基于VMD-SE的电力负荷分量的多特征短期预测

doi:10.11930/j.issn.1004-9649.202303085

摘要/Abstract

摘要：

为提高电力负荷的预测精度，提出一种基于VMD-SE的电力负荷分量的多特征短期预测方法。首先采用变分模态分解（VMD）将原始负荷分解为一系列模态分量与残差，VMD的分解层数由样本熵值（sample entropy，SE）确定；然后对比原始负荷与模态分量的SE值，重构为平稳分量和波动分量，来降低运算规模；同时利用皮尔逊相关系数来筛选特征变量，删除特征冗余，建立灰狼算法优化后的支持向量回归模型（GWO-SVR）和长短期记忆神经网络（LSTM）分别对平稳分量和波动分量预测；最后以某地区2018—2020年用电负荷为例进行实验。实验证明：此模型精准度高达94.7%，平均绝对百分误差降低到2.98%，具有更好的精准性和适用性。

关键词: 短期预测, VMD, 样本熵, 波动分量, 平稳分量, GWO-SVR, 长短期记忆神经网络

Abstract:

To improve the accuracy of power load prediction, a multi-feature short-term prediction method based on VMD-SE for power load components is proposed. Firstly, the variational modal decomposition (VMD) is used to decompose the original load into a series of modal components and residuals, and the decomposition level of VMD is determined by sample entropy (SE). Then the SE values of the original load and modal components are compared, and the original load series are reconstructed into stationary and fluctuating components to reduce the computational scale. At the same time, the Pearson correlation coefficient is used to screen feature variables and delete feature redundancy, and a support vector regression model (GWO-SVR) optimized by gray wolf algorithm and a long short term memory neural network are established to predict the stationary component and fluctuation component respectively. Finally, an experiment was conducted using the electricity load of an area in Xi'an from 2018 to 2020 as an example. The experiment proves that the accuracy of this model is as high as 94.7%, and the MAPE error is reduced to 2.98%, indicating good accuracy and applicability.

Key words: short-term prediction, variational modal decomposition, sample entropy, fluctuation component, stationary component, GWO-SVR, short and long term memory neural network

邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57(4): 162-170.

Bilin SHAO, Danyang JI. Multi-feature Short-term Prediction of Power Load Components Based on VMD-SE[J]. Electric Power, 2024, 57(4): 162-170.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202303085

https://www.electricpower.com.cn/CN/Y2024/V57/I4/162

图/表 14

图 1 GWO-SVR流程

Fig.1 GWO-SVR flow chart

图 2 LSTM的框架结构

Fig.2 Frame structure of LSTM

图 3 整体预测框架

Fig.3 Overall prediction framework

图 4 电力负荷折线图

Fig.4 Power load line diagram

表 1 特征相关度

Table 1 Feature correlation

特征变量	相关度	特征变量	相关度	特征变量	相关度
最高温度	0.715	相对湿度	0.122	前一天负荷	0.950
最低温度	0.656	降雨量	0.119	前两天负荷	0.889
平均温度	0.740	工作日	0.147	前三天负荷	0.855

图 5 样本熵值

Fig.5 Sample entropy

图 6 VMD分解模态分量和残差量

Fig.6 The VMD-decomposed modal components and residual

图 7 原始负荷和各分量的样本熵值

Fig.7 Sample entropy of original load and components

图 8 平稳分量折线图

Fig.8 Line chart of stationary components

图 9 波动分量折线图

Fig.9 Line chart of fluctuation component

图 10 适应度随迭代次数的变化

Fig.10 Change of fitness with iteration number

图 11 训练集和测试集的损失

Fig.11 Training and validation loss

表 2 各模型评价指标对比

Table 2 Comparison of model evaluation indicators

预测模型	R²	E_MAPE/%	E_MAE/MW	E_RMSE/MW
SVR	0.828	5.278	446.76	593.5
GWO-SVR	0.878	4.325	372.51	501.5
PSO-SVR	0.872	4.34	375.02	512.4
ELM	0.843	5.027	433.29	568.2
LSTM	0.922	3.275	296.35	358.2
GWO-SVR+LSTM	0.947	2.98	261.6	348.8

图 12 多模型预测对比

Fig.12 Comparison of model prediction results

参考文献 30

1	JAHAN I S, SNASEL V, MISAK S. Intelligent systems for power load forecasting: a study review[J]. Energies, 2020, 13 (22): 6105. DOI
2	BEDI J, TOSHNIWAL D. Empirical mode decomposition based deep learning for electricity demand forecasting[J]. IEEE Access, 2018, 6, 49144- 49156. DOI
3	QU H R, ZHANG R N. Short-term mathematical prediction model of air quality based on CEEMD-ELM-PSO[C]//2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA). Changchun, China. IEEE, 2022: 227–232.
4	方娜, 陈浩, 邓心, 等. 基于VMD-ARIMA-DBN的短期电力负荷预测[J]. 电力系统及其自动化学报, 2023, 35 (6): 59- 65.
	FANG Na, CHEN Hao, DENG Xin, et al. Short-term power load forecasting based on VMD-ARIMA-DBN[J]. Proceedings of the CSU-EPSA, 2023, 35 (6): 59- 65.
5	邓带雨, 李坚, 张真源, 等. 基于EEMD-GRU-MLR的短期电力负荷预测[J]. 电网技术, 2020, 44 (2): 593- 602.
	DENG Daiyu, LI Jian, ZHANG Zhenyuan, et al. Short-term electric load forecasting based on EEMD-GRU-MLR[J]. Power System Technology, 2020, 44 (2): 593- 602.
6	段明明, 杨捷, 李沛霖. 基于小波和径向基函数神经网络的电力负荷预测研究[J]. 云南大学学报(自然科学版), 2020, 42 (S2): 18- 25. DOI
	DUAN Mingming, YANG Jie, LI Peilin. The research on power load forecasting based on wavelet and radical basis function neural network[J]. Journal of Yunnan University, 2020, 42 (S2): 18- 25. DOI
7	WEI N, LI C J, PENG X L, et al. Daily natural gas consumption forecasting via the application of a novel hybrid model[J]. Applied Energy, 2019, 250, 358- 368.
8	杨胡萍, 余阳, 汪超, 等. 基于VMD-CNN-BIGRU的电力系统短期负荷预测[J]. 中国电力, 2022, 55 (10): 71- 76. DOI
	YANG Huping, YU Yang, WANG Chao, et al. Short-term load forecasting of power system based on VMD-CNN-BIGRU[J]. Applied Energy, 2022, 55 (10): 71- 76. DOI
9	石安平, 周吕, 王成, 等. 结合EMD与小波阈值去噪的GB[J]. 测绘通报, 2022, (增刊2): 227- 232, 240.
10	刁涵彬, 李培强, 郭思源, 等. PMU小扰动信号下的综合负荷模型参数辨识方法[J]. 电力系统保护与控制, 2023, 51 (13): 37- 49. DOI
	DIAO Hanbin, LI Peiqiang, GUO Siyuan, et al. Parameter identification method of composite load model using small disturbance signal of PMU[J]. Power System Protection and Control, 2023, 51 (13): 37- 49. DOI
11	陆磊, 张铭飞, 朱浩钰. 基于VMD-IPSO-LSSVM的短期电力负荷预测研究[J]. 电工技术, 2022, (24): 175- 178, 197.
	LU Lei, ZHANG Mingfei, ZHU Haoyu. Research on short-term power load forecasting based on VMD-IPSO-LSSVM[J]. Electric Engineering, 2022, (24): 175- 178, 197.
12	李雪冬, 黄莹, 胡勇, 等. 基于PAU-LSSVM模型融合多特征变量的电力负荷预测[J]. 电子器件, 2021, 44 (2): 474- 479. DOI
	LI Xuedong, HUANG Ying, HU Yong, et al. Multiple-feature power load forecasting based on PAU-LSSVM model[J]. Chinese Journal of Electron Devices, 2021, 44 (2): 474- 479. DOI
13	HAFEEZ G, KHAN I, JAN S, et al. A novel hybrid load forecasting framework with intelligent feature engineering and optimization algorithm in smart grid[J]. Applied Energy, 2021, 299, 117178. DOI
14	张栋栋, 陈洁, 李洋. 基于VMD-SE和BiLSTM在短期负荷预测应用[J]. 现代电子技术, 2021, 44 (23): 155- 159.
	ZHANG Dongdong, CHEN Jie, LI Yang. Application of VMD-SE and BiLSTM in short-term load forecasting[J]. Modern Electronics Technique, 2021, 44 (23): 155- 159.
15	黄志祥, 周莉. 基于VMD-LSTM的短期电力负荷预测研究[J]. 洛阳理工学院学报(自然科学版), 2022, 32 (3): 76- 80, 96.
	HUANG Zhixiang, ZHOU Li. Research on short term load forecasting based on VMD-LSTM[J]. Journal of Luoyang Institute of Science and Technology (Natural Science Edition), 2022, 32 (3): 76- 80, 96.
16	VEERAMSETTY V, REDDY K R, SANTHOSH M, et al. Short-term electric power load forecasting using random forest and gated recurrent unit[J]. Electrical Engineering, 2022, 104 (1): 307- 329. DOI
17	张腾达, 李琦, 陈波. 基于LSTM的热力站短期热负荷预测研究[J]. 计算机仿真, 2022, 39 (9): 507- 512.
	ZHANG Tengda, LI Qi, CHEN Bo. Research on short-term heat load forecasting of thermal power station based on LSTM[J]. Computer Simulation, 2022, 39 (9): 507- 512.
18	SAJJAD M, AHMAD KHAN Z, ULLAH A, et al. A novel CNN-GRU-based hybrid approach for short-term residential load forecasting[J]. IEEE Access, 2020, 8, 143759- 143768. DOI
19	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 shortterm memory with dual-stage attention mechanism[J]. Automation of Electric Power Systems, 2021, 45 (3): 174- 182.
20	徐晋宏, 魏秀业, 贺妍, 等. 基于CEEMDAN样本熵与PNN的行星齿轮故障诊断[J]. 机床与液压, 2021, 49 (20): 179- 183.
	XU Jinhong, WEI Xiuye, HE Yan, et al. Fault diagnosis of planetary gear based on CEEMDAN sample entropy and PNN[J]. Machine Tool & Hydraulics, 2021, 49 (20): 179- 183.
21	TANG R N, LI X W, LI C, et al. Prediction of rubber leaf nitrogen content based on fractional-order GWO-SVR[C]//Proceedings of the 20th International Conference on Near Infrared Spectroscopy, August 9th 2022, Springer, Singapore, 2022: 303–315.
22	董彦军, 王晓甜, 马红明, 等. 基于随机森林与长短期记忆网络的电力负荷预测方法[J]. 全球能源互联网, 2022, 5 (2): 147- 156.
	DONG Yanjun, WANG Xiaotian, MA Hongming, et al. Power load forecasting method based on random forest and long short-term memory[J]. Journal of Global Energy Interconnection, 2022, 5 (2): 147- 156.
23	ZHANG Y G, PAN G F. A hybrid prediction model for forecasting wind energy resources[J]. Environmental Science and Pollution Research, 2020, 27 (16): 19428- 19446. DOI
24	黄睿, 朱玲俐, 高峰, 等. 基于变分模态分解的卷积长短时记忆网络短期电力负荷预测方法[J/OL]. 现代电力: 1–10[2023-12-11]. https://doi.org/10.19725/j.cnki.1007-2322.2022.0210.
	HUANG Rui, ZHU Lingli, GAO Feng, et al. A convolutional long short term memory network short term power load prediction method based on variational mode decomposition [J/OL]. Modern Electric Power, 1–10 [2023-12-11]. https://doi.org/10.19725/j.cnki.1007-2322.2022.0210.
25	姚浩然, 李成鑫, 郑秀娟, 等. 集成自适应啁啾模态分解和Bi LSTM的短期负荷组合预测模型[J]. 电力系统保护与控制, 2022, 50 (19): 58- 66.
	YAO Haoran, LI Chengxin, ZHENG Xiujuan, et al. Short-term load combination forecasting model integrating ACMD and BiLSTM[J]. Power System Protection and Control, 2022, 50 (19): 58- 66.
26	杨信强, 李振华, 钟悦, 等. 基于变分模态分解和CNN-GRU-ED的超短期互感器误差预测[J]. 电力系统保护与控制, 2023, 51 (12): 68- 77. DOI
	YANG Xinqiang, LI Zhenhua, ZHONG Yue, et al. Ultra-short term transformer error forecast based on variational mode decomposition and CNN-GRU-ED[J]. Power System Protection and Control, 2023, 51 (12): 68- 77. DOI
27	林希程. 基于组合预测模型电力负荷优化算法研究[J]. 电子技术与软件工程, 2023, (5): 110- 113.
28	XIAN H F, CHE J X. Multi-space collaboration framework based optimal model selection for power load forecasting[J]. Applied Energy, 2022, 314, 118937. DOI
29	AHMAD N, GHADI Y, ADNAN M, et al. Load forecasting techniques for power system: research challenges and survey[J]. IEEE Access, 1054, 10, 71054- 71090.
30	CUI C, HE M, DI F C, et al. Research on power load forecasting method based on LSTM model[C]//2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). Chongqing, China. IEEE, 2020: 1657–1660.

[1]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[2]	徐峰亮, 王克谦, 王文豪, 王鹏, 王文烨, 张帅, 赵凤展. 计及激励型需求响应的低压配电网混合储能优化配置[J]. 中国电力, 2024, 57(6): 90-101.
[3]	杨国华, 祁鑫, 贾睿, 刘一峰, 蒙飞, 马鑫, 邢潇文. 基于CEEMD-SE的CNN&LSTM-GRU短期风电功率预测[J]. 中国电力, 2024, 57(2): 55-61.
[4]	武鑫, 胡超, 王祺, 熊星宇, 胡亮, 钱相臣. 基于VMD的SOFC电堆密封失效泄漏故障诊断[J]. 中国电力, 2024, 57(12): 139-147.
[5]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[6]	郭洪武, 车建峰, 闫钇汛, 王丽婕. 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.
[7]	赵隆, 温冠儒, 刘志成, 袁鹏, 董新胜. 基于参数优化的VMD-SVD和LSTM的输电杆塔倾斜状态识别[J]. 中国电力, 2023, 56(12): 217-226, 237.
[8]	李丰君, 王磊, 赵健, 张建宾, 张世尧, 田杨阳. 基于天气融合和LSTM网络的分布式光伏短期功率预测方法[J]. 中国电力, 2022, 55(11): 149-154.
[9]	阮莹, 叶行汶, 邓明锋, 王星, 杨林禹, 舒勤. 基于自适应VMD和A-SVD的MOA在线监测方法[J]. 中国电力, 2021, 54(10): 177-185.
[10]	索春梅, 孙健, 张宗峰, 王贤宗. 基于灰色关联理论与经验模态分解的光伏出力超短期预测[J]. 中国电力, 2017, 50(12): 159-164.
[11]	马小敏, 高剑, 吴驰, 何锐, 龚奕宇, 李熠, 吴天宝. 基于灰色支持向量机的输电线路覆冰厚度预测模型[J]. 中国电力, 2016, 49(11): 46-50.
[12]	张娜，王守相，王亚旻. 基于掩模经验模态分解的风速组合预测模型[J]. 中国电力, 2014, 47(5): 129-135.
[13]	李元诚, 杨瑞仙. 用于短期风速预测的优化核心向量回归模型[J]. 中国电力, 2012, 45(3): 68-71.