融合多元经验模态分解和贝叶斯优化的多任务多元负荷预测方法

陈梓恺; 张勇; 宋贤芳; 陈志鹏

doi:10.19912/j.0254-0096.tynxb.2024-2138

PDF(2898 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (4) : 38-45. DOI: 10.19912/j.0254-0096.tynxb.2024-2138

融合多元经验模态分解和贝叶斯优化的多任务多元负荷预测方法

陈梓恺, 张勇, 宋贤芳, 陈志鹏

作者信息 +

MULTI-TASK MULTIVARIATE LOAD FORECASTING METHOD INTEGRATING MULTIVARIATE EMPIRICAL MODE DECOMPOSITION AND BAYESIAN OPTIMIZATION

Chen Zikai, Zhang Yong, Song Xianfang, Chen Zhipeng

Author information +

文章历史 +

摘要

提出一种融合多元经验模态分解和贝叶斯优化的多任务多元负荷预测方法（MEMD-BO-MMFM）。首先,给出一种融合多元经验模态分解和近似熵的多元负荷数据重组方法,将每种负荷的分解量重组为随机、周期和趋势3类分量;随后,给出一种基于贝叶斯优化的门控循环单元-多任务学习模型训练方法,为每类分量确定最为适合的网络超参数,并在建模过程中充分挖掘不同负荷之间的共性规律,实现多负荷预测任务的协同优化。实验结果表明,所提方法在预测精度和计算效率方面均优于传统方法。

Abstract

This paper proposes a multi-task multivariate load forecasting method integrating multivariate empirical mode decomposition and Bayesian optimization （MEMD-BO-MMFM）. Firstly, a multi load data recombination method that integrates multi empirical mode decomposition and approximate entropy is proposed, which recombines the decomposition of each load into three categories： random, periodic, and trend components; Subsequently, a Bayesian optimization-based training framework for the gated recurrent unit-multi-task learning （GRU-MTL） model is developed, aiming to identify the optimal network hyperparameters for each category of decomposed components. During the modeling process, the method fully leverages the underlying commonalities across different load types to facilitate the collaborative optimization of multiple load forecasting tasks. The experimental results show that the proposed method outperforms traditional methods in both prediction accuracy and computational efficiency.

导出引用

陈梓恺, 张勇, 宋贤芳, 陈志鹏. 融合多元经验模态分解和贝叶斯优化的多任务多元负荷预测方法[J]. 太阳能学报. 2026, 47(4): 38-45 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2138

Chen Zikai, Zhang Yong, Song Xianfang, Chen Zhipeng. MULTI-TASK MULTIVARIATE LOAD FORECASTING METHOD INTEGRATING MULTIVARIATE EMPIRICAL MODE DECOMPOSITION AND BAYESIAN OPTIMIZATION[J]. Acta Energiae Solaris Sinica. 2026, 47(4): 38-45 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2138

中图分类号： TP18

参考文献

[1] YOLCAN O O.World energy outlook and state of renewable energy: 10-year evaluation[J]. Innovation and green development, 2023, 2(4): 100070.
[2] WU J, YAN J Y, JIA H J, et al.Integrated energy systems[J]. Applied energy, 2016, 167: 155-157.
[3] 汪德成, 李妍, 张群, 等. 冷热电储一体化综合能源系统优化研究[J]. 太阳能学报, 2023, 44(6): 130-136.
WANG D C, LI Y, ZHANG Q, et al.Research on optimization of cooling, heating, electricity and storage multi-energy coupling system[J]. Acta energiae solaris sinica, 2023, 44(6): 130-136.
[4] 朱继忠, 董瀚江, 李盛林, 等. 数据驱动的综合能源系统负荷预测综述[J]. 中国电机工程学报, 2021, 41(23): 7905-7924.
ZHU J Z, DONG H J, LI S L, et al.Review of data-driven load forecasting for integrated energy system[J]. Proceedings of the CSEE, 2021, 41(23): 7905-7924.
[5] 李志颖, 王致杰, 王鸿. 考虑功率可调节裕度的区域综合能源系统多时间尺度优化调度[J]. 太阳能学报, 2025, 46(2): 255-261.
LI Z Y, WANG Z J, WANG H.Multi-time scale optimal scheduling of regional integrated energy system considering power adjustable margin[J]. Acta energiae solaris sinica, 2025, 46(2): 255-261.
[6] 孙庆凯, 王小君, 张义志, 等. 基于LSTM和多任务学习的综合能源系统多元负荷预测[J]. 电力系统自动化, 2021, 45(5): 63-70.
SUN Q K, WANG X J, ZHANG Y Z, et al.Multiple load prediction of integrated energy system based on long short-term memory and multi-task learning[J]. Automation of electric power systems, 2021, 45(5): 63-70.
[7] 薛东, 段立强, 高统彤, 等. 考虑多重特征与不确定性度量的综合能源系统负荷预测研究[J]. 太阳能学报, 2024, 45(7): 379-388.
XUE D, DUAN L Q, GAO T T, et al.Study of integrated energy system load forecasting considering multiple characteristics and uncertainty measures[J]. Acta energiae solaris sinica, 2024, 45(7): 379-388.
[8] 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.
[9] HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings: mathematical, physical and engineering sciences, 1998, 454(1971): 903-995.
[10] YANG F F, FU X Q, YANG Q, et al.Decomposition strategy and attention-based long short-term memory network for multi-step ultra-short-term agricultural power load forecasting[J]. Expert systems with applications, 2024, 238: 122226.
[11] WU Z H, HUANG N E.Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in adaptive data analysis, 2009, 1(1): 1-41.
[12] LI K, HUANG W, HU G Y, et al.Ultra-short term power load forecasting based on CEEMDAN-SE and LSTM neural network[J]. Energy and buildings, 2023, 279: 112666.
[13] 尚传福. 基于多尺度样本熵的时间序列复杂度研究[J]. 现代电子技术, 2017, 40(17): 40-43.
SHANG C F.Time series complexity research based on multiscale sample entropy[J]. Modern electronics technique, 2017, 40(17): 40-43.
[14] KARIJADI I, CHOU S Y.A hybrid RF-LSTM based on CEEMDAN for improving the accuracy of building energy consumption prediction[J]. Energy and buildings, 2022, 259: 111908.
[15] LIU H B, MA Z Q, YANG L X, et al.SADI: a self-adaptive decomposed interpretable framework for electric load forecasting under extreme events[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rhodes Island, Greece, 2023: 1-5.
[16] HASTIE T J.Generalized additive models[M]. Statistical models in S. New York: Routledge, 2017: 249-307.
[17] HUANG Y M, HASAN N, DENG C R, et al.Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting[J]. Energy, 2022, 239: 122245.
[18] LI Y R, ZHU N, HOU Y Z.A novel hybrid model for building heat load forecasting based on multivariate Empirical modal decomposition[J]. Building and environment, 2023, 237: 110317.
[19] ZHANG Y, LIU L F, YUAN F M, et al.Multifactor and multiscale method for power load forecasting[J]. Knowledge-based systems, 2023, 268: 110476.
[20] CARUANA R.Multitask learning[J]. Machine learning, 1997, 28(1): 41-75.
[21] WANG L L, TAN M, CHEN J, et al.Multi-task learning based multi-energy load prediction in integrated energy system[J]. Applied intelligence, 2023, 53(9): 10273-10289.
[22] 岳伟民, 刘青荣, 阮应君, 等. 基于MTL-GRU-Attention的综合能源系统多元负荷预测[J]. 电力系统及其自动化学报, 2023, 35(6): 83-89.
YUE W M, LIU Q R, RUAN Y J, et al.Multivariate load forecasting of integrated energy system based on MTL-GRU-Attention mechanism[J]. Proceedings of the CSU-EPSA, 2023, 35(6): 83-89.
[23] LIU C L, TSENG C J, HUANG T H, et al.A multi-task learning model for building electrical load prediction[J]. Energy and buildings, 2023, 278: 112601.
[24] 赵洋, 王瀚墨, 康丽, 等. 基于时间卷积网络的短期电力负荷预测[J]. 电工技术学报, 2022, 37(5): 1242-1251.
ZHAO Y, WANG H M, KANG L, et al.Temporal convolution network-based short-term electrical load forecasting[J]. Transactions of China Electrotechnical Society, 2022, 37(5): 1242-1251.
[25] TAN M, LIAO C C, CHEN J, et al.A multi-task learning method for multi-energy load forecasting based on synthesis correlation analysis and load participation factor[J]. Applied energy, 2023, 343: 121177.
[26] MUNEM M, RUBAITH BASHAR T M, RONI M H, et al. Electric power load forecasting based on multivariate LSTM neural network using Bayesian optimization[C]//2020 IEEE Electric Power and Energy Conference (EPEC). Edmonton, AB, Canada, 2021: 1-6.
[27] LU Y T, WANG G C.A load forecasting model based on support vector regression with whale optimization algorithm[J]. Multimedia tools and applications, 2023, 82(7): 9939-9959.
[28] 徐科, 徐金梧, 班晓娟. 基于小波分解的某些非平稳时间序列预测方法[J]. 电子学报, 2001, 29(4): 566-568.
XU K, XU J W, BAN X J.Forecasting of some non-stationary time series based on wavelet decomposition[J]. Acta electronica sinica, 2001, 29(4): 566-568.
[29] REHMAN N, MANDIC D P.Multivariate empirical mode decomposition[J]. Proceedings: mathematical, physical and engineering sciences, 466(2117): 1291-1302.
[30] ZEILER A, FALTERMEIER R, KECK I R, et al.Empirical mode decomposition-an introduction[C]//The 2010 International Joint Conference on Neural Networks (IJCNN). Barcelona, Spain, 2010: 1-8.
[31] PINCUS S M.Approximate entropy as a measure of system complexity[J]. Proceedings of the national academy of sciences of the United States of America, 1991, 88(6): 2297-2301.
[32] VERMAAK J, BOTHA E C.Recurrent neural networks for short-term load forecasting[J]. IEEE transactions on power systems, 1998, 13(1): 126-132.
[33] CHUNG J, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL].2014: arXiv: 1412.3555. https://arxiv.org/abs/1412.3555
[34] AOKI M.On some convergence questions in Bayesian optimization problems[J]. IEEE transactions on automatic control, 1965, 10(2): 180-182.
[35] 黄璜, 张安安. 基于分解算法与元学习结合的综合能源系统负荷预测[J]. 电力系统自动化, 2024, 48(10): 151-160.
HUANG H, ZHANG A A.Load forecasting of integrated energy system based on combination of decomposition algorithms and meta-learning[J]. Automation of electric power systems, 2024, 48(10): 151-160.
[36] HYNDMAN R J, KOEHLER A B.Another look at measures of forecast accuracy[J]. International journal of forecasting, 2006, 22(4): 679-688.