Interval Prediction Technology of Photovoltaic Power Based on Parameter Optimization of Extreme Learning Machine

doi:10.16183/j.cnki.jsjtu.2022.338

Abstract

Abstract:

This paper proposes an interval prediction technology of photovoltaic (PV) power based on parameter optimization of extreme learning machine (ELM) model. First, the weighted Euclidean distance is proposed as the evaluation index of PV power prediction interval. The historical sample units are screened and the ELM training set is optimized. Then, a hybrid optimization algorithm for ELM parameters is proposed. The hidden layer input and output weights and biases parameters of the ELM model are optimized by using the elitist strategy genetic algorithm and quantile regression, and the trained model is used to predict the PV power range. Finally, an actual calculation example is constructed based on the historical data of PV power plants and weather stations. The PV power interval is predicted, and the results are compared with those obtained by other methods. The results of the calculation example show that the method proposed can greatly improve the accuracy of interval prediction while increasing the reliability of interval prediction.

Key words: photovoltaic (PV) power, interval prediction, extreme learning machine (ELM), parameter optimization, weighted Euclidean distance index

CLC Number:

TM615

HE Zhizhuo, ZHANG Ying, ZHENG Gang, ZHENG Fang, HUANG Wandi, ZHANG Shenxi, CHENG Haozhong. Interval Prediction Technology of Photovoltaic Power Based on Parameter Optimization of Extreme Learning Machine[J]. Journal of Shanghai Jiao Tong University, 2024, 58(3): 285-294.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Fig.5

Tab.2

Fig.6

Tab.3

Tab.4

References 28

[1]	REN21 Community. Renewables 2021 global status report[R]. Paris:REN21 Secretariat, 2021.
[2]	方晓涛, 严正, 王晗, 等. 考虑概率电压不平衡度越限风险的共享储能优化运行方法[J]. 上海交通大学学报, 2022, 56(7): 827-839. doi: 10.16183/j.cnki.jsjtu.2021.455
	FANG Xiaotao, YAN Zheng, WANG Han, et al. A shared energy storage optimal operation method considering the risk of probabilistic voltage unbalance factor limit violation[J]. Journal of Shanghai Jiao Tong University, 2022, 56(7): 827-839.
[3]	丁明, 王伟胜, 王秀丽, 等. 大规模光伏发电对电力系统影响综述[J]. 中国电机工程学报, 2014, 34(1): 1-14.
	DING Ming, WANG Weisheng, WANG Xiuli, et al. A review on the effect of large-scale PV generation on power systems[J]. Proceedings of the CSEE, 2014, 34(1): 1-14.
[4]	赖昌伟, 黎静华, 陈博, 等. 光伏发电出力预测技术研究综述[J]. 电工技术学报, 2019, 34(6): 1201-1217.
	LAI Changwei, LI Jinghua, CHEN Bo, et al. Review of photovoltaic power output prediction technology[J]. Transactions of China Electrotechnical Society, 2019, 34(6). 1201-1217.
[5]	LI Y T, SU Y, SHU L J. An ARMAX model for forecasting the power output of a grid connected photovoltaic system[J]. Renewable Energy, 2014, 66: 78-89. doi: 10.1016/j.renene.2013.11.067 URL
[6]	黄磊, 舒杰, 姜桂秀, 等. 基于多维时间序列局部支持向量回归的微网光伏发电预测[J]. 电力系统自动化, 2014, 38(5): 19-24.
	HUANG Lei, SHU Jie, JIANG Guixiu, et al. Photovoltaic generation forecast based on multidimensional time-series and local support vector regression in microgrids[J]. Automation of Electric Power Systems, 2014, 38(5): 19-24.
[7]	PERSSON C, BACHER P, SHIGA T, et al. Multi-site solar power forecasting using gradient boosted regression trees[J]. Solar Energy, 2017, 150: 423-436. doi: 10.1016/j.solener.2017.04.066 URL
[8]	SHANG C F, WEI P C. Enhanced support vector regression based forecast engine to predict solar power output[J]. Renewable Energy, 2018, 127: 269-283. doi: 10.1016/j.renene.2018.04.067 URL
[9]	BEHERA M K, NAYAK N. A comparative study on short-term PV power forecasting using decomposition based optimized extreme learning machine algorithm[J]. Engineering Science & Technology, 2020, 23(1): 156-167.
[10]	张倩, 马愿, 李国丽, 等. 频域分解和深度学习算法在短期负荷及光伏功率预测中的应用[J]. 中国电机工程学报, 2019, 39(8): 2221-2230.
	ZHANG Qian, MA Yuan, LI Guoli, et al. Application of frequency domain decomposition and deep learning algorithm in short-term load and photovoltaic power prediction[J]. Proceedings of the CSEE, 2019, 39(8): 2221-2230.
[11]	王岩, 陈耀然, 韩兆龙, 等. 基于互信息理论与递归神经网络的短期风速预测模型[J]. 上海交通大学学报, 2021, 55(9): 1080-1086. doi: 10.16183/j.cnki.jsjtu.2020.433
	WANG Yan, CHEN Yaoran, HAN Zhaolong, et al. Short-term wind speed forecasting model based on mutual information and recursive neural network[J]. Journal of Shanghai Jiao Tong University, 2021, 55(9): 1080-1086.
[12]	KHOSRAVI A, MAZLOUMI E, NAHAVANDI S, et al. Prediction intervals to account for uncertainties in travel time prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(2): 537-547. doi: 10.1109/TITS.2011.2106209 URL
[13]	KHOSRAVI A, NAHAVANDI S, CREIGHTON D, et al. Comprehensive review of neural network-based prediction intervals and new advances[J]. IEEE Transactions on Neural Networks, 2011, 22(9): 1341-1356. doi: 10.1109/TNN.2011.2162110 pmid: 21803683
[14]	董雷, 周文萍, 张沛, 等. 基于动态贝叶斯网络的光伏发电短期概率预测[J]. 中国电机工程学报, 2013, 33(Sup.1) 38-45.
	DONG Lei, ZHOU Wenping, ZHANG Pei, et al. Short-term photovoltaic output forecast based on dynamic Bayesian network theory[J]. Proceedings of the CSEE, 2013, 33(Sup.1) 38-45.
[15]	VOYANT C, DARRAS C, MUSELLI M, et al. Bayesian rules and stochastic models for high accuracy prediction of solar radiation[J]. Applied Energy, 2014, 114: 218-226. doi: 10.1016/j.apenergy.2013.09.051 URL
[16]	KHOSRAVI A, NAHAVANDI S, SRINIVASAN D, et al. Constructing optimal prediction intervals by using neural networks and bootstrap method[J]. IEEE Transactions on Neural Networks & Learning Systems, 2015, 26(8): 1810-1815.
[17]	WAN C, XU Z, PINSON P, et al. Probabilistic forecasting of wind power generation using extreme learning machine[J]. IEEE Transactions on Power Systems, 2014, 29(3): 1033-1044. doi: 10.1109/TPWRS.2013.2287871 URL
[18]	KHOSRAVI A, NAHAVANDI S, CREIGHTON D, et al. Lower upper bound estimation method for construction of neural network-based prediction intervals[J]. IEEE Transactions on Neural Networks, 2011, 22(3): 337-346. doi: 10.1109/TNN.2010.2096824 pmid: 21189235
[19]	叶林, 马明顺, 靳晶新, 等. 考虑风电-光伏功率相关性的因子分析-极限学习机聚合方法[J]. 电力系统自动化, 2021, 45(23): 31-40.
	YE Lin, MA Mingshun, JIN Jingxin, et al. Factor analysis-extreme learning machine aggregation method considering correlation of wind power and photovoltaic power[J]. Automation of Electric Power Systems, 2021, 45(23): 31-40.
[20]	WAN C, LIN J, SONG Y H, et al. Probabilistic forecasting of photovoltaic generation: An efficient statistical approach[J]. IEEE Transactions on Power Systems, 2017, 32(3): 2471-2472. doi: 10.1109/TPWRS.2016.2608740 URL
[21]	LI S, WANG P, GOEL L. A novel wavelet-based ensemble method for short-term load forecasting with hybrid neural networks and feature selection[J]. IEEE Transactions on Power Systems, 2016, 31(3): 1788-1798. doi: 10.1109/TPWRS.2015.2438322 URL
[22]	杨锡运, 关文渊, 刘玉奇, 等. 基于粒子群优化的核极限学习机模型的风电功率区间预测方法[J]. 中国电机工程学报, 2015, 35(Sup.1): 146-153.
	YANG Xiyun, GUAN Wenyuan, LIU Yuqi, et al. Prediction intervals forecasts of wind power based on PSO-KELM[J]. Proceedings of the CSEE, 2015, 35(Sup.1): 146-153.
[23]	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: A new learning scheme of feedforward neural networks[C]// 2004 IEEE International Joint Conference on Neural Networks. Budapest, Hungary: IEEE, 2004: 985-990.
[24]	HUANG G, ZHU Q, SIEW C. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501. doi: 10.1016/j.neucom.2005.12.126 URL
[25]	KOENKER R. Quantile regression[M]. Cambridge: Cambridge University Press, 2005.
[26]	丁明, 鲍玉莹, 毕锐. 应用改进马尔科夫链的光伏出力时间序列模拟[J]. 电网技术, 2016, 40(2): 459-464.
	DING Ming, BAO Yuying, BI Rui. Time series simulation of photovoltaic output using improved Markov chain[J]. Power System Technology, 2016, 40(2): 459-464.
[27]	黎敏, 林湘宁, 张哲原, 等. 超短期光伏出力区间预测算法及其应用[J]. 电力系统自动化, 2019, 43(3): 10-18.
	LI Min, LIN Xiangning, ZHANG Zheyuan, et al. Interval prediction algorithm for ultra-short-term photovoltaic output and its application[J]. Automation of Electric Power Systems, 2019, 43(3): 10-18.
[28]	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, 31(34): 28-35.
	DAI Qian, DUAN Shanxu, CAI Tao, et al. Short-term PV generation system forecasting model without irradiation based on weather type clustering[J]. Proceedings of the CSEE, 2011, 31(34): 28-35.

p_PINC/%	p_PICP/%	p_PINAW/%
95	95.12	2.69
90	95.12	1.93
85	92.68	1.48
80	87.80	1.18

p_PINC /%	p_PICP/%	p_PINAW/%
95	100	12.87
90	100	6.23
85	97.56	3.67
80	90.24	3.03

p_PINC /%	p_PICP/%	p_PINAW/%
95	97.73	7.87
90	97.73	4.85
85	95.45	3.36
80	90.91	2.67

日期	p_PINC/%	方法I		方法II		方法III		方法IV
日期	p_PINC/%	p_PICP/%	p_PINAW/%	p_PICP/%	p_PINAW/%	p_PICP/%	p_PINAW/%	p_PICP/%	p_PINAW/%
7月1日	95	95.12	2.69	95.12	2.78	97.56	7.82	93.90	3.00
7月1日	90	95.12	1.93	92.68	1.95	97.56	4.50	88.78	2.01
7月1日	85	92.68	1.48	92.68	1.60	95.12	4.42	86.83	1.51
7月1日	80	87.80	1.18	87.80	1.21	90.24	3.91	85.37	1.23
8月3日	95	100.00	12.87	100.00	14.31	100.00	14.35	99.76	14.27
8月3日	90	100.00	6.23	100.00	6.95	97.56	7.11	99.27	6.93
8月3日	85	97.56	3.67	95.12	3.71	95.12	4.66	97.07	3.81
8月3日	80	90.24	3.03	90.24	3.11	95.12	3.99	92.44	3.12
9月10日	95	97.73	7.87	100.00	8.52	100.00	22.30	97.50	9.28
9月10日	90	97.73	4.85	100.00	4.97	100.00	8.92	96.14	5.47
9月10日	85	95.45	3.36	93.18	3.64	95.45	8.46	95.68	3.64
9月10日	80	90.91	2.67	88.64	2.77	95.45	5.37	92.56	2.91