD) along with Artificial Neural Networks (ANN) was proposed. The data used in this work are the maximum online user, minimum online user, traffic of MIMO-A and traffic of MIMO-B. These data are available from LibyaMax network (WiMAX technology) motorized by Libya Telecom and Technology over a period of 90 days. The quality of forecasting WIMAX traffic obtained by focusing on the ANN design through comparing different configurations of and models that consist of investigating different topology and learning algorithms. The decision of changing the ANN architecture is essentially based on prediction results to obtain the best ANN model for flow traffic prediction model. Testing the different configurations using real traffic data recorded at base stations (A, B and AB) that belong to a Libyan WiMAX Network. Statistical measurement is used to evaluate the different ANNs configuration to selected best model based on higher performance resulting. Outcome founded indicate that ANN model using maximum and minimum online user as inputs, gives good accurate results for predicting traffic by employing TrainLM with all considered cases.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: WIMAX traffic, ANN model , Forecasting System
Depositing User: Mr. John Steve
Date Deposited: 27 May 2019 07:59
Last Modified: 27 May 2019 07:59
URI: http://publications.theired.org/id/eprint/2750

Actions (login required)

View Item View Item