A Forecasting Method of Short-Term Power Output of Photovoltaic System Based on Wavelet Neural Network Trained by Quasi-Newton Method

doi:10.11930/j.issn.1004-9649.2014.6.117.7

Abstract

Abstract: The randomness of the power output of a photovoltaic system has an impact on the power grid. So it is needed to strengthen the study of the power output forecasting of photovoltaic systems. In this paper, the short-term forecasting model of PV station power, based on wavelet neural network which is trained by quasi-Newton method, was proposed. The comparison experiments were made for the forecasting model above and the forecasting models based on BP neural network which is trained by quasi-Newton methed, traditional BP algorithm or combining increasing momentum method with varying learning rate method. The experimental results indicate that the short-term forecasting model of PV station power, based on BP neural network with quasi-Newton method, can significantly improve the precision of PV power prediction, and the method based on wavelet neural network with quasi-Newton method did better than that based on BP neural network. Especially, it can significantly improve the precision of PV power prediction under circumstance with low irradiance, such as in daily morning and evening time, rainfalls and snow as well as fluctuating power inflection point.

Key words: photovoltaic, power forecasting, wavelet neural network, BP neural network, quasi-Newton method, forecasting model

CLC Number:

TM615

YANG Chao-ying, WANG Jin-hao, WANG Shuo, XU Yong-hai, HUANG Hao. A Forecasting Method of Short-Term Power Output of Photovoltaic System Based on Wavelet Neural Network Trained by Quasi-Newton Method[J]. Electric Power, 2014, 47(6): 117-124.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.2014.6.117.7

https://www.electricpower.com.cn/EN/Y2014/V47/I6/117

References

[1] RIKOS E, TSELEPIS E, HOYER K C, et al . Stability and power quality issues in microgrids under weather disturbances study of photovoltaic integration [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2008, 1(3): 170-180.
[2] YUN T T. Impact on the power system with a large penetration of photovoltaic generation [D]. UK: The University of Manchester Institute of Science and Technology. 2004: 7-47.
[3] XIAO W, LIND M G J, DUNFORD W G, et al . Real-time identification of optimal operating points in photovoltaic power systems [J]. IEEE Transactions on Industrial Electronics, 2006, 53(4): 1017-1026.
[4] MORENO M A, de la Rosa, J., POSADILLO R. Short term forecasting of solar radiation [C]//IEEE International Symposium on Industrial Electronics, ISIE, Cambridge, 2008: 1537-1541.
[5] 栗然,李广敏. 基于支持向量机回归的光伏发电出力预测[J].中国电力,2008,41（2）：74-78.
LI Ran, LI Guang-min. Photovoltaic power generation output forecasting based on support vector machinery regression technique [J]. Electric Power, 2008, 41(2): 74-78.
[6] 曹石亚,李琼慧,黄碧斌,等. 光伏发电技术经济分析及发展预测[J]. 中国电力,2012,45（8）：64-68.
CAO Shi-ya, LI Qiong-hui, HUANG Bi-bin, et al . Economic analysis and development forecast of photovoltaic power technology [J]. Electric Power, 2012, 45(8): 64-68.
[7] 丁明,徐宁舟. 基于马尔可夫链的光伏发电系统输出功率短期预测方法[J]. 电网技术,2011,35（1）：152-157.
DING Ming, XU Ning-zhou. A method to forecast short-term output power of photovoltaic generation system based on Markov Chain [J]. Power System Technology, 2011, 35(1): 152-157.
[8] OUDJANA S H, HELLAL A, MAHAMED I H. Short term photovoltaic power generation forecasting using neural network [C]//International Joint Conference on Neural Networks, Venice, 2011: 706-711.
[9] 陈昌松,段善旭,殷进军. 基于神经网络的光伏阵列发电预测模型的设计[J]. 电工技术学报,2009,24（9）：153-158.
CHEN Chang-song, DUAN Shan-xu, YIN Jin-jun. Design of photovoltaic array power forecasting model based on neutral network [J]. Transactions of China Electrotechnical Society, 2009, 24(9): 153-158.
[10] 张岚,张艳霞,郭嫦敏,等. 基于神经网络的光伏系统发电功率预测[J]. 中国电力,2010,43（9）：75-78.
ZHANG Lan, ZHANG Yan-xia, GUO Chang-min, et al . Photovoltaic system power forecasting based on neutral networks [J]. Electric Power, 2010, 43(9): 75-78.
[11] 代倩,段善旭,蔡涛,等. 基于天气类型聚类识别的光伏系统短期无辐照度发电预测模型研究[J]. 中国电机工程学报,2011,33（3）：28-35.
DAI Qian, DUAN Shan-xu, CAI Tao, et al . Short-term PV generation system forecasting model without irradiation based on weather type clustering [J]. Proceedings of the CSEE, 2011, 33(3): 28-35.
[12] 丁明,王磊,毕锐. 基于改进BP神经网络的光伏发电系统输出功率短期预测模型[J]. 电力系统保护与控制,2012,40（11）：93-99.
DING Ming, WANG Lei, BI Rui. A short-term prediction model to forecast output power of photovoltaic system based on improved BP neural network [J]. Power System Protection and Control, 2012, 40(11): 93-99.
[13] 周松林,茆美琴,苏建徽. 基于小波分析与支持向量机的风速预测[J]. 太阳能学报,2012.3,33（3）：452-456.
ZHOU Song-lin, MAO Mei-qin, SU Jian-hui. Wind speed forecasting based on wavelet analysis and support vector machine [J]. Acta Energiae Solaris Sinica, 2012.3, 33(3): 452-456.
[14] 孙文涛,刘涤尘,赵洁. 基于小波-神经网络的日光照辐射总量及光伏发电量预测[C]//中国高等学校电力系统及其自动化专业第二十六届学术年会,上海,2010：225-230.
[15] JEWELL W T, UNRUH T D. Limits on cloud-induced fluctuation in photovoltaic generation[J]. IEEE Transactions on Energy Conversion. 1999, 5(1): 8-14.
[16] MELLIT A, ARAB A H, KHORISSI N, et al . An ANFIS-based forecasting for solar radiation data from sunshine duration and ambient temperature[C]//IEEE Power Engineering Society General Meeting, Tampa, USA, 2007: 315-320.