Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction

doi:10.11930/j.issn.1004-9649.202406005

Abstract

Abstract:

A short-term photovoltaic power combination prediction method based on similar day selection and data reconstruction is proposed to address the strong randomness of photovoltaic power. Firstly, clustering analysis of photovoltaic power is performed using the kernel fuzzy C-means algorithm, and the main influencing features are extracted through the maximum information coefficient. Secondly, the cooperative game theory is used to calculate the comprehensive correlation coefficient between the predicted days and the historical days, and the historical days with strong correlation are selected to construct the training set. Then, the variational mode decomposition method is used to decompose the photovoltaic power into several subsequences, and the permutation entropy is calculated and reconstructed into trend, low-frequency, and high-frequency terms. Finally, the long short-term memory neural networks are used to predict the trend and low-frequency items, while the convolutional neural network-bidirectional long short-term memory-attention models are used to predict the high-frequency items. The final prediction result is obtained by overlaying the results. Through practical examples, it has been verified that under different weather conditions, the overall prediction error of the model is the smallest, which can effectively improve the prediction accuracy.

Key words: photovoltaic power, similar days, variational mode decomposition, bidirectional long short term memory neural network, combination prediction

Qingbin CHEN, Genghuang YANG, Liqing GENG, Juan SU, Jingsheng SUN. Short Term Photovoltaic Power Combination Prediction Method Based on Similar Day Selection and Data Reconstruction[J]. Electric Power, 2024, 57(12): 71-81.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202406005

https://www.electricpower.com.cn/EN/Y2024/V57/I12/71

Figures/Tables 12

References 23

1	王东风, 刘婧, 黄宇, 等. 结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究[J]. 太阳能学报, 2024, 45 (2): 443- 450.
	WANG Dongfeng, LIU Jing, HUANG Yu, et al. Photovoltaic power prediction method combinating solar radiation calculation and CNN-LSTM[J]. Acta Energiae Solaris Sinica, 2024, 45 (2): 443- 450.
2	ZHANG Y G, PAN Z Y, WANG H, et al. Achieving wind power and photovoltaic power prediction: an intelligent prediction system based on a deep learning approach[J]. Energy, 2023, 283, 129005. DOI
3	黄泽, 毕贵红, 谢旭, 等. 基于MBI-PBI-ResNet的超短期光伏功率预测[J]. 电力系统保护与控制, 2024, 52 (2): 165- 176.
	HUANG Ze, BI Guihong, XIE Xu, et al. Ultra-short-term PV power prediction based on MBI-PBI-ResNet[J]. Power System Protection and Control, 2024, 52 (2): 165- 176.
4	邱建, 张建新, 朱煜昆, 等. 光伏并网稳定控制系统设计方法及其在南方电网的应用与实践[J]. 南方电网技术, 2024, 18 (7): 139- 147.
	QIU Jian, ZHANG Jianxin, ZHUN Yukun, et al. Design method of stability control system for photovoltaic grid-connected station and its application and practice in CSG[J]. Southern Power System Technology, 2024, 18 (7): 139- 147.
5	解振学, 林帆, 王若谷, 等. 基于时序动态回归的超短期光伏发电功率预测方法[J]. 智慧电力, 2022, 50 (7): 45- 51.
	XIE Zhenxue, LIN Fan, WANG Ruogu, et al. Very short-term photovoltaic power forecasting method based on time series dynamic regression[J]. Smart Power, 2022, 50 (7): 45- 51.
6	郭洪武, 车建峰, 闫钇汛, 等. 基于无爬坡事件定义标准晴空集的短期光伏功率预测[J]. 中国电力, 2023, 56 (9): 187- 195.
	GUO Hongwu, CHE Jianfeng , YAN Yixun, et al. Short-term photovoltaic power prediction based on standard clear sky set defined by no climbing event[J]. Smart Power, 2023, 56 (9): 187- 195.
7	龙小慧, 秦际赟, 张青雷, 等. 基于相似日聚类及模态分解的短期光伏发电功率组合预测研究[J]. 电网技术, 2024, 48 (7): 2948- 2957.
	LONG Xiaohui, QIN Jiyun, ZHANG Qinglei, et al. Short-term photovoltaic power prediction study based on similar day clustering and modal decomposition[J]. Power System Technology, 2024, 48 (7): 2948- 2957.
8	李争, 张杰, 徐若思, 等. 基于相似日聚类和PCC-VMD-SSA-KELM模型的短期光伏功率预测[J]. 太阳能学报, 2024, 45 (2): 460- 468.
	LI Zheng, ZHANG Jie, XU Ruosi, et al. Short term photovoltaic power prediction based on similar day clustering and PCC-VMD-SSA-KELM model[J]. Acta Energiae Solaris Sinica, 2024, 45 (2): 460- 468.
9	SMYL S, DUDEK G, PELKA P. ES-dRNN: a hybrid exponential smoothing and dilated recurrent neural network model for short-term load forecasting[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35 (8): 11346- 11358. DOI
10	ZHANG N, LI Z Y, ZOU X, et al. Comparison of three short-term load forecast models in Southern California[J]. Energy, 2019, 189, 116358. DOI
11	孟安波, 许炫淙, 陈嘉铭, 等. 基于强化学习和组合式深度学习模型的超短期光伏功率预测[J]. 电网技术, 2021, 45 (12): 4721- 4728.
	MENG Anbo, XU Xuancong, CHEN Jiaming, et al. Ultra short term photovoltaic power prediction based on reinforcement learning and combined deep learning model[J]. Power System Technology, 2021, 45 (12): 4721- 4728.
12	陈铁, 张治藩, 李咸善, 等. 基于混合模态分解和LSTM-CNN的变压器油中溶解气体浓度预测[J]. 中国电力, 2023, 56 (1): 132- 141.
	CHEN Tie, ZHANG Zhifan, LI Xianshan, et al. Prediction of dissolved gas concentration in transformer oil based on hybrid mode decomposition and LSTM-CNN[J]. Electric Power, 2023, 56 (1): 132- 141.
13	ZHONG J Q, LIU L Y, SUN Q, et al. Prediction of photovoltaic power generation based on general regression and back propagation neural network[J]. Energy Procedia, 2018, 152, 1224- 1229. DOI
14	李秉晨, 于惠钧, 刘靖宇. 基于Kmeans和CEEMD-PE-LSTM 的短期光伏发电功率预测[J]. 水电能源科学, 2021, 39 (4): 204- 208.
	LI Bingchen, YU Huijun, LIU Jingyu. Prediction of short-term photovoltaic power generation based on Kmeans and CEEMD-PE-LSTM[J]. Water Resources and Power, 2021, 39 (4): 204- 208.
15	冯沛儒, 江桂芬, 徐加银, 等. 基于CEEMD-BiLSTM-RFR的短期光伏功率预测[J]. 科学技术与工程, 2024, 24 (5): 1955- 1962. DOI
	FENG Peiru, JIANG Guifen, XU Jiayin, et al. Short-term photovoltaic power prediction based on CEEMD-BiLSTM-RFR[J]. Science Technology and Engineering, 2024, 24 (5): 1955- 1962. DOI
16	CHEN X, DING K, ZHANG J W, et al. Online prediction of ultra-short-term photovoltaic power using chaotic characteristic analysis, improved PSO and KELM[J]. Energy, 2022, 248, 123574. DOI
17	LI P T, ZHOU K L, LU X H, et al. A hybrid deep learning model for short-term PV power forecasting[J]. Applied Energy, 2020, 259, 114216. DOI
18	BÜYÜKŞAHIN Ü Ç, ERTEKIN Ş. Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition[J]. Neurocomputing, 2019, 361, 151- 163. DOI
19	王开艳, 杜浩东, 贾嵘, 等. 基于相似日聚类和QR-CNN-BiLSTM模型的光伏功率短期区间概率预测[J]. 高电压技术, 2022, 48 (11): 4372- 4384.
	WANG Kaiyan, DU Haodong, JIA Rong, et al. Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model[J]. High Voltage Engineering, 2022, 48 (11): 4372- 4384.
20	赵雅雪, 王旭, 蒋传文, 等. 基于最大信息系数相关性分析和改进多层级门控LSTM的短期电价预测方法[J]. 中国电机工程学报, 2021, 41 (1): 135- 146.
	ZHAO Yaxue, WANG Xu, JIANG Chuanwen, et al. A novel short-term electricity price forecasting method based on correlation analysis with the maximal information coefficient and modified multi-hierachy gated LSTM[J]. Proceedings of the CSEE, 2021, 41 (1): 135- 146.
21	赵源上, 林伟芳. 基于皮尔逊相关系数融合密度峰值和熵权法典型场景研究[J]. 中国电力, 2023, 56 (5): 193- 202.
	ZHAO Yuanshang, LIN Weifang. Research on typical scenarios based on fusion density peak value and entropy weight method of Pearson’s correlation coefficient[J]. Electric Power, 2023, 56 (5): 193- 202.
22	于群, 霍筱东, 何剑, 等. 基于斯皮尔曼相关系数和系统惯量的中国电网停电事故趋势预测[J]. 中国电机工程学报, 2023, 43 (14): 5372- 5380.
	YU Qun, HUO Xiaodong, HE Jian, et al. Trend prediction of power blackout accidents in Chinese power grid based on Spearman’s correlation coefficient and system inertia[J]. Proceedings of the CSEE, 2023, 43 (14): 5372- 5380.
23	GAO C Z, HOU J P, GONG J. Study on the symbiotic development path of traditional villages in the county based on the grey relation analysis: the case of Xunxian county in Henan, China[J]. Grey Systems: Theory and Application, 2023, 13 (1): 193- 205. DOI

影响特征	晴天	多云	雨天
组件温度	0.506	0.346	0.385
温度	0.280	0.192	0.233
气压	0.423	0.354	0.327
湿度	0.210	0.169	0.234
总辐射	0.703	0.604	0.579
直射辐射	0.688	0.600	0.575
散射辐射	0.395	0.300	0.413

影响特征	晴天	多云	雨天
组件温度	0.506	0.346	0.385
温度	0.280	0.192	0.233
气压	0.423	0.354	0.327
湿度	0.210	0.169	0.234
总辐射	0.703	0.604	0.579
直射辐射	0.688	0.600	0.575
散射辐射	0.395	0.300	0.413

日期	M₁			M₂			M₃			M₄
日期	Q₁	Q₂	Q₃	Q₁	Q₂	Q₃	Q₁	Q₂	Q₃	Q₁	Q₂	Q₃
06-04	0.890	0.979	0.981	0.840	0.977	0.977	0.519	0.514	0.506	1.312	1.542	1.550
06-05	0.891	0.962	0.964	0.950	0.975	0.977	0.519	0.535	0.532	2.345	2.456	2.457
06-08	0.955	0.955	0.958	0.908	0.938	0.938	0.585	0.593	0.605	1.848	1.877	1.890
06-10	0.839	0.979	0.979	0.720	0.987	0.985	0.628	0.603	0.602	0.931	1.363	1.362
06-15	0.977	0.995	0.996	0.961	0.996	0.996	0.570	0.490	0.485	2.505	2.478	2.474
06-16	0.980	0.998	0.998	0.952	0.998	0.998	0.512	0.472	0.469	0.609	0.599	0.596
06-27	0.979	0.999	0.999	0.950	0.999	0.999	0.600	0.456	0.454	2.529	2.454	2.452
06-30	0.977	0.995	0.995	0.947	0.994	0.994	0.417	0.477	0.473	2.339	2.464	2.460
07-01	0.941	0.959	0.959	0.865	0.966	0.965	0.442	0.502	0.500	2.248	2.427	2.424
07-14	0.969	0.999	1.000	0.914	0.999	0.999	0.871	0.938	0.927	2.734	2.915	2.905
07-18	0.944	0.899	0.905	0.880	0.937	0.933	0.867	0.813	0.836	2.062	2.049	2.068
07-19	0.968	0.958	0.963	0.937	0.941	0.947	0.854	0.895	0.907	0.369	0.387	0.391
07-20	0.948	0.934	0.939	0.926	0.941	0.948	0.838	0.816	0.838	0.032	0.015	0.022
07-24	0.966	0.975	0.976	0.916	0.973	0.970	0.852	0.899	0.906	2.711	2.823	2.828
07-27	0.969	1.000	1.000	0.924	0.999	1.000	0.888	0.975	0.981	2.779	2.972	2.979
07-28	0.932	0.975	0.977	0.989	0.973	0.977	0.862	0.895	0.905	0.786	0.873	0.881

日期	M₁			M₂			M₃			M₄
日期	Q₁	Q₂	Q₃	Q₁	Q₂	Q₃	Q₁	Q₂	Q₃	Q₁	Q₂	Q₃
06-04	0.890	0.979	0.981	0.840	0.977	0.977	0.519	0.514	0.506	1.312	1.542	1.550
06-05	0.891	0.962	0.964	0.950	0.975	0.977	0.519	0.535	0.532	2.345	2.456	2.457
06-08	0.955	0.955	0.958	0.908	0.938	0.938	0.585	0.593	0.605	1.848	1.877	1.890
06-10	0.839	0.979	0.979	0.720	0.987	0.985	0.628	0.603	0.602	0.931	1.363	1.362
06-15	0.977	0.995	0.996	0.961	0.996	0.996	0.570	0.490	0.485	2.505	2.478	2.474
06-16	0.980	0.998	0.998	0.952	0.998	0.998	0.512	0.472	0.469	0.609	0.599	0.596
06-27	0.979	0.999	0.999	0.950	0.999	0.999	0.600	0.456	0.454	2.529	2.454	2.452
06-30	0.977	0.995	0.995	0.947	0.994	0.994	0.417	0.477	0.473	2.339	2.464	2.460
07-01	0.941	0.959	0.959	0.865	0.966	0.965	0.442	0.502	0.500	2.248	2.427	2.424
07-14	0.969	0.999	1.000	0.914	0.999	0.999	0.871	0.938	0.927	2.734	2.915	2.905
07-18	0.944	0.899	0.905	0.880	0.937	0.933	0.867	0.813	0.836	2.062	2.049	2.068
07-19	0.968	0.958	0.963	0.937	0.941	0.947	0.854	0.895	0.907	0.369	0.387	0.391
07-20	0.948	0.934	0.939	0.926	0.941	0.948	0.838	0.816	0.838	0.032	0.015	0.022
07-24	0.966	0.975	0.976	0.916	0.973	0.970	0.852	0.899	0.906	2.711	2.823	2.828
07-27	0.969	1.000	1.000	0.924	0.999	1.000	0.888	0.975	0.981	2.779	2.972	2.979
07-28	0.932	0.975	0.977	0.989	0.973	0.977	0.862	0.895	0.905	0.786	0.873	0.881

日期	M₁		M₂		M₃		M₄
日期	整体相关系数	排序	整体相关系数	排序	整体相关系数	排序	整体相关系数	排序
06-04	2.850	12	2.794	13	1.539	12	4.404	11
06-05	2.817	14	2.902	8	1.586	10	7.258	7
06-08	2.868	10	2.784	14	1.783	9	5.615	10
06-10	2.797	15	2.692	16	1.833	8	3.656	12
06-15	2.968	4	2.953	1	1.545	11	7.457	4
06-16	2.976	2	2.948	2	1.453	14	1.804	14
06-27	2.977	1	2.948	3	1.510	13	7.435	5
06-30	2.967	6	2.935	5	1.367	16	7.263	6
07-01	2.859	11	2.796	12	1.444	15	7.099	8
07-14	2.968	5	2.912	7	2.736	2	8.554	2
07-18	2.748	16	2.750	15	2.516	6	6.179	9
07-19	2.889	8	2.825	10	2.656	5	1.147	15
07-20	2.821	13	2.815	11	2.492	7	0.069	16
07-24	2.917	7	2.859	9	2.657	4	8.362	3
07-27	2.969	3	2.923	6	2.844	1	8.730	1
07-28	2.884	9	2.939	4	2.662	3	2.540	13