基于改进时间卷积网络的短期光伏出力概率预测方法

doi:10.19912/j.0254-0096.tynxb.2021-1033

摘要/Abstract

摘要： 为提高光伏出力的预测精度,提出基于改进时间卷积网络的短期光伏出力概率预测方法。首先,通过递归特征消除确定特征数量,采用分组整合方法进行特征选择;然后,采用变分模态分解处理光伏出力序列;最后,构建一种结合注意力机制的改进时间卷积网络预测模型,得到未来时刻不同分位数下的预测值,再利用核密度估计得到概率密度曲线。实验结果表明,提出方法具有更高的预测精度,可有效反映光伏出力的不确定性。

关键词: 光伏出力, 预测, 概率密度, 变分模态分解, 注意力机制

Abstract: In order to improve the accuracy of solarpower prediction, a short-term solarpower probability prediction method based on an improved temporal convolutional network is proposed. First, recursive feature elimination is used to determine the number of features, and the EGSG method is used for feature selection; then the variational mode decomposition（VMD） is used to decompose the power sequence. Finally, an improved time convolutional network prediction model combined with attention mechanism is constructed to obtain the predicted values at different quantiles in the future, the kernel density estimation is used to obtain the probability density curve. Experimental results show that the proposed method has higher prediction accuracy and can reflect the uncertainty of photovoltaic output moreeffectively.

Key words: photovoltaic output, prediction, probability density, VMD, attention mechanism

中图分类号:

TM715

邢晨, 张照贝. 基于改进时间卷积网络的短期光伏出力概率预测方法[J]. 太阳能学报, 2023, 44(2): 373-380.

Xing Chen, Zhang Zhaobei. SHORT-TERM PROBABILISTIC FORECASTING METHOD OF PHOTOVOLTAIC OUTPUT POWER BASED ON IMPROVED TEMPORAL CONVOLUTIONAL NETWORK[J]. Acta Energiae Solaris Sinica, 2023, 44(2): 373-380.

参考文献

[1] DAS U K, TEY K S, SEYEDMAHMOUDIAN M, et al.Forecasting of photovoltaic power generation and model optimization: a review[J]. Renewable and sustainable energy reviews, 2018, 81: 912-928.
[2] 张金金, 张倩, 马愿, 等. 模糊聚类-Elman神经网络短期光伏发电预测模型[J]. 电测与仪表, 2020, 57(12):46-51.
ZHANG J J, ZHANG Q, MA Y, et al.Fuzzy clustering-Elman neural network model for short-term photovoltaic power generation prediction[J]. Electrical measurement & instrumentation, 2020, 57(12): 46-51.
[3] ZHENG W Q, PENG X G, LU D, et al.Composite quantile regression extreme learning machine with feature selection for short-term wind speed forecasting: a new approach[J]. Energy conversion and management, 2017,151(5): 737-752.
[4] WANG K J, QI X X, LIU H D.Photovoltaic power forecasting based LSTM-convolutional network[J]. Energy, 2019, 189(4): 116225.
[5] 张爱枫, 段新宇, 何枭峰. 基于CNN和LightGBM的新型风电功率预测模型[J]. 电测与仪表, 2021, 58(11): 121-127.
ZHANG A F, DUAN X Y, HE X F.A new wind power prediction model based on CNN and LightGBM[J]. Electrical measurement & instrumentation, 2021, 58(11): 121-127.
[6] 盛四清, 金航, 刘长荣. 基于VMD-WSGRU的风电场发电功率中短期及短期预测[J]. 电网技术, 2022, 46(3): 897-904.
SHENG S Q, JIN H, LIU C R.Short-term and mid-short-term wind power forecasting based on VMD-WSGRU[J]. Power system technology, 2022, 46(3): 897-904.
[7] LIU B D,JAKUB N, TAO H, et al.Probabilistic load forecasting via quantile regression averaging on sister forecasts[J]. IEEE transactions on smart grid, 2017, 8(2): 730-737.
[8] KOENKER R W,BASSETT J G.Regression quantiles[J]. Econometrica, 1978, 46(1): 33-50.
[9] 何耀耀, 秦杨, 杨善林. 基于LASSO分位数回归的中期电力负荷概率密度预测方法[J]. 系统工程理论与实践,2019, 39(7): 1845-1854.
HE Y Y, QIN Y, YANG S L.Medium-term power load probability density forecasting method based on LASSO quantile regression[J]. Systems engineering-theory & practice, 2019, 39(7): 1845-1854.
[10] 庞昊, 高金峰, 杜耀恒. 基于时间卷积网络分位数回归的短期负荷概率密度预测方法[J]. 电网技术, 2020, 44(4): 1343-1350.
PANG H, GAO J F, DU Y H.A Short-term load probability density prediction based on quantile regression of time convolution network[J]. Power system technology, 2020, 44(4): 1343-1350.
[11] ZHU R J, LIAO W L, WANG Y S.Short-term prediction for wind power based on temporal convolutional network[J]. Energy reports, 2020, 6(4): 424-429.
[12] LIU H W,LIU L, ZHANG H J.Ensemble gene selection by grouping for microarray data classification[J]. Journal of biomedical informatics, 2010, 43(1): 81-87.
[13] 涂天成, 刘幸. 基于BiGRU-Copula的多重不确定性变量的概率区间预测方法[J]. 电网与清洁能源, 2021, 37(7): 25-33.
TU T C, LIU X.Probability interval prediction method of multiple uncertain variables based on BiGRU-Copula[J]. Power system and clean energy, 2021, 37(7): 25-33.
[14] 张慧娥, 刘大贵, 朱婷婷, 等. 基于相似日和动量法优化BP神经网络的光伏短期功率预测研究[J]. 智慧电力,2021, 49(6): 46-52.
ZHANG H E, LIU D G, ZHU T T, et al.Short-term PV power prediction based on BP neural network optimized by similar daily and momentum method[J]. Smart power, 2021, 49(6): 46-52.
[15] JEON H, OH S.Hybrid-recursive feature elimination for efficient feature selection[J]. Applied sciences, 2020, 10(9): 3211.
[16] 陈禹帆, 温蜜, 张凯, 等. 基于相似日匹配及 TCN-Attention 的短期光伏出力预测[J]. 电测与仪表, 2022, 59(10): 108-116.
CHEN Y F, WEN M, ZHANG K, et al.Short-term photovoltaic output forecasting based on similar day matching and TCN-Attention[J]. Electrical measurement and instrumentation, 2022, 59(10): 108-116.
[17] 何耀耀, 许启发, 杨善林, 等. 基于RBF神经网络分位数回归的电力负荷概率密度预测方法[J]. 中国电机工程学报, 2013, 33(1): 93-98.
HE Y Y, XU Q F, YANG S L, et al.A power load probability density forecasting method based on RBF neural network quantile regression[J]. Proceedings of the CSEE, 2013, 33(1): 93-98.
[18] ZHANG W J, QUAN H, SRINIVASAN D.An improved quantile regression neural network for probabilistic load forecasting[J]. IEEE transactions on smart grid, 2019, 10(4): 4425-4434.
[19] 杨秀, 曹泽棋, 张美霞, 等. 基于Attention-LSTM的商业建筑负荷分解研究[J]. 智慧电力, 2020, 48(9): 89-95.
YANG X, CAO Z Q, ZHANG M X, et al.Short-term public building load probability density prediction based on correlation analysis and long-and short-term memory network quantile regression[J]. Smart power, 2020,48(9): 89-95.
[20] HE H, PAN J T, LU N Y, et al.Short-term load probabilistic forecasting based on quantile regression convolutional neural network and Epanechnikov kernel density estimation[J]. Energy reports, 2020, 6: 1550-1556.