The Ultra-Short-Term Forecast of Photovoltaic Power Output Based on Grey Relational Analysis and Empirical Mode Decomposition

doi:10.11930/j.issn.1004-9649.201707137

Abstract

Abstract: PV power output is affected by solar irradiance, temperature and instantaneous cloud, and its generation presents obvious non-stationary features, which increases the difficulty of prediction. To reduce the influence of output volatility on the prediction effectiveness and satisfy the accuracy requirement of ultra-short-term prediction, this paper proposes a two-stage method to build input samples. Firstly, the grey correlation principle is applied to build similar sample collection. Then, the empirical mode decomposition method is used to decompose the output sequence of similar days. After getting the relatively stable function and the remaining component, the support vector machine, a data mining tool, is used to do rolling prediction for every component. Finally, all the prediction results are added to get the prediction of next moment. A case study proves that the root-mean-square error of the combined model shows a high precision of 1.93, which can provide more decision-making support for PV power scheduling.

Key words: grey correlation principle, empirical mode decomposition method, photovoltaic, ultra-short-term prediction

CLC Number:

TM615

SUO Chunmei, SUN Jian, ZHANG Zongfeng, WANG Xianzong. The Ultra-Short-Term Forecast of Photovoltaic Power Output Based on Grey Relational Analysis and Empirical Mode Decomposition[J]. Electric Power, 2017, 50(12): 159-164.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.201707137

https://www.electricpower.com.cn/EN/Y2017/V50/I12/159

References

[1] 国家能源局. 2016年光伏发电统计信息[EB/OL]. [2017-02-04]http://www.nea.gov.cn/2017-02/04/c_136030860.htm.
[2] 陈炜,艾欣,吴涛,等. 光伏并网发电系统对电网的影响研究综
述[J]. 电力自动化设备,2013,33（2）：26-32.
3 CHEN Wei, AI Xin, WU Tao, et al . Influence of grid-connected photovoltaic system on power network[J]. Electric Power Automation Equipment, 2013, 33(2): 26-32.
[3] 张雪莉,刘其辉,马会萌,等. 光伏电站输出功率影响因素分析[J]. 电网与清洁能源,2012,28（5）：76-81.
ZHANG Xueli, LIU Qihui, MA Huimeng, et al Analysis of influencingfactors of output power of photovoltaic power plant[J]. Power System and Clean Energy, 2012, 28(5): 76~81.
[4] 杨超颖,王金浩,王硕,等. 基于拟牛顿法小波神经网络的光伏发电系统短期功率预测模型[J]. 中国电力,2014,47（6）：117-124.
YANG Chaoying, WANG Jinhao, WANG Shuo, et al . A forecasting method of short-term power output of photovoltaic system based on wavelet neural network trained by quasi-newton nethod [J]. Electric Power, 2014, 47(6): 117-124.
[5] YONA A, SENJYU T, SABER A Y, et al . Application of neural network to 24-hour-ahead generating power forecasting for PV system[C]// IEEE Power and Energy Society General Meeting- Conversion and Delivery of Electrical Energy in the 21st Century. 2008.
[6] 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 Guangmin. Photovoltaic power generation output forecasting based on support vector machine regression technique[J]. Electric Power, 2008, 41(2): 74-78.
[7] 罗毅,邢校萄. 基于小波变换和支持向量机的短期光伏发电功率预测[J]. 新能源进展,2014,2（5）：380-384.
LUO Yi, XING Xiaotao. Short-termforecasting of photovoltaic power generation based on wavelet decomposition and support vector machine[J]. Advances in New and Renewable Energy, 2014, 2(5): 380-384.
[8] 朱永强,田军. 最小二乘支持向量机在光伏功率预测中的应用[J]. 电网技术,2011,35（7）：54-59.
ZHU Yongqiang, TIAN Jun. Application ofleast square support vector machine in photovoltaic power forecasting [J]. Power System Technology, 2011, 35(7): 54-59.
[9] 傅美平,马红伟,毛建容. 基于相似日和最小二乘支持向量机的光伏发电量短期预测[J]. 电力系统保护与控制,2012,40（16）：65-69.
FU Meiping, MA Hongwei, MAO Jianrong. Short-term photovoltaic power forecasting based on similar days and least square support vector machine[J]. Power System Protection and Control, 2012, 40(16): 65-69.
[10] 茆美琴,龚文剑,张榴晨,等. 基于EEMD-SVM方法的光伏电站短期出力预测[J]. 中国电机工程学报,2013,33（34）：17-24.
MAO Meiqin, GONG Wenjian, ZHANG Liuchen, et al . Short- term photovoltaic generation forecasting based on EEMD-SVM combined method [J]. Proceedings of the CSEE, 2013, 33(34): 17-24.
[11] 杜翠. 针对气象数据弱相关的光伏输出功率预测方法研究[D].北京：华北电力大学,2016.
[12] 刘思峰,郭天榜,党耀国,等.灰色系统理论及其应用[M]. 2版. 北京：科学出版社,1999：1-18.
[13] HYANG N E. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proc. R. Soc. Lond. A. 1998, 454(1971): 903-995.
[14] HUANG N E, SHEN Z, LONG S R, et al . A new view of nonlinear water waves: the Hillbert spectrum[J]. Annual Review of Fluid Mechanics, 1999, 31: 417-457.
[15] HASIMAH A, MUTHUSAMY H, SAZALI Y, et al . Facial emotion recognition using empirical mode decomposition[J]. Expert System with Application,2015, 42(3): 1261-1277.
[16] GUNTURKUN U. Bivariate empirical mode decomposition for cognitive radar scene analysis[J]. IEEE Signal Processing Letters,2015, 22(5): 603-607.
[17] TERRADAS J, OLIVER R, BALLESTER J L. Application of statistical techniques to the analysis of solar coronal oscillation[J]. The Astrophysical Journal, 2004(614): 435-447.
[18] VAPNIK V N. The nature of statistical learning theory[M]. Berlin: springer-verlag, 1995.