基于双模态分解的发电站母线短期负荷预测*

doi:10.11985/2024.01.013

摘要/Abstract

摘要：

母线负荷预测是电力系统运营和规划中至关重要的一项任务，针对电力负荷数据的非线性强以及影响因素多等问题，提出了一种基于双模态分解、深度学习和注意力机制的负荷预测模型。首先，对输入数据进行经验模态分解(Empirical mode decomposition, EMD)，通过K-means聚类分析对复杂度相似的分量进行集合得到三个组合分量。其次，使用变分模态分解(Variational mode decomposition, VMD)对组合分量再次进行分解得到不同分量，使用麻雀搜索算法(Sparrow search algorithm, SSA)对变分模态分解的参数进行优化。再次，将变分模态分解得到的分量与影响因素连接并输入长短期记忆网络(Long short-term memory network, LSTM)，通过注意力机制挖掘数据内部的相关性，并使用SSA对LSTM网络的参数进行优化。最后，采用宁夏某电站一年的负荷数据进行验证，经过与不同模型的对比分析，所提模型有更高的预测精度。

关键词: 负荷预测, 经验模态分解, 麻雀搜索算法, 变分模态分解, 长短期记忆网络, 注意力机制

Abstract:

Load forecasting is a crucial task in the operation and planning of power systems. To address the challenges posed by the nonlinearity and multiple influencing factors of power load data, a load forecasting model based on bimodal decomposition, deep learning, and Attention mechanism is presented. Firstly, empirical mode decomposition(EMD) is applied to the input data, and K-means clustering is used to group similar components, resulting in three composite components. Secondly, variational mode decomposition(VMD) is employed to further decompose the composite components into distinct modes, and sparrow search algorithm(SSA) is utilized to optimize the parameters of variational mode decomposition. Subsequently, the VMD-derived components are combined with influencing factors and fed into a long short-term memory(LSTM) network. An Attention mechanism is employed to uncover internal data correlations, and SSA is used to optimize the parameters of the LSTM network. Finally, the model is validated using load data from a power station in Ningxia over the course of a year. Comparative analysis with different models demonstrates that the proposed model achieves higher forecasting accuracy.

Key words: Load forecasting, empirical mode decomposition, sparrow search algorithm, variational mode decomposition, long short-term memory network, Attention mechanism

中图分类号:

TM74

刘昕明, 吉建光, 李玮, 石光磁. 基于双模态分解的发电站母线短期负荷预测^*[J]. 电气工程学报, 2024, 19(1): 124-132.

LIU Xinming, JI Jianguang, LI Wei, SHI Guangci. Short-term Load Forecasting for Power Substations Based on Bimodal Decomposition[J]. Journal of Electrical Engineering, 2024, 19(1): 124-132.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

参考文献 24

[1]	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 Yunqin, CHENG Qize, JIANG Wenjie, et al. A photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta Energiae Solaris Sinica, 2021, 42(9):62-69.
[2]	刘鑫, 滕欢, 宫毓斌, 等. 基于改进卡尔曼滤波算法的短期负荷预测[J]. 电测与仪表, 2019, 56(3):42-46.
	LIU Xin, TENG Huan, GONG Yubin, et al. Short-term load forecasting based on the improved Kalman filter algorithm[J]. Electrical Measurement & Instrumentation, 2019, 56(3):42-46.
[3]	廖旎焕, 胡智宏, 马莹莹, 等. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制, 2011, 39(1):147-152.
	LIAO Nihuan, HU Zhihong, MA Yingying, et al. Review of short term load forecasting methods for power systems[J]. Power System Protection and Control, 2011, 39(1):147-152.
[4]	耿光飞, 郭喜庆. 模糊线性回归法在负荷预测中的应用[J]. 电网技术, 2002, 26(4):19-21.
	GENG Guangfei, QUO Xiqing. Application of fuzzy linear regression to load forecasting[J]. Power System Technology, 2002, 26(4):19-21.
[5]	吴迪, 马文莉, 杨利君. 二次指数平滑多目标组合模型电力负荷预测[J]. 计算机工程与设计, 2023, 44(8):2541-2547.
	WU Di, MA Wenli, YANG Lijun. Second order exponential smoothing multi objective combination model for power load forecasting[J]. Computer Engineering and Design, 2023, 44(8):2541-2547.
[6]	李江, 王义伟, 魏超, 等. 卡尔曼滤波理论在电力系统中的应用综述[J]. 电力系统保护与控制, 2014, 42(6):135-144.
	LI Jiang, WANG Yiwei, WEI Chao, et al. Review of the application of Kalman filter theory in power systems[J]. Power System Protection and Control, 2014, 42(6):135-144.
[7]	FUMO N, BISWAS M A R. Regression analysis for prediction of residential energy consumption[J]. Renewable and Sustainable Energy Reviews, 2015,47:332-343.
[8]	朱亚玲. 基于改进高斯过程回归的负荷预测模型研究[D]. 淄博: 山东理工大学, 2023.
	ZHU Yaling. Research on load forecasting model based on improved Gaussian process regression[D]. Zibo: Shandong University of Technology, 2023.
[9]	周思思, 李勇, 郭钇秀, 等. 考虑时序特征提取与双重注意力融合的TCN超短期负荷预测[J]. 电力系统自动化, 2023, 47(18):193-205.
	ZHOU Sisi, LI Yong, GUO Yixiu, et al. Ultra-short-term load forecasting based on temporal convolutional network considering temporal feature extraction and dual attention fusion[J]. Automation of Electric Power Systems, 2023, 47(18):193-205.
[10]	付文杰, 李化, 杨伯青, 等. 基于集合卡尔曼滤波与相空间重构的负荷预测方法研究[J]. 电力需求侧管理, 2022, 24(1):49-54.
	FU Wenjie, LI Hua, YANG Boqing, et al. Research on load forecasting method based on set Kalman filter and phase space reconstruction[J]. Power Demand Side Management, 2022, 24(1):49-54.
[11]	杜伟春, 罗宏波, 杨楠. 改进灰色预测模型在电力负荷预测中的应用[J]. 湖南电力, 2023, 43(3):88-93. doi: 10.3969/j.issn.1008-0198.2023.03.014
	DU Weichun, LUO Hongbo, YANG Nan. Application of improved grey prediction model in power load forecasting[J]. Hunan Electric Power, 2023, 43(3):88-93. doi: 10.3969/j.issn.1008-0198.2023.03.014
[12]	NOBLE W S. What is a support vector machine?[J]. Nature Biotechnology, 2006, 24(12):1565-1567. doi: 10.1038/nbt1206-1565 pmid: 17160063
[13]	SMOLA A J, SCHÖLKOPF B. A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3):199-222. doi: 10.1023/B:STCO.0000035301.49549.88
[14]	程宇也. 基于人工神经网络的短期电力负荷预测研究[D]. 杭州: 浙江大学, 2017.
	CHENG Yuye. Research on short term power load forecasting based on artificial neural networks[D]. Hangzhou: Zhejiang University, 2017.
[15]	MOHANDES M. Support vector machines for short-term electrical load forecasting[J]. International Journal of Energy Research, 2002, 26(4):335-345. doi: 10.1002/(ISSN)1099-114X
[16]	杨秀媛, 肖洋, 陈树勇. 风电场风速和发电功率预测研究[J]. 中国电机工程学报, 2005, 25(11):1-5.
	YANG Xiuyuan, XIAO Yang, CHEN Shuyong. Wind speed and generated power forecasting in wind farm[J]. Proceedings of the CSEE, 2005, 25(11):1-5.
[17]	ZOU H, YANG Q, CHEN J, et al. Short-term power load forecasting based on phase space reconstruction and EMD-ELM[J]. Journal of Electrical Engineering & Technology, 2023(5):1-11.
[18]	陈卓, 孙龙祥. 基于深度学习LSTM网络的短期电力负荷预测方法[J]. 电子技术, 2018, 47(1):39-41.
	CHEN Zhuo, SUN Longxiang. Short term power load forecasting method based on deep learning LSTM network[J]. Electronic Technology, 2018, 47(1):39-41.
[19]	杨汪洋, 魏云冰, 罗程浩. 基于CVMD-TCN-BiLSTM的短期电力负荷预测[J/OL]. 电气工程学报:1-10[2023-09-26]. http://kns.cnki.net/kcms/detail/10.1289.TM.20230601.1229.002.html
	YANG Wangyang, WEI Yunbing, LUO Chenghao. Short term power load prediction based on CVMD-TCN-BiLSTM[J/OL]. Journal of Electrical Engineering:1-10,[2023-09-26]. http://kns.cnki.net/kcms/detail/10.1289.TM.20230601.1229.002.html
[20]	穆晨宇, 薛文斌, 穆羡瑛, 等. 基于VMD-LSTM- Attention模型的短期负荷预测研究[J]. 现代电子技术, 2023, 46(17):174-178.
	MU Chenyu, XUE Wenbin, MU Xianying, et al. Research on short term load forecasting based on VMD-LSTM- Attention model[J]. Modern Electronic Technology, 2023, 46(17):174-178.
[21]	王婷. EMD算法研究及其在信号去噪中的应用[D]. 哈尔滨: 哈尔滨工程大学, 2011.
	WANG Ting. Research on EMD algorithm and its application in signal denoising[D]. Harbin:Harbin Engineering University, 2011.
[22]	刘建昌, 权贺, 于霞, 等. 基于参数优化VMD和样本熵的滚动轴承故障诊断[J]. 自动化学报, 2022, 48(3):808-819.
	LIU Jianchang, QUAN He, YU Xia, et al. Fault diagnosis of rolling bearings based on parameter optimization VMD and sample entropy[J]. Acta Automatica Sinica, 2022, 48(3):808-819.
[23]	李晓淞, 黄茜, 郭木涵, 等. 基于麻雀搜索算法优化BP神经网络的短期负荷预测[J]. 信息记录材料, 2023, 24(6):224-227.
	LI Xiaosong, HUANG Qian, GUO Muhan, et al. Short term load forecasting based on sparrow search algorithm optimized BP neural network[J]. Information Recording Materials, 2023, 24(6):224-227.
[24]	朱张莉, 饶元, 吴渊, 等. 注意力机制在深度学习中的研究进展[J]. 中文信息学报, 2019, 33(6):1-11.
	ZHU Zhangli, RAO Yuan, WU Yuan, et al. Research progress on Attention mechanisms in deep learning[J]. Journal of Chinese Information Processing, 2019, 33(6):1-11.

模型	RMSE/kW	MAE/kW	MAPE(%)	R²(%)
LSTM	463.7	377.9	6.06	88.7
EMD-LSTM	409.4	355.1	4.88	91.1
EMD-LSTM- Attention	340.3	263.2	4.35	93.9
EMD-SSA-VMD-LSTM-Attention	285.6	214.8	4.06	95.2