针对传统分解预测方法忽略太阳辐照度等多维气象因素与光伏功率在时域和频域上的耦合关系以及深度神经网络在训练中出现的特征学习效率低、训练速度慢、过拟合等问题,提出基于多元变分模态分解（MVMD）和混合深度神经网络的短期光伏功率预测方法。首先,采用MVMD对光伏功率及多维气象序列进行时频同步分析,将其分解为频率对齐的多元本征模态函数,从而降低序列中非线性和波动性的影响。其次,针对多元本征模态函数,分别建立基于混合深度神经网络的预测模型。该模型采用卷积神经网络和双向长短时记忆神经网络来分别提取光伏功率及气象序列的空间相关特征和时间相关特征,并采用注意力机制来增强对重要时间点特征的学习权重。此外,使用残差连接来加快网络的训练速度以及缓解过拟合问题。通过实际工程实验分析,验证了该文方法的优越性。
Abstract
In view of the traditional decomposition forecasting method neglecting the coupling relationship between multi-dimensional meteorological factors such as solar irradiance and photovoltaic power in time and frequency domains, as well as the low feature learning efficiency, slow training speed, over fitting and other problems in the training of depth neural network, a short-term photovoltaic power forecasting method based on multivariate variational mode decomposition （MVMD） and hybrid depth neural network is proposed. Firstly, MVMD is used to analyze the time-frequency synchronization of the photovoltaic power sequence and the multi-dimensional meteorological sequence, and decompose them into frequency-aligned multivariate intrinsic mode functions, thereby reducing the influence of nonlinearity and volatility in the sequence. Secondly, for the multivariate intrinsic mode functions, a forecasting model based on a hybrid deep neural network is established respectively. The model uses convolutional neural network and bidirectional long short-term memory neural network to extract the spatial correlation characteristics and temporal correlation characteristics of photovoltaic power and meteorological sequence, respectively, and uses attention mechanism to enhance the learning weight of important time point features. In addition, the residual connection is used to speed up the training speed of the network and alleviate the overfitting problem. The superiority of the proposed method in this paper is verified by the actual engineering experiment analysis.
关键词
光伏 /
预测 /
神经网络 /
多元变分模态分解 /
注意力机制 /
残差连接
Key words
photovoltaic /
forecasting /
neural network /
multivariate variational mode decomposition /
attention mechanism /
residual connection
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 隋欣, 魏毅, 罗小林, 等. 面向“双碳”目标的脆弱区域生态光伏模式研究[J]. 太阳能学报, 2022, 43(7): 56-63.
SUI X, WEI Y, LUO X L, et al.Emergence of a new pattern of ecological solar photovoltaics(eco-PV)in ecologically fragile areas driven by carbon peak and neutrality targets in China[J]. Acta energiae solaris sinica, 2022, 43(7): 56-63.
[2] TAWN R, BROWELL J.A review of very short-term wind and solar power forecasting[J]. Renewable and sustainable energy reviews, 2022, 153: 111758.
[3] 程礼临, 臧海祥, 卫志农, 等. 考虑多光谱卫星遥感的区域级超短期光伏功率预测[J]. 中国电机工程学报, 2022, 42(20): 7451-7465.
CHENG L L, ZANG H X, WEI Z N, et al.Ultra-short-term forecasting of regional photovoltaic power generation considering multispectral satellite remote sensing data[J]. Proceedings of the CSEE, 2022, 42(20): 7451-7465.
[4] ZHOU Y L, WANG J Z, LI Z W, et al.Short-term photovoltaic power forecasting based on signal decomposition and machine learning optimization[J]. Energy conversion and management, 2022, 267: 115944.
[5] LI Q, ZHANG X Y, MA T J, et al.A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine[J]. Energy, 2021, 224: 120094.
[6] 王振浩, 王翀, 成龙, 等. 基于集合经验模态分解和深度学习的光伏功率组合预测[J]. 高电压技术, 2022, 48(10): 4133-4142.
WANG Z H, WANG C, CHENG L, et al.Photovoltaic power combined prediction based on ensemble empirical mode decomposition and deep learning[J]. High voltage engineering, 2022, 48(10): 4133-4142.
[7] LI J, ZHANG S Q, YANG Z N.A wind power forecasting method based on optimized decomposition prediction and error correction[J]. Electric power systems research, 2022, 208: 107886.
[8] 孙永辉, 范磊, 卫志农, 等. 基于小波分析和集成学习的光伏输出功率短期预测[J]. 电力系统及其自动化学报, 2016, 28(4): 6-11, 30.
SUN Y H, FAN L, WEI Z N, et al.Short-term forecasting of the PV output power based on wavelet analysis and ensemble learning[J]. Proceedings of the CSU-EPSA, 2016, 28(4): 6-11, 30.
[9] ABEDINIA O, LOTFI M, BAGHERI M, et al.Improved EMD-based complex prediction model for wind power forecasting[J]. IEEE transactions on sustainable energy, 2020, 11(4): 2790-2802.
[10] 张淑清, 李君, 姜安琦, 等. 基于FPA-VMD和BiLSTM神经网络的新型两阶段短期电力负荷预测[J]. 电网技术, 2022, 46(8): 3269-3279.
ZHANG S Q, LI J, JIANG A Q, et al.A novel two-stage model based on FPA-VMD and BiLSTM neural network for short-term power load forecasting[J]. Power system technology, 2022, 46(8): 3269-3279.
[11] 张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69.
ZHANG Y Q, CHENG Q Z, JIANG W J, et al.Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta energiae solaris sinica, 2021, 42(9): 62-69.
[12] 袁建华, 谢斌斌, 何宝林, 等. 基于DTW-VMD-PSO-BP的光伏发电功率短期预测方法[J]. 太阳能学报, 2022, 43(8): 58-66.
YUAN J H, XIE B B, HE B L, et al.Short term forecasting method of photovoltaic output based on DTW-VMD-PSO-BP[J]. Acta energiae solaris sinica, 2022, 43(8): 58-66.
[13] HINTON G E, OSINDERO S, TEH Y W.A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7): 1527-1554.
[14] ZHANG S, CHEN Y, XIAO J H, et al.Hybrid wind speed forecasting model based on multivariate data secondary decomposition approach and deep learning algorithm with attention mechanism[J]. Renewable energy, 2021, 174: 688-704.
[15] 毕贵红, 赵鑫, 陈臣鹏, 等. 基于多通道输入和PCNN-BiLSTM的光伏发电功率超短期预测[J]. 电网技术, 2022, 46(9): 3463-3476.
BI G H, ZHAO X, CHEN C P, et al.Ultra-short-term prediction of photovoltaic power generation based on multi-channel input and PCNN-BiLSTM[J]. Power system technology, 2022, 46(9): 3463-3476.
[16] 王福忠, 王帅峰, 张丽. 基于VMD-LSTM与误差补偿的光伏发电超短期功率预测[J]. 太阳能学报, 2022, 43(8): 96-103.
WANG F Z, WANG S F, ZHANG L.Ultra short term power prediction of photovoltaic power generation based on vmd-lstm and error compensation[J]. Acta energiae solaris sinica, 2022, 43(8): 96-103.
[17] LV L L, WU Z Y, ZHANG J H, et al.A VMD and LSTM based hybrid model of load forecasting for power grid security[J]. IEEE transactions on industrial informatics, 2022, 18(9): 6474-6482.
[18] EKISTICA, DESERT Knowledge Australia. Desert Knowledge Australia Solar Center [DB/CD]. https://dkasolarcentre.com.au/download?location=alice-springs, 2022-12-15.
[19] REHMAN N U, AFTAB H.Multivariate variational mode decomposition[J]. IEEE transactions on signal processing, 2019, 67(23): 6039-6052.
[20] NIU Z Y, ZHONG G Q, YU H.A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48-62.
[21] LI X Y, LI J L, ZHAO C Y, et al.Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1D separable convolution with residual connection[J]. Mechanical systems and signal processing, 2020, 142: 106740.
基金
河北省重大科技成果转化专项（22284504Z）
PDF(3009 KB)
