Researching of Chaotic Characteristics and Forecasting of Elman Network on the Communication Traffic

Abstract:

Communication traffic is a kind of dynamic nonlinear time series affected by various factors; the traditional predication methods cant achieve higher accuracy. In order to improve the communication traffic forecasting accuracy, in this paper, analyzing Chaotic characteristics and Predictability of the Communication traffic based on the Communication traffic data of daily rush hour by collecting, and reconstructing the phase space of the communication traffic time series, proposing a method of building the predication model of the communication traffic by using Elman dynamic neural network, and using proposed model to do one-step forecasting, the experimental results show that this method improves the communication traffic forecasting accuracy. It can provide an effective way for forecasting of the communication traffic.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3565-3570
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3565
• Online since: August 2013
• Authors: Zhi Mei Duan, Yan Jie Zhou, Xiao Jin Yuan
• Keywords: Chaotic Characteristics, Communication Traffic, Elman Neural Network (ENN), Forecasting

References

[1] CHENG Wei. Traffic Prediction Based on Seasonal Changes. Telecommunications Technology, 2000, 10: 25-27.

[2] LEI Miao, PENG Yu, GUO Jia, PENG Chun-yuan. Traffic forecasting for prior knowledge based clustered complex echo state networks. Chinese Journal of Scientific Instrument, 2011, 32(10): 2190-2197.

DOI: 10.1109/imtc.2011.5944078

[3] YAO Shi-hong, WANG Tao, JIA Zhen-hong, TAN Xi-zhong, CHANG Chun, WANG Hao. Algorithm of microcanonical-SVM based for forecasring traffic load. Computer Engineering and Applications, 2012, 48(3): 105-106, 110.

[4] ZENG Jun. Modeling and Simulation on Communication Traffic Forecasting Model. Computer Simulation, 2012, 29(2): 116-119.

[5] LIU Dao-wen, HU Hai-na. Anlysis of Chaotic Characteristics of Nonlinear Time Series and Short-term Prediction. Computer Simulation, 2012，29(10)：370-373.

[6] LIN Chun-yan, ZHU Dong-hua. Stock market forecasting research based on Elman neural netwok. Computer Applications, 2006, 26(2): 476-477, 484.

[7] SHAO Yue-hong, LIU Yong-he. Soil Moisture Prediction Based on Elman Recurrent Dynamic Neural Networks Model. Bulletin of Soil and Water Conservation, 2012, 32(5)：257-260.

[8] LI Na, YAN Wei-ping, MA Liang-yu. Stress Soft-sensing Model for Steam-Water Separator of Ultra Supercritical Boilers Based on Elman Neural Network. Power Engineering, 2012. 32(10): 747-752.