Traffic Forecasting and Planning of WiMAX under Multiple Priority Using Fuzzy Time Series AnalysisReportar como inadecuado




Traffic Forecasting and Planning of WiMAX under Multiple Priority Using Fuzzy Time Series Analysis - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Network traffic prediction plays afundamental role in characterizing the network performance and it is ofsignificant interests in many network applications, such as admission control ornetwork management. Therefore, The main idea behind this work, is thedevelopment of a WIMAX Traffic Forecasting System for predicting traffic timeseries based on the daily and monthly traffic data recorded TRD withassociation of feed forward multi-layer perceptron FFMLP. The quality offorecasting WIMAX Traffic obtained by comparing different configurations of theFFMLP that consist of investigating different FFMLP model architectures anddifferent Learning Algorithms. The decision of changing the FFMLP architectureis essentially based on prediction results to obtain the FFMLP model for flowtraffic prediction model. The different configurations were tested using dailyand monthly real traffic data recorded at each of the two base stations A andB that belongs to a Libyan WiMAX Network. We evaluate our approach withstatistical measurement and a good statistic measure of FMLP indicates theperformance of selected neural network configuration. The developed systemindicates promising results in which it successfully network traffic predictionthrough daily and monthly traffic data recorded TRD association withartificial neural network.

KEYWORDS

Network Traffic, Wimax, Fuzzy Time Series, Forecasting

Cite this paper

Abdullah, I. , Daw, D. and Seman, K. 2015 Traffic Forecasting and Planning of WiMAX under Multiple Priority Using Fuzzy Time Series Analysis. Journal of Applied Mathematics and Physics, 3, 68-74. doi: 10.4236-jamp.2015.31009.





Autor: Ismail Bin Abdullah, Daw Abdulsalam Ali Daw, Kamaruzzaman Bin Seman

Fuente: http://www.scirp.org/



DESCARGAR PDF




Documentos relacionados