Multi-factor Power Load Forecasting Based on Improved Variational Mode Decomposition and Deep Learning

doi:10.19678/j.issn.1000-3428.0069241

Abstract

Abstract:

To address the problems of low accuracy and large noise of load data in traditional power load forecasting methods, this study proposes a multi-factor power load forecasting method based on improved Variational Modal Decomposition(VMD), Convolutional Neural Network(CNN), and deformed length short-term memory network(Mogrifier LSTM). First, the Sparrow Search Algorithm(SSA) is used to optimize the VMD and obtain the decomposition subsequence with the best effect, which effectively reduces the influence of load data noise on the prediction accuracy. Second, the influence mechanism of each factor on load prediction is analyzed, the correlation between each influencing factor and load is derived using the Pearson's correlation coefficient, and redundant features are removed, which greatly reduces the probability of model inaccuracy. Finally, a CNN is employed to extract feature vectors. The decomposed load data and feature data such as temperature and humidity are fed into the CNN-Mogrifier LSTM deep network model. The feature data are analyzed in multiple dimensions in this model to improve the short-term load prediction accuracy. The results show that the multi-factor power load prediction model proposed in this study has good adaptability and prediction effects. Compared with the suboptimal VMD-CNN-Mogrifier LSTM model, the prediction accuracy of the proposed model on two real datasets is improved by 0.5 and 2.4 percentage points, respectively, which provides a feasible solution for short-term power load forecasting.

Key words: load forecasting, Sparrow Search Algorithm(SSA), variational mode decomposition, Long Short-Term Memory(LSTM) network, correlation analysis

摘要：

针对传统电力负荷预测方法存在精度较低、负荷数据噪声大等问题, 提出一种基于改进变分模态分解(VMD)、卷积神经网络(CNN)和形变长短期记忆(Mogrifier LSTM)网络的多因素电力负荷预测方法。首先, 运用麻雀搜索算法(SSA)对变分模态分解进行优化, 得到最佳效果的分解子序列, 有效减轻负荷数据噪声对预测精度的影响; 其次, 分析各因素对负荷预测的影响机理, 利用皮尔逊相关系数推导各影响因素与负荷之间的相关性, 剔除冗余特征, 大幅降低模型失准的发生概率; 最后, 采用CNN提取特征向量, 将分解后的负荷数据及温度、湿度等特征数据输入到CNN-Mogrifier LSTM深度网络模型中, 通过CNN-Mogrifier LSTM深度网络模型对特征数据进行多维分析, 提高短期负荷预测精度。算例分析结果表明, 所提出的多因素电力负荷预测模型具有较好的适配性和预测效果, 与次优VMD-CNN-Mogrifier LSTM模型相比, 在两份所用真实数据集上的预测精度分别提升0.5和2.4百分点, 为短期电力负荷预测提供一种可行的解决思路。

关键词: 负荷预测, 麻雀搜索算法, 变分模态分解, 长短期记忆网络, 相关分析

LAI Xiaoling, HE Manman, HU Wei, ZHANG Yi, DU Puliang, LIU Rui, SONG Xiaotong, ZHENG Tingting. Multi-factor Power Load Forecasting Based on Improved Variational Mode Decomposition and Deep Learning[J]. Computer Engineering, 2025, 51(2): 375-386.

赖小玲, 贺嫚嫚, 胡伟, 张艺, 杜璞良, 刘蕊, 宋晓彤, 郑婷婷. 基于改进变分模态分解与深度学习的多因素电力负荷预测[J]. 计算机工程, 2025, 51(2): 375-386.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069241

https://www.ecice06.com/EN/Y2025/V51/I2/375

Figures/Tables 18

Fig.1 Fitness curves for four optimization algorithms

Fig.2 Overall procedure VMD

Fig.3 LSTM basic unit structure

Fig.4 Mogrifier LSTM basic unit structure

Fig.5 Combinatorial prediction model procedure of improve VMD-CNN-Mogrifier LSTM

Fig.6 Pearson correlation coefficient heat map

Fig.7 SSA optimizes the envelope entropy change curve of VMD

Fig.8 The results of VMD decomposition after optimization

Fig.9 Comparison of prediction curves of combination model comparison experiments

Fig.10 Comparison of prediction curves of comparison experiments of four models

Fig.11 Comparison of prediction curves for robustness verification experiments

References 25

1	吴铁洲, 邹智, 姜奔, 等. 基于TLBGA-GRU神经网络的短期负荷预测. 计算机工程, 2022, 48 (11): 69- 76. doi: 10.19678/j.issn.1000-3428.0063153
	WU T Z , ZOU Z , JIANG B , et al. Short-term load forecasting based on TLBGA-GRU neural network. Computer Engineering, 2022, 48 (11): 69- 76. doi: 10.19678/j.issn.1000-3428.0063153
2	HAN J Y , YAN L , LI Z Y . A task-based day-ahead load forecasting model for stochastic economic dispatch. IEEE Transactions on Power Systems, 2021, 36 (6): 5294- 5304. doi: 10.1109/TPWRS.2021.3072904
3	AKHTAR S , SHAHZAD S , ZAHEER A , et al. Short-term load forecasting models: a review of challenges, progress, and the road ahead. Energies, 2023, 16 (10): 4060. doi: 10.3390/en16104060
4	ACQUAH M A , JIN Y W , OH B C , et al. Spatiotemporal sequence-to-sequence clustering for electric load forecasting. IEEE Access, 2023, 11, 5850- 5863. doi: 10.1109/ACCESS.2023.3235724
5	YAN H F , YU X Y , LI D W , et al. Research on commercial sector electricity load model based on exponential smoothing method. Berlin, Germany: Springer, 2022.
6	LIANG Z, ZHENG C Y, ZHAO Z G, et al. Short-term load forecasting based on Kalman filter and nonlinear autoregressive neural network[C]//Proceedings of the 33rd Chinese Control and Decision Conference. Kunming, China: [s. n. ], 2021: 3747-3751.
7	BIAN H H , WANG Q , XU G Z , et al. Research on short-term load forecasting based on accumulated temperature effect and improved temporal convolutional network. Energy Reports, 2022, 8, 1482- 1491. URL
8	曹正志, 叶春明. 基于并联CNN-SE-Bi-LSTM的轴承剩余使用寿命预测. 计算机应用研究, 2021, 38 (7): 2103- 2107. doi: 10.19734/j.issn.1001-3695.2020.08.0224
	CAO Z Z , YE C M . Prediction of bearing remaining useful life based on parallel CNN-SE-Bi-LSTM. Application Research of Computers, 2021, 38 (7): 2103- 2107. doi: 10.19734/j.issn.1001-3695.2020.08.0224
9	CHEN Z X , ZHANG D L , JIANG H R , et al. Load forecasting based on LSTM neural network and applicable to loads of "Replacement of coal with electricity". Journal of Electrical Engineering & Technology, 2021, 16 (5): 2333- 2342. URL
10	HAN M C , ZHONG J W , SANG P , et al. A combined model incorporating improved SSA and LSTM algorithms for short-term load forecasting. Electronics, 2022, 11 (12): 1835. doi: 10.3390/electronics11121835
11	LIN J , MA J , ZHU J G , et al. Short-term load forecasting based on LSTM networks considering attention mechanism. International Journal of Electrical Power and Energy Systems, 2022, 137, 107818. doi: 10.1016/j.ijepes.2021.107818
12	REN C, JIA L, WANG Z L. A CNN-LSTM hybrid model based short-term power load forecasting[C]//Proceedings of Power System and Green Energy Conference. [S. 1. ]: IEEE Press, 2021: 182-186.
13	YANG Z D, LI X F, KONG X Y, et al. A method of short-term load prediction of renewable energy power system based on CNNLSTM[C]//Proceedings of the 25th International Conference on Electrical Machines and Systems. Washington D. C., USA: IEEE Press, 2022: 1-5.
14	SAEED F , PAUL A , SEO H . A hybrid channel-communication-enabled CNN-LSTM model for electricity load forecasting. Energies, 2022, 15 (6): 2263. doi: 10.3390/en15062263
15	SHEN X D , ZHAO H X , XIANG Y , et al. Short-term electric vehicles charging load forecasting based on deep learning in low-quality data environments. Electric Power Systems Research, 2022, 212, 108247. doi: 10.1016/j.epsr.2022.108247
16	ZHANG W H , WANG T . Short-term power load forecasting model design based on EMD-PSO-GRU. Scientific Programming, 2022, 22, 4755519. URL
17	ZHUANG Z Y , ZHENG X D , CHEN Z X , et al. A reliable short-term power load forecasting method based on VMD-IWOA-LSTM algorithm. IEEJ Transactions on Electrical and Electronic Engineering, 2022, 17 (8): 1121- 1132. URL
18	袁东辉, 朱愉洁, 齐咏生, 等. 一种增强型的滚动轴承故障诊断. 计算机仿真, 2022, 39 (10): 526- 532. URL
	YUAN D H , ZHU Y J , QI Y S , et al. An enhanced fault diagnosis of rolling bearing. Computer Simulation, 2022, 39 (10): 526- 532. URL
19	YANG J J , YAN K , WANG Z , et al. A novel denoising method for partial discharge signal based on improved variational mode decomposition. Energies, 2022, 15 (21): 8167. URL
20	YAN S Q , LIU W D , LI X Q , et al. Comparative study and improvement analysis of sparrow search algorithm. Wireless Communications and Mobile Computing, 2022, 22, 4882521. URL
21	YUE Y G , CAO L , LU D W , et al. Review and empirical analysis of sparrow search algorithm. Artificial Intelligence Review, 2023, 56 (10): 10867- 10919. URL
22	XUE J K , SHEN B . A novel swarm intelligence optimization approach: sparrow search algorithm. Systems Science & Control Engineering, 2020, 8 (1): 22- 34.
23	LI J X , LIU Z W , QIU M , et al. Fault diagnosis model of rolling bearing based on parameter adaptive VMD algorithm and sparrow search algorithm-Based PNN. Systems Science & Control Engineering, 2020, 8 (1): 22- 34.
24	ZHANG Z M , LIU C L , WANG R , et al. Mechanical fault diagnosis of a disconnector operating mechanism based on vibration and the motor current. Energies, 2022, 15 (14): 5194. URL
25	韩富佳, 王晓辉, 乔骥, 等. 基于人工智能技术的新型电力系统负荷预测研究综述. 中国电机工程学报, 2023, 43 (22): 8569- 8592. doi: 10.13334/j.0258-8013.pcsee.221560
	HAN F J , WANG X H , QIAO J , et al. Review on artificial intelligence based load forecasting research for the new-type power system. Proceedings of the CSEE, 2023, 43 (22): 8569- 8592. doi: 10.13334/j.0258-8013.pcsee.221560

[1]	WANG Ruying, MA Jiajun, DONG Jianqiang, LIU Wanlong, ZHANG Haitao, YIN Kai, ZHAO Bochao. Industrial Load Forecasting Method Based on MTS-BiGRU-DMHSA [J]. Computer Engineering, 2024, 50(9): 169-178.
[2]	Yue MA, Mi WEN. Spatial Load Forecasting Method Based on Multiscale LDTW and TCN [J]. Computer Engineering, 2024, 50(3): 106-113.
[3]	Bochao ZHAO, Jiajun MA, Lei CUI, Wenpeng LUAN, Jing ZHU. Anomaly Detection for Photovoltaic Based on Improved VMD-XGBoost-BiLSTM Combination Model [J]. Computer Engineering, 2024, 50(3): 306-316.
[4]	Guohui DING, Yuqi LIU, Yankai WANG, Shizhan GENG, Tianhao JIANG. Research on Low-Correlation Sequence Data Prediction Based on Flip Network [J]. Computer Engineering, 2024, 50(2): 78-90.
[5]	Cong HUANG, Yaobin ZOU, Shuifa SUN. Multi-threshold Segmentation Method with High Accuracy and Adaptability Using Circular Histogram Linearization [J]. Computer Engineering, 2024, 50(1): 259-270.
[6]	Jianrui XI, Hongmei TANG, Chunyang LIANG, Xin LIU. Point Cloud Object Reconstruction Based on Improved Implicit Function [J]. Computer Engineering, 2023, 49(7): 214-222.
[7]	ZHAO Hong, CHEN Zhiwen, GUO Lan, AN Dong. Video Content Caption Generation Based on ViT and Semantic Guidance [J]. Computer Engineering, 2023, 49(5): 247-254.
[8]	CAO Shuxin, FENG Tengteng, GE Fengpei, LIANG Chunyan. Speaker Recognition Based on Scale Correlation-Bidirectional Long Short-Term Memory Network Model [J]. Computer Engineering, 2023, 49(4): 289-296.
[9]	ZOU Guojian, LAI Ziliang, LI Ye. Traffic Speed Prediction Based on Spatio-Temporal Attention Network for Dynamic Expressway Network [J]. Computer Engineering, 2023, 49(2): 303-313.
[10]	Enxu WANG, Xiaohong WANG, Kun ZHANG, Dongwen ZHANG. Cloud Computing Load Forecasting Model Based on Dual Attention Mechanism [J]. Computer Engineering, 2023, 49(11): 40-48, 69.
[11]	LU Suihao, HAN Yong, QI Yongyang, SONG Guoxian. Method of B-spline Curve Fitting Based on Improved Sparrow Search Algorithm [J]. Computer Engineering, 2023, 49(1): 100-112.
[12]	MA Yatong, WANG Song, LIU Yingfang. Research on Human Action Recognition Method by Fusing Multimodal Data [J]. Computer Engineering, 2022, 48(9): 180-188.
[13]	ZHANG Heng, CHEN Xiaohong, LAN Yuxiang, LI Shunming. Supervised Canonical Correlation Analysis Based on Deep Learning [J]. Computer Engineering, 2022, 48(5): 222-228.
[14]	HE Xiaowei, XU Jingjie, WANG Bin, WU Hao, ZHANG Bowen. Research on Cloud Computing Resource Load Forecasting Based on GRU-LSTM Combination Model [J]. Computer Engineering, 2022, 48(5): 11-17,34.
[15]	LI Xiao, LU Xianling. ethod for Forecasting Short-Term Power Load Based on Dual-Stage Attention Mechanism and Gated Recurrent Unit Network [J]. Computer Engineering, 2022, 48(2): 291-296,305.

Please choose a citation manager

Content to export