Forecasting increasing rate of power consumption based on immune genetic algorithm combined with neural network

Abstract

Considering the factors affecting the increasing rate of power consumption, the BP neural network structure and the neural network forecasting model of the increasing rate of power consumption were established. Immune genetic algorithm was applied to optimizing the weight from input layer to hidden layer, from hidden layer to output layer, and the threshold value of neuron nodes in hidden and output layers. Finally, training the related data of the increasing rate of power consumption from 1980 to 2000 in China, a nonlinear network model between the increasing rate of power consumption and influencing factors was obtained. The model was adopted to forecasting the increasing rate of power consumption from 2001 to 2005, and the average absolute error ratio of forecasting results is 13.521 8%. Compared with the ordinary neural network optimized by genetic algorithm, the results show that this method has better forecasting accuracy and stability for forecasting the increasing rate of power consumption.

Keywords

immune genetic algorithm / neural network / power consumption / increasing rate / forecast

References

[1] LiuH.-y., FanH.-jun.. Prediction of production performances of oil and injection wells with multivariate time series method [J]. Journal of the University of Petroleum, 2001, 25(2): 70-72

[2] LiangY.-li.Studying for cyclic fluctuation characteristics and influencing element of electricity demand in China [D], 2005, Beijing, North China Electricity Power University

[3] YangS.-xia.Studies on the expansion-contraction law and turning points of power demand cycle in China [D], 2006, Beijing, North China Electricity Power University

[4] PanA.-j., WangK.-fa.. The forecasting model and application of multifactor time series data GM(1,N) [J]. Journal of Third Military Medicine University, 2003, 25(19): 1774-1775

[5] HOU Tung-Hsu(Tony)Using neural networks and immune algorithms to find the optimal parameter for an IC wire bonding process [J]. Expert Systems with Applications, 2008, 34(1): 427-436

[6] ZhangH.-l., ZouZ., LiJ., ChenX.-tao.. Flame image recognition of alumina rotary kiln by artificial neural network and support vector machine methods [J]. Journal of Central South University of Technology, 2008, 15(1): 39-43

[7] TongC.-r., LiM.-z., WuJ.-c., LiuD.-bin.. Soft sensor model of sodium aluminate solution based on BP neural network with inverse mapping algorithm [J]. The Chinese Journal of Nonferrous Metals, 2008, 18(5): 917-922

[8] DingY.-s., ZhangT.-liang.. Using Chou’s pseudo amino acid composition to predict subcellular localization of apoptosis proteins: An approach with immune genetic algorithm-based ensemble classifier [J]. Pattern Recognition Letters, 2008, 29(13): 1887-1892

[9] ChenT. C., HsiehY. C.. Using immune-based genetic algorithms for single trader’s periodic marketing problem [J]. Mathematical and Computer Modelling, 2008, 48(3/4): 420-428

[10] ComanA., IonescuA., CandauY.. Hourly ozone prediction for a 24-h horizon using neural networks [J]. Environmental Modelling & Software, 2008, 23(12): 1407-1421

[11] MccallJ.. Genetic algorithms for modelling and optimization [J]. Journal of Computational and Applied Mathematics, 2005, 184: 205-222

[12] NasseriM., AsghariK., AbediniM. J.. Optimized scenario for rainfall forecasting using genetic algorithm coupled with artificial neural network [J]. Expert Systems with Applications, 2008, 35: 1415-1421

[13] XuX.-s., ZhuJ.. An improved immune genetic algorithm for fuzzy control [J]. Information and Control, 2003, 35(1): 64-68

[14] XuW., HeZ.-z., HuangS.-t., YangL.. Recurrent fuzzy neural network based on immune genetic algorithm [J]. Journal of Jilin Univcersity: Information Scicncc Edition, 2005, 23(2): 162-166

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