Optimizing neural network forecast by immune algorithm

Abstract

Considering multi-factor influence, a forecasting model was built. The structure of BP neural network was designed, and immune algorithm was applied to optimize its network structure and weight. After training the data of power demand from the year 1980 to 2005 in China, a nonlinear network model was obtained on the relationship between power demand and the factors which had impacts on it, and thus the above proposed method was verified. Meanwhile, the results were compared to those of neural network optimized by genetic algorithm. The results show that this method is superior to neural network optimized by genetic algorithm and is one of the effective ways of time series forecast.

Keywords

neural network / forecast / immune algorithm / optimization

References

[1] LiuHui-you, FanHai-jun. Prediction of production performances of oil and injection wells with multivariate time series method[J]. Journal of University of Petroleum, 2001, 25(2): 70-72(in Chinese)

[2] PanAi-jun, WangKai-fa. The forecasting model and application of multifactor time series data GM(1, N) [J]. Journal of the Third Military Medicine University, 2003, 25(19): 1774-1775(in Chinese)

[3] WU Chang-rong, YE Ming-quan. The application of BP neural networks in hospital multifactor time series forecast[J]. Fujian Computer, 2005(1): 38–39. (in Chinese)

[4] WangYue, CaoChang-xiu. Application research of the BP algorithm used in medicine planning system of HIS [J]. Computer Engineering and Design, 2002, 23(4): 19-22(in Chinese)

[5] LiLiu-ren, JiaoLi-cheng. Prediction of the oil field output under the effects of nonlinear factors by artificial neural network[J]. Journal of Xi’an Petroleum Institute: Natural Science Edition, 2002, 17(4): 42-44(in Chinese)

[6] LiangHong-sheng, HaoYong-na, WangKai, et al.. Immune algorithms[J]. Journal of Kunming University of Science and Technology: Science and Technology, 2003, 28(5): 72-76(in Chinese)

[7] WuJian-sheng, JinLong, NongJi-fu. Forecast research and applying of BP neural network based on genetic algorithms[J]. Mathematics in Practice and Theory, 2005, 35(1): 83-88(in Chinese)

[8] HaoYong-na, LiangHong-sheng, ChaiJi-he, et al.. Design of the weight of B-P networks based on immune algorithm[J]. Journal of Kunming University of Science and Technology: Science and Technology, 2004, 29(2): 65-67(in Chinese)

[9] WangLingIntelligent optimization algorithm and its application[M], 2001, Beijing, Tsinghua University Press: 17-35(in Chinese)

[10] YANG Shu-xia, LI Ning. Power demand forecast based on optimized neural networks by improved genetic algorithm[C]// The International Conference on Machine Learning and Cybernetics. Dalian, 2006: 2877–2881. (in Chinese)