Short-term Load Forecasting Based on a Combined ICEEMDAN-PE and IDBO-Informer Model

doi:10.11930/j.issn.1004-9649.202410086

Abstract

Abstract:

To address the problems of insufficient noise processing, limited feature extraction ability and complex model training when using traditional methods to deal with complex load data, an innovative forecasting model based on a combined ICEEMDAN-PE and IDBO-Informer is proposed. Firstly, the raw load data were preprocessed using wavelet soft-threshold denoising algorithm to reduce noise interference. Secondly, ICEEMDAN was used for multi-scale decomposition of load data to precisely characterize load features, and the permutation entropy was used to evaluate the component complexity. Finally, an improved Dung Beetle Optimizer (IDBO) was proposed by synergistically integrating chaotic and opposition-based learning strategies for population initialization, incorporating adaptive step size, convex lens opposition imaging, and stochastic differential mutation strategies. This approach optimizes hyperparameters of the Informer forecasting model, significantly enhancing computational efficiency and prediction accuracy. The experimental results show that the model performs well in short-term load forecasting, with MAE of 81.3 MW (the original load data range is about 500 MW to 1500 MW), RMSE of 109.2 MW and R² score of 0.991, which is much better than the traditional method, and fully verifies the innovation and superiority of the model.

Key words: load forecasting, ICEEMDAN, improved dung beetle optimizer algorithm, Informer

YU Duo, CAO Yi, WANG Hairong, ZHAO Aodong, CAO Qian. Short-term Load Forecasting Based on a Combined ICEEMDAN-PE and IDBO-Informer Model[J]. Electric Power, 2025, 58(6): 19-32.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202410086

https://www.electricpower.com.cn/EN/Y2025/V58/I6/19

Figures/Tables 19

References 26

1	杨海柱, 田馥铭, 张鹏, 等. 基于CEEMD-FE和AOA-LSSVM的短期电力负荷预测[J]. 电力系统保护与控制, 2022, 50 (13): 126- 133.
	YANG Haizhu, TIAN Fuming, ZHANG Peng, et al. Short-term load forecasting based on CEEMD-FE-AOA-LSSVM[J]. Power System Protection and Control, 2022, 50 (13): 126- 133.
2	戴浩男, 张辰灏, 甄钊, 等. 基于时空特征聚类和双层动态图卷积网络建模的短期净负荷预测[J]. 高电压技术, 2024, 50 (9): 3914- 3923.
	DAI Haonan, ZHANG Chenhao, ZHEN Zhao, et al. Short-term net load forecasting based on temporal-spatial feature clustering and two-layer dynamic graph convolutional network modeling[J]. High Voltage Engineering, 2024, 50 (9): 3914- 3923.
3	孟衡, 张涛, 王金, 等. 基于多尺度时空图卷积网络与Transformer融合的多节点短期电力负荷预测方法[J]. 电网技术, 2024, 48 (10): 4297- 4311.
	MENG Heng, ZHANG Tao, WANG Jin, et al. Multi-node short-term power load forecasting method based on multi-scale spatiotemporal graph convolution network and transformer[J]. Power System Technology, 2024, 48 (10): 4297- 4311.
4	范明康, 张怡, 康健, 等. 基于模糊聚类-马尔可夫链的换电站负荷预测模型[J]. 电力建设, 2023, 44 (10): 63- 71.
	FAN Mingkang, ZHANG Yi, KANG Jian, et al. Fuzzy clustering-markov chain based load forecasting modeling for battery-swap stations[J]. Electric Power Construction, 2023, 44 (10): 63- 71.
5	YAMASAKI M, FREIRE R Z, SEMAN L O, et al. Optimized hybrid ensemble learning approaches applied to very short-term load forecasting[J]. International Journal of Electrical Power & Energy Systems, 2024, 155, 109579.
6	WEI N, YIN C, YIN L H, et al. Short-term load forecasting based on WM algorithm and transfer learning model[J]. Applied Energy, 2024, 353, 122087. DOI
7	王晨, 李又轩, 吴其琦, 等. 基于SVM-STL-LSTM的区域短期电力负荷预测研究[J]. 水电能源科学, 2024, 42 (4): 215- 218.
	WANG Chen, LI Youxuan, WU Qiqi, et al. Research on regional short-term load forecasting based on SVM-STL-LSTM[J]. Water Resources and Power, 2024, 42 (4): 215- 218.
8	王永利, 刘泽强, 董焕然, 等. 基于VMD-CSO-RF的综合能源系统短期负荷预测[J/OL]. 华北电力大学学报(自然科学版), 2024: 1–10. [2024-10-04]. http://kns.cnki.net/kcms/detail/13.1212.TM.20240314.1850.002.html.
	WANG Yongli, LIU Zeqiang, DONG Huanran, et al. Short-term load forecasting of integrated energy systems based on VMD-CSO-RF [J/OL]. Journal of North China Electric Power University(Natural science edition), 1–10[2024-10-04]. http://kns.cnki.net/kcms/detail/13.1212.TM.20240314.1850.002.html.
9	ZHANG T R, HUANG Y P, LIAO H, et al. A hybrid electric vehicle load classification and forecasting approach based on GBDT algorithm and temporal convolutional network[J]. Applied Energy, 2023, 351, 121768. DOI
10	李甲祎, 赵兵, 刘宣, 等. 基于DWT-Informer的台区短期负荷预测[J]. 电测与仪表, 2024, 61 (3): 160- 166, 191.
	LI Jiayi, ZHAO Bing, LIU Xuan, et al. Short-term substation load forecasting based on DWT-Informer model[J]. Electrical Measurement & Instrumentation, 2024, 61 (3): 160- 166, 191.
11	ABUMOHSEN M, OWDA A Y, OWDA M. Electrical load forecasting using LSTM, GRU, and RNN algorithms[J]. Energies, 2023, 16 (5): 2283. DOI
12	茹瑶, 赵永宁, 叶林, 等. 超短期LSTM风电功率预测模型的混合专家模块化代理解释方法[J]. 电力建设, 2024, 45 (11): 114- 124.
	RU Yao, ZHAO Yongning, YE Lin, et al. Modular surrogate interpretation method based on decision tree mixture of experts for ultra-short-term LSTM wind power forecasting model[J]. Electric Power Construction, 2024, 45 (11): 114- 124.
13	侯健敏, 孟莹, 李志, 等. 基于综合相关性指标与SA-BiGRU的综合能源系统多元负荷预测[J]. 电力建设, 2024, 45 (5): 118- 130.
	HOU Jianmin, MENG Ying, LI Zhi, et al. Multi-energy load forecasting in integrated energy systems based on comprehensive correlation index and SA-BiGRU network[J]. Electric Power Construction, 2024, 45 (5): 118- 130.
14	吴军英, 路欣, 刘宏, 等. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57 (6): 131- 140.
	WU Junying, LU Xin, LIU Hong, et al. Ultra-short-term multi-region power load forecasting based on spearman-GCN-GRU model[J]. Electric Power, 2024, 57 (6): 131- 140.
15	JALALIFAR R, DELAVARM R, GHADERI S F. SAC-ConvLSTM: a novel spatio-temporal deep learning-based approach for a short term power load forecasting[J]. Expert Systems with Applications, 2024, 237, 121487. DOI
16	MOUNIR N, OUADI H, JRHILIFA I. Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system[J]. Energy and Buildings, 2023, 288, 113022. DOI
17	WIDIANTO A J, ADYTIA D, ADITYA I A. Feature modelling for electricity load forecasting using hybrid EEMD-BiLSTM with spatially correlated weather data[J]. International Journal of Intelligent Engineering & Systems, 2024, 17 (6): 1193.
18	ZHENG G Q, KONG L R, SU Z E, et al. Approach for short-term power load prediction utilizing the ICEEMDAN–LSTM–TCN–bagging model[J]. Journal of Electrical Engineering & Technology, 2025, 20 (1): 231- 243.
19	杨国华, 祁鑫, 贾睿, 等. 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.
	YANG Guohua, QI Xin, JIA Rui, et al. Short-term wind power forecast based on CNN&LSTM-GRU model integrated with CEEMD-SE algorithm[J]. Electric Power, 2024, 57 (2): 55- 61.
20	SHI Y F, WANG B, YU Y W, et al. Robust anomaly detection for multivariate time series through temporal GCNs and attention-based VAE[J]. Knowledge-Based Systems, 2023, 275, 110725. DOI
21	JIAO D X, HE R T, WANG L Y, et al. Research on a short-term forecast of industry load based on PSO-LSTM[J]. Journal of Physics: Conference Series, 2024, 2814 (1): 012040. DOI
22	FAN C C, ZHENG Y X, WANG S Q, et al. Prediction of bond strength of reinforced concrete structures based on feature selection and GWO-SVR model[J]. Construction and Building Materials, 2023, 400, 132602. DOI
23	AHMED U, KHAN A R, MAHMOOD A, et al. Short-term global horizontal irradiance forecasting using weather classified categorical boosting[J]. Applied Soft Computing, 2024, 155, 111441. DOI
24	刘洋, 伍双喜, 朱誉, 等. 基于CEEMDAN和DBO-GRNN的风电功率超短期预测[J]. 电力建设, 2024, 45 (8): 97- 105.
	LIU Yang, WU Shuangxi, ZHU Yu, et al. Ultra-short-term prediction of wind power based on CEEMDAN and DBO-GRNN[J]. Electric Power Construction, 2024, 45 (8): 97- 105.
25	刘杰, 从兰美, 夏远洋, 等. 基于DBO-VMD和IWOA-BILSTM神经网络组合模型的短期电力负荷预测[J]. 电力系统保护与控制, 2024, 52 (8): 123- 133.
	LIU Jie, CONG Lanmei, XIA Yuanyang, et al. Short-term power load prediction based on DBO-VMD and an IWOA-BILSTM neural network combination model[J]. Power System Protection and Control, 2024, 52 (8): 123- 133.
26	丁立, 吴东晖, 隋佳音, 等. 基于MIV-DBO-DeepAR模型的净负荷预测研究[J/OL]. 华北电力大学学报(自然科学版), 1–14[2025-01-27]. http://kns.cnki.net/kcms/detail/13.1212.TM.20240311.1446.002.html.
	DING Li, WU Donghui, SUI Jiayin, et al. Research on net load prediction based on MIV-DBO-DeepAR model [J/OL]. Journal of North China Electric Power University (Natural Science Edition) , 1–14[2025-01-27]. http://kns.cnki.net/kcms/detail/13.1212.TM.20240311.1446.002.html.

算法		参数设置
PSO		C₁=C₂=2，w₁=0.8
SSA		D=0.3，T=0.1，R₂=0.6
GWO		f_i=2，A=0.1，w₂=0.5
DBO		K₁=0.1，S₁=0.5
IDBO		K₂=0.1，S₂=0.5

算法		参数设置
PSO		C₁=C₂=2，w₁=0.8
SSA		D=0.3，T=0.1，R₂=0.6
GWO		f_i=2，A=0.1，w₂=0.5
DBO		K₁=0.1，S₁=0.5
IDBO		K₂=0.1，S₂=0.5

测试函数	算法	BV	WV	MV	SD	测试函数	算法	BV	WV	MV	SD
f₁	PSO	5.6797×10^–90	5.3574×10^–87	6.6176×10^–88	1.2604×10^–87	f₄	PSO	1.3712×10^–91	8.4084×10^–88	1.3777×10^–88	8.4084×10^–88
	SSA	0	1.8782×10^–57	6.2805×10^–59	3.4288×10^–58		SSA	2.2061×10^–56	0	8.2669×10^–58	4.0257×10^–57
	GWO	1.7348×10^–29	5.9903×10^–27	1.0541×10^–27	1.3803×10^–27		GWO	9.3765×10^–30	1.9702×10^–27	1.6280×10^–28	3.6480×10^–28
	DBO	5.0220×10^–152	7.1639×10^–112	2.5442×10^–113	1.3078×10^–112		DBO	4.1327×10^–166	1.4584×10^–104	5.0713×10^–105	2.6613×10^–105
	IDBO	0	0	0	0		IDBO	0	0	0	0

测试函数	算法	BV	WV	MV	SD	测试函数	算法	BV	WV	MV	SD
f₅	PSO	1.5772×10^–45	9.5814×10^–47	8.0128×10^–45	1.1912×10^–45	f₁₁	PSO	9.5097×10^–183	8.4709×10^–174	8.6362×10^–175	0
	SSA	1.0629×10^–107	1.3856×10^–28	4.6849×10^–30	2.5287×10^–29		SSA	6.2132×10^–202	1.7317×10^–50	5.7724×10^–52	3.1616×10^–51
	GWO	2.3430×10^–17	2.4452×10^–16	1.0058×10^–16	6.3196×10^–17		GWO	2.6723×10^–17	5.4980×10^–85	1.8424×10^–86	1.0036×10^–85
	DBO	1.4972×10^–83	3.6254×10^–54	1.2086×10^–55	6.6191×10^–55		DBO	1.0159×10^–187	4.6142×10^–112	1.5430×10^–113	8.4235×10^–113
	IDBO	0	0	0	0		IDBO	0	0	0	0

测试函数	算法	BV	WV	MV	SD	测试函数	算法	BV	WV	MV	SD
f₁₅	PSO	0	0	0	0	f₂₀	PSO	4.4409×10^–15	7.9936×10^–15	6.0988×10^–15	1.8027×10^–15
	SSA	0	0	0	0		SSA	8.8818×10^–16	8.8818×10^–16	8.8818×10^–16	0
	GWO	5.6843×10^–14	8.2608	1.7812	2.5556		GWO	6.4838×10^–14	1.4655×10^–13	0	0
	DBO	0	9.1724	0.30575	1.6746		DBO	8.8818×10^–16	8.8818×10^–16	8.8818×10^–16	0
	IDBO	8.8818×10^–16	8.8818×10^–16	8.8818×10^–16	0		IDBO	0	0	0	0

测试函数	算法	BV	WV	MV	SD	测试函数	算法	BV	WV	MV	SD
f₁	PSO	5.6797×10^–90	5.3574×10^–87	6.6176×10^–88	1.2604×10^–87	f₄	PSO	1.3712×10^–91	8.4084×10^–88	1.3777×10^–88	8.4084×10^–88
	SSA	0	1.8782×10^–57	6.2805×10^–59	3.4288×10^–58		SSA	2.2061×10^–56	0	8.2669×10^–58	4.0257×10^–57
	GWO	1.7348×10^–29	5.9903×10^–27	1.0541×10^–27	1.3803×10^–27		GWO	9.3765×10^–30	1.9702×10^–27	1.6280×10^–28	3.6480×10^–28
	DBO	5.0220×10^–152	7.1639×10^–112	2.5442×10^–113	1.3078×10^–112		DBO	4.1327×10^–166	1.4584×10^–104	5.0713×10^–105	2.6613×10^–105
	IDBO	0	0	0	0		IDBO	0	0	0	0

测试函数	算法	BV	WV	MV	SD	测试函数	算法	BV	WV	MV	SD
f₅	PSO	1.5772×10^–45	9.5814×10^–47	8.0128×10^–45	1.1912×10^–45	f₁₁	PSO	9.5097×10^–183	8.4709×10^–174	8.6362×10^–175	0
	SSA	1.0629×10^–107	1.3856×10^–28	4.6849×10^–30	2.5287×10^–29		SSA	6.2132×10^–202	1.7317×10^–50	5.7724×10^–52	3.1616×10^–51
	GWO	2.3430×10^–17	2.4452×10^–16	1.0058×10^–16	6.3196×10^–17		GWO	2.6723×10^–17	5.4980×10^–85	1.8424×10^–86	1.0036×10^–85
	DBO	1.4972×10^–83	3.6254×10^–54	1.2086×10^–55	6.6191×10^–55		DBO	1.0159×10^–187	4.6142×10^–112	1.5430×10^–113	8.4235×10^–113
	IDBO	0	0	0	0		IDBO	0	0	0	0

测试函数	算法	BV	WV	MV	SD	测试函数	算法	BV	WV	MV	SD
f₁₅	PSO	0	0	0	0	f₂₀	PSO	4.4409×10^–15	7.9936×10^–15	6.0988×10^–15	1.8027×10^–15
	SSA	0	0	0	0		SSA	8.8818×10^–16	8.8818×10^–16	8.8818×10^–16	0
	GWO	5.6843×10^–14	8.2608	1.7812	2.5556		GWO	6.4838×10^–14	1.4655×10^–13	0	0
	DBO	0	9.1724	0.30575	1.6746		DBO	8.8818×10^–16	8.8818×10^–16	8.8818×10^–16	0
	IDBO	8.8818×10^–16	8.8818×10^–16	8.8818×10^–16	0		IDBO	0	0	0	0

数据集	模型	MAE/ MW	RMSE/ MW	R²
一区	ICEEMDAN-PE-IDBO-SVR	265.7	296.8	0.947
	ICEEMDAN-PE-IDBO-LSTM	190.5	226.3	0.965
	ICEEMDAN-PE-IDBO-GRU	140.8	169.1	0.972
	ICEEMDAN-PE-IDBO-Transformer	90.8	121.4	0.980
	ICEEMDAN-PE-IDBO-Informer	81.3	109.2	0.991
二区	ICEEMDAN-PE-IDBO-SVR	1397.6	1685.1	0.941
	ICEEMDAN-PE-IDBO-LSTM	694.7	877.2	0.962
	ICEEMDAN-PE-IDBO-GRU	557.6	706.6	0.979
	ICEEMDAN-PE-IDBO-Transformer	493.3	585.8	0.985
	ICEEMDAN-PE-IDBO-Informer	331.8	384.1	0.995