Author:
Sui Yongbo,He Yigang,Shi Luqiang,Huang Yuang,Cheng Tongtong,Wu Yuting
Abstract
Abstract
In this paper, a novel prediction strategy based on firefly algorithm, echo state network and Savitzky-Golay filter for short-term prediction of fading channel is proposed and introduced in detail. This hybrid strategy includes two parts, that is, optimization part and repairing part. In the former, parameters of echo state network are optimized by firefly algorithm so that an optimal prediction echo state network is obtained, then in order to improve performances in prediction strategy, prediction sample of echo state network is repaired by repairing strategy based on Savitzky-Golay filter. Finally, the classic Rayleigh channel is tested and performances are analysed and compared with classic AR, which verified the validity and correctness of our proposed prediction strategy.
Subject
General Physics and Astronomy
Reference14 articles.
1. Prediction of fast fading parameters by resolving the interference pattern;Eyceoz,1997
2. Limitations of sum-of-sinusoids fading channel simulators;Pop;IEEE Transactions on Communications,2001
3. Short-term fading simulator based on artificial neural networks;Tomasevic,2009
4. Short-term fading simulation using artificial neural networks;Nikola;AEU - International Journal of Electronics and Communications,2011
5. Artificial neural network based simulation of correlated short-term fading;Nikola;AEU - International Journal of Electronics and Communications,2014