基于VMD和改进TCN的短期光伏发电功率预测

doi:10.16180/j.cnki.issn1007-7820.2023.03.007

摘要/Abstract

摘要：

光伏发电功率存在波动性,且光伏出力易受各种气象特征影响,传统TCN网络容易过度强化空间特性而弱化个体特性。针对上述问题,文中提出一种基于VMD和改进TCN的短期光伏发电功率预测模型。通过VMD将原始光伏发电功率时间序列分解为若干不同频率的模态分量,将各个模态分量以及相对应的气象数据输入至改进TCN网络进行建模学习。利用中心频率法确定VMD的最优分解模态分解个数。在传统TCN预测模型的基础上,使用DropBlock正则化取代Dropout正则化以达到抑制卷积层中信息协同的效果,并引入注意力机制自主挖掘并突出关键气象输入特征的影响,量化各气象因素对光伏发电的影响,从而提高预测精度。以江苏省某光伏电站真实数据为例进行仿真实验,结果表明所提预测方法的RMSE为0.62 MW,MAPE为2.03%。

关键词: 光伏发电功率, 变分模态分解, 时序卷积神经网络, DropBlock正则化, 注意力机制, 功率预测, 时间序列预测, 数据分解

Abstract:

Photovoltaic power generation fluctuates, photovoltaic output is easily affected by various meteorological characteristics, and traditional TCN networks tend to over-enhance spatial characteristics and weaken individual characteristics. In view of these problem, a short-term photovoltaic power generation prediction model based on VMD and improved TCN is proposed in this study. The original photovoltaic power generation time series is decomposed into several modal components of different frequencies through VMD, and each modal component and the corresponding meteorological data are input to the improved TCN network for modeling and learning. The center frequency method is used to determine the optimal decomposition modal number of VMD. On the basis of the traditional TCN prediction model, DropBlock regularization is used to replace Dropout regularization to achieve the effect of suppressing information synergy in the convolutional layer, and the attention mechanism is introduced to autonomously mine and highlight the impact of key meteorological input characteristics and quantify the impact of various meteorological factors on photovoltaic power generation to improve forecasting precision. Based on the real data of a photovoltaic power station in Jiangsu, the simulation experiments show that the RMSE of the proposed prediction method is 0.62 MW and the MAPE is 2.03%.

Key words: photovoltaic power generation, variational modal decomposition, time-series convolutional neural network, DropBlock regularization, attention mechanism, power forecast, time series forecasting, data decomposition

中图分类号:

TP183

黄圆,魏云冰,童东兵,王维高. 基于VMD和改进TCN的短期光伏发电功率预测[J]. 电子科技, 2023, 36(3): 42-49.

HUANG Yuan,WEI Yunbing,TONG Dongbing,WANG Weigao. Short-Term Photovoltaic Power Prediction Based on VMD and Improved TCN[J]. Electronic Science and Technology, 2023, 36(3): 42-49.

图/表 12

图1

图2

图3

图4

图5

图6

表1

图7

表2

图8

图9

表3

参考文献 18

[1]	张金平, 汪宁渤, 黄蓉, 等. 高渗透率光伏参与电力系统调频研究综述[J]. 电力系统保护与控制, 2019, 47(15):179-186.
	Zhang Jinping, Wang Ningbo, Huang Rong, et al. Survey on frequency regulation technology of power grid by high-penetration photovoltaic[J]. Power System Protection and Control, 2019, 47(15):179-186.
[2]	黎静华, 骆怡辰, 杨舒惠, 等. 可再生能源电力不确定性预测方法综述[J]. 高电压技术, 2021, 47(4):1144-1155.
	Li Jinghua, Luo Yichen, Yang Shuhui, et al. Review of uncertainty forecasting methods for renewable energy power[J]. High Voltage Technology, 2021, 47(4): 1144-1155.
[3]	Ghadimi N, Akbarimajd A, Shayeghi H, et al. Two stage forecast engine with feature selection technique and improved meta-heuristic algorithm for electricity load forecasting[J]. Energy, 2018, 16(1):130-142.
[4]	朱想, 居蓉蓉, 程序, 等. 组合数值天气预报与地基云图的光伏超短期功率预测模型[J]. 电力系统自动化, 2015, 39(6):4-10.
	Zhu Xiang, Ju Rongrong, Cheng Xu, et al. A very short-term prediction model for photovoltaic power based on numerical weather prediction and ground-based cloud images[J]. Automation of Electric Power Systems, 2015, 39(6):4-10.
[5]	虞海彪, 李林, 丁明, 等. 基于混沌特性分析和Volterra滤波器的光伏出力预测[J]. 电工电能新技术, 2020, 39(10): 39-46.
	Yu Haibiao, Li Lin, Ding Ming, et al. Photovoltaic output prediction based on chaotic characteristic analysis and Volterra filter[J]. Advanced Technology of Electrical Engineering and Energy, 2020, 39(10):39-46.
[6]	Jie S, Lee W J, Liu Y, et al. Forecasting power output of photovoltaic systems based on weather classification and support vector machines[J]. IEEE Transactions on Industry Applications, 2015, 48(3):1064-1069. doi: 10.1109/TIA.2012.2190816
[7]	Jiang Y M, Yang Y, Wu Q X, et al. Research on predicting the short-term output of photovoltaic (PV) based on extreme learning machine model and improved similar day[C]. Chengdu: Proceedings of the IEEE Innovative Smart Grid Technologies-Asia, 2019.
[8]	王超洋, 张蓝宇, 刘铮, 等. 基于特征挖掘的indRNN光伏发电功率预测[J]. 电力系统及其自动化学报, 2021, 33(4):17-22.
	Wang Chaoyang, Zhang Lanyu, Liu Zheng, et al. Feature mining based indRNN for photovoltaic power generation prediction[J]. Proceedings of the CSU-EPSA, 2021, 33(4):17-22.
[9]	乔颖, 孙荣富, 丁然, 等. 基于数据增强的分布式光伏电站群短期功率预测(二):网格化预测[J]. 电网技术, 2021, 45(6):2210-2218.
	Qiao Ying, Sun Furong, Ding Ran, et al. Distributed photovoltaic station cluster gridding short-term power forecasting part II: Gridding prediction[J]. Power System Technology, 2021, 45(6):2210-2218.
[10]	杨晶显, 张帅, 刘继春, 等. 基于VMD 和双重注意力机制LSTM的短期光伏功率预测[J]. 电力系统自动化, 2021, 45(3):174-182.
	Yang Jingxian, Zhang Shuai, Liu Jichun, et al. Short-term photovoltaic power prediction based on variational mode decomposition and long short-term memory with dual-stage attention mechanism[J]. Automation of Electric Power Systems, 2021, 45(3):174-182.
[11]	宋绍剑, 李博涵. 基于LSTM网络的光伏发电功率短期预测方法的研究[J]. 可再生能源, 2021, 39(5):594-602.
	Song Shaojian, Li Bohan. Short-term forecasting method of photovoltaic power based on LSTM[J]. Renewable Energy Resources, 2021, 39(5):594-602.
[12]	黄睿, 杜文娟, 王海风. 计及湍流强度的风电功率短期预测[J]. 电网技术, 2019, 43(6):1907-1913.
	Huang Rui, Du Wenjuan, Wang Haifeng. Short-term prediction of wind power considering turbulence intensity[J]. Power System Technology, 2019, 43(6):1907-1913.
[13]	Song Z, Brown L E. Multi-dimensional evaluation of temporal neural networks on solar irradiance forecasting[C]. Chengdu: Proceedings of IEEE Innovative Smart Grid Technologies-Asia, 2019.
[14]	Zhao Y J, Li C S, Fu W L, et al. A modified variational mode decomposition method based on envelope nesting and multi-criteria evaluation[J]. Journal of Sound and Vibration, 2019, 468(3):1-25.
[15]	朱永利, 贾亚飞, 王刘旺, 等. 基于改进变分模态分解和Hilbert变换的变压器局部放电信号特征提取及分类[J]. 电工技术学报, 2017(9):221-235.
	Zhu Yongli, Jia Yafei, Wang Liuwang, et al. Feature extraction and classification on partial discharge signals of power transformers based on improved variational mode decomposition and Hilbert transform[J]. Transactions of China Electrotechnical Society, 2017(9):221-235.
[16]	杨琳, 王衍学, 何水龙. 基于变分模态分解和广义Warblet变换的齿轮故障诊断[J]. 机械传动, 2018, 42(7):157-161. doi: 10.16578/j.issn.1004.2539.2018.07.031
	Yang Lin, Wang Yanxue, He Shuilong. Gear fault diagnosis based on VMD and generalized Warblet transform[J]. Journal of Mechanical Transmission, 2018, 42(7):157-161. doi: 10.16578/j.issn.1004.2539.2018.07.031
[17]	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):1343-1349.
	Pang Hao, Gao Jinfeng, Du Yaoheng. A short-term load probability density prediction based on quantile regression of time-convolutional networks[J]. Power Grid Technology, 2020, 44(4):1343-1349.
[18]	祁鑫, 王福忠, 张丽, 等. 基于SVD-LSTM的高校学生宿舍空调负荷预测[J]. 电子科技, 2020, 33(11):59-66.
	Qi Xin, Wang Fuzhong, Zhang Li, et al. Air conditioning load forecast of university students'dormitory based on SVD-LSTM[J]. Electronic Science and Technology, 2020, 33(11):59-66.

k	u₁	u₂	u₃	u₄	u₅	u₆	u₇	u₈
3	0.001 4	0.138	0.272	-	-	-	-	-
4	0.001 3	0.135	0.236	0.331	-	-	-	-
5	0.000 2	0.025	0.145	0.253	0.398	-	-	-
6	0.000 2	0.024	0.143	0.239	0.320	0.405	-	-
7	0.000 1	0.019	0.123	0.189	0.254	0.326	0.476	-
8	0.000 1	0.020	0.096	0.152	0.240	0.317	0.395	0.477

预测模型	RMSE/MW	MAPE/%
SVM	9.38	18.25
LSTM	4.29	10.32
VMD+LSTM	2.57	6.16
传统TCN	1.35	4.56
VMD+TCN	1.18	3.52
改进TCN	1.08	3.12
VMD+改进TCN	0.62	2.03