基于情感神经网络的风电功率预测

doi:10.11959/j.issn.1000-0801.2017005

摘要/Abstract

摘要：

风力发电功率预测对于风能并网具有重要意义。采用一种可用于复杂系统和模式建模的新型神经网络——情感神经网络，对风力发电功率进行预测。为防止ENN在训练时陷入局部最优解，提出采用遗传算法对其进行训练。采用预测误差的均方根和标准差衡量预测准确性、稳定性，对ENN性能进行了检验。结果表明，相比于人工神经网络、支持向量机和自滑动回归模型，ENN能够获得更高的预测准确率和预测可靠性。

关键词: 情感神经网络, 风力发电功率, 预测, 遗传算法

Abstract:

Accurate wind power forecasting is vital for the integration of wind power into the grid. Emotional neural network (ENN)——a new type of neural network which could be used to model complex systems and patterns, was used to forecast wind power. To prevent ENN from stucking in locally optimal solution in the process of training, genetic algorithm was proposed to train ENN. The root-mean-square and the standard deviation of the forecast errors were also adopted to measure the accuracy and reliability of the forecast to test the performance of ENN. The results demonstrate that, compared with artificial neural network, ENN can improve the accuracy and reliability of the forecast by 3.8% and 46% respectively.

Key words: emotional neural network, wind power, prediction, genetic algorithm

中图分类号:

TP183

张国玲. 基于情感神经网络的风电功率预测[J]. 电信科学, 2017, 33(3): 168-172.

Guoling ZHANG. An emotional neural network based approach for wind power prediction[J]. Telecommunications Science, 2017, 33(3): 168-172.

图/表 5

参考文献 17

[1]	谷兴凯，范高锋，王晓蓉，等. 风电功率预测技术综述[J]. 电网技术， 2007(S2): 335-338.
	GU X K , FAN G F , WANG X R, , et al. Summarization of wind power prediction technology[J]. Power System Technology, 2007(S2): 335-338.
[2]	王健，严干贵，宋薇，等. 风电功率预测技术综述[J]. 东北电力大学学报， 2011, 31(3): 20-24.
	WANG J , YAN G G , SONG W , et al. Summarization of wind power prediction technology[J]. Journal of Northeast Dianli University, 2011, 31(3): 20-24.
[3]	范高锋，裴哲义，辛耀中 . 风电功率预测的发展现状与展望[J]. 中国电力， 2011, 44(6): 38-41.
	FAN G F , PEI Z Y , XIN Y Z . Wind power prediction achievement and prospect[J]. Electric Power, 2011, 44(6): 38-41.
[4]	冬雷，王丽婕，郝颖，等. 基于自回归滑动平均模型的风力发电容量预测[J]. 太阳能学报， 2011, 32(5): 617-622.
	DONG L , WANG L J , HAO Y , et al. Prediction of wind power generation based on auto regressive moving average model[J]. Acta Energiae Solaris Sinica, 2011, 32(5): 617-622.
[5]	修春波，任晓，李艳晴，等. 基于卡尔曼滤波的风速序列短期预测方法[J]. 电工技术学报， 2014(2): 253-259.
	XIU C B , REN X , LI Y Q , et al. Short-term prediction method of wind speed series based on Kalman filtering fusion[J]. Transactions of China Electrotechnical Society, 2014(2): 253-259.
[6]	CATALAO J P S , POUSINHO H M I , MENDES V M F . An artificial neural network approach for short-term wind power forecasting in portugal[J]. International Journal of Engineering Intelligent Systems for Electrical Engineering＆Communications, 2009,17(1): 1-5.
[7]	HANADA K , HAMAJIMA T , TSUDA M , et al. Wind power forecasting using an artificial neural network for ASPCS[J]. Energy＆Power Engineering, 2013,5(4): 414-417.
[8]	范高锋，王伟胜，刘纯，等. 基于人工神经网络的风电功率预测[J]. 中国电机工程学报， 2008(34): 118-123.
	FAN G F , WANG W S , LIU C , et al. Wind power prediction based on artificial neural network[J]. Proceedings of the CSEE, 2008(34): 118-123.
[9]	ZENG J , QIAO W . Support vector machine-based short-term wind power forecasting[C]// Power Systems Conference and Exposition March 20-23, 2011, Phoenix, AZ, USA. New Jersey: IEEE Press, 2011: 1-8.
[10]	MATHABA T , XIA X , ZHANG J . hort-term wind power prediction using least-square support vector machines[C]// Power Engineering Society Conference and Exposition in Africa March 20-23, 2011, Phoenix,AZ,USA. New Jersey: IEEE Press, 2012: 1-6.
[11]	丁志勇，杨苹，杨曦，等. 基于连续时间段聚类的支持向量机风电功率预测方法[J]. 电力系统自动化， 2012,36(14): 131-135.
	DING Z Y , YANG P , YANG X , et al. Wind power prediction method based on sequential time clustering support vector machine[J]. Automation of Electric Power Systems, 2012,36(14): 131-135.
[12]	LOTFI E , AKBARZADEH T M R . Practical emotional neural networks[J]. Neural Networks, 2014,59(11): 61-72.
[13]	PAVLOS G P , ILIOPOULOS A C , TSOUTSOURAS V G , et al. First and second order non-equilibrium phase transition and evidence for non-extensive Tsallis statistics in earth's magnetosphere[J]. Physica A Statistical Mechanics ＆ its Applications, 2011,390(15): 2819-2839.
[14]	BABAIE T , KARIMIZANDI R , LUCAS C . Learning based brain emotional intelligence as a new aspect for development of an alarm system[J]. Soft Computing-A Fusion of Foundations, Methodologies and Applications, 2008,12(9): 857-873.
[15]	KHASHMAN A . Modeling cognitive and emotional processes: a novel neural network architecture[J]. Neural Networks the Official Journal of the International Neural Network Society, 2010,23(10): 1155-1163.
[16]	KHASHMAN A . A modified backpropagation learning algorithm with added emotional coefficients[J]. IEEE Transactions on Neural Networks, 2008,19(11): 1896-1909.
[17]	QUAN H , SRINIVASAN D , KHOSRAVI A . Short-term load and wind power forecasting using neural network-based prediction intervals[J]. IEEE Transactions on Neural Networks＆ Learning Systems, 2014,25(2): 303-315.

			隐含层个数
	5	10	15	20	25
均方误差	0.596 7	0.629 7	0.673 4	0.697 3	0.661 2
误差的标准差	0.006 3	0.007 1	0.006 2	0.006 7	0.007 4