许世欣,李雯婷,彭道刚,税纪钧,刘杰,钟华平
XU Shixin,LI Wenting,PENG Daogang,SHUI Jijun,LIU Jie,ZHONG Huaping

• 1:上海电力大学自动化工程学院
• 2:国网上海市电力公司金山供电公司

摘要(Abstract)：

针对单一深度学习模型特征提取不全面、非线性数据处理能力不足等传统方法存在的问题，提出一种基于二次模态分解与Informer-BiLSTM的电力负荷预测模型。首先利用CEEMDAN（自适应噪声完备经验模态分解）联合小波阈值对原始数据去噪，再通过VMD（变分模态分解）将原始数据分解为一组平稳性强的模态分量，然后利用Informer和BiLSTM并行网络分别捕捉负荷数据集的长期趋势与短期波动，最后融合两者输出实现更为精准的预测。采用两组特性不同的负荷数据集在不同情境下验证所提模型性能，结果表明该模型有效提升了负荷预测精度与泛化能力，可为电力系统优化调度提供可靠的数据支持。
To address the limitations of traditional methods—such as inadequate feature extraction and insufficient nonlinear processing capability in single deep learning models—this paper proposes a novel power load forecasting model integrating secondary modal decomposition(SMD) with Informer-BiLSTM. First, complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN) combined with wavelet thresholding is applied to denoise the raw data. Next, variational mode decomposition(VMD) decomposes the raw data into a set of highly stable modal components. These components are then processed through a parallel network architecture comprising Informer and BiLSTM to capture long-term trends and short-term fluctuations in the load data set, respectively. Finally, the outputs of both networks are fused to achieve more accurate forecasting. The proposed model is validated under multiple scenarios using two distinct load datasets. Results demonstrate that the model significantly improves forecasting accuracy and generalization capability, providing reliable data support for optimized power system scheduling.

关键词(KeyWords)： 电力负荷预测;二次模态分解;自适应噪声完备经验模态分解;变分模态分解;Informer;BiLSTM
power load forecasting;SMD;CEEMDAN;VMD;Informer;BiLSTM

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（62373241）;; 国网上海市电力公司科技项目（520932250002）

作者(Author): 许世欣,李雯婷,彭道刚,税纪钧,刘杰,钟华平
XU Shixin,LI Wenting,PENG Daogang,SHUI Jijun,LIU Jie,ZHONG Huaping

DOI: 10.19585/j.zjdl.202510005

参考文献(References)：

• [1]谭显东，刘俊，徐志成，等.“双碳”目标下“十四五”电力供需形势[J].中国电力，2021,54(5):1-6.TAN Xiandong,LIU Jun,XU Zhicheng,et al.Power supply and demand balance during the 14th Five-Year Plan period under the goal of carbon emission peak and carbon neutrality[J].Electric Power,2021,54(5):1-6.
• [2]黄雨薇，彭道刚，姚峻，等.基于SSA和K均值的TD-BP神经网络超短期光伏功率预测[J].太阳能学报，2021,42(4):229-238.HUANG Yuwei,PENG Daogang,YAO Jun,et al.Ultrashort-term photovoltaic power forecast of td-bp neural network based on ssa and k-means[J].Acta Energiae Solaris Sinica,2021,42(4):229-238.
• [3]张未，余成波，王士彬，等.基于VMD-LSTM-LightGBM的多特征短期电力负荷预测[J].南方电网技术，2023,17(2):74-81.ZHANG Wei,YU Chengbo,WANG Shibin,et al.Multifeatured short-term power load forecasting based on VMD-LSTM-LightGBM[J]. Southern Power System Technology,2023,17(2):74-81.
• [4]马传杰，孙宇贞，彭道刚，等.基于XGBoost-MTL的综合能源系统多元负荷预测[J].电力工程技术，2023,42(5):158-166.MA Chuanjie,SUN Yuzhen,PENG Daogang,et al.Multivariate load forecasting for integrated energy system based on XGBoost-MTL[J].Electric Power Engineering Technology,2023,42(5):158-166.
• [5]程明，翟金星，马骏，等.基于迁移学习的CNN-GRU短期电力负荷预测方法[J].武汉大学学报（工学版），2024,57(6):812-820.CHENG Ming,ZHAI Jinxing,MA Jun,et al. Transfer learning based CNN-GRU short-term power load forecasting method[J].Engineering Journal of Wuhan University,2024,57(6):812-820.
• [6]杨丽徙，张永锋，许向伟，等.半参数回归分析法在电力负荷预测中的应用[J].郑州大学学报（工学版），2010,31(3):29-32.YANG Lixi,ZHANG Yongfeng,XU Hongwei,et al.Application of semi-parametric regression analysis method in electric power load forecasting[J]. Journal of Zhengzhou University(Engineering Science),2010,31(3):29-32.
• [7]侯慧，王晴，赵波，等.关键信息缺失下基于相空间重构及机器学习的电力负荷预测[J].电力系统保护与控制，2022,50(4):75-82.HOU Hui,WANG Qing,ZHAO Bo,et al. Power load forecasting without key information based on phase space reconstruction and machine learning[J]. Power System Protection and Control,2022,50(4):75-82.
• [8]叶远胜，张静.基于时间序列的SVM短时电力负荷预测[J].现代信息科技，2020,4(24):17-19.YE Yuansheng,ZHANG Jing. SVM short term power load forecasting based on time series[J].Modern Information Technology,2020,4(24):17-19.
• [9]姚博骞.基于SSA优化CNN-GRU的短期电力负荷预测[D].西安：西安理工大学，2024.YAO Bojian. Optimization of CNN-GRU short-term power load forecasting based on SSA[D]. Xi’an:Xi’an University of Technology,2024.
• [10]吴梦凯.新常态下中长期电力负荷分析与预测方法研究[D].北京：华北电力大学，2018.WU Mengkai.Research on medium and long-term power load analysis and forecasting methods under the new normal[D].Beijing:North China Electric Power University,2018.
• [11] HE C B,JIA Z H,HU J,et al.CDTDNet:a neural network for capturing deep temporal dependencies in time series[J].Information Sciences,2025,706:121995.
• [12] ZHUANG W,XI Q Y,LU C X,et al.A novel trend and periodic characteristics enhanced decoupling framework for multi-energy load prediction of regional integrated energy systems[J].Electric Power Systems Research,2024,237:111028.
• [13] CUI J P,KUANG W,GENG K,et al. Advanced shortterm load forecasting with XGBoost-RF feature selection and CNN-GRU[J].Processes,2024,12(11):2466.
• [14]钱仲文，陈浩，纪德良.一种基于XGBoost算法的月度负荷预测方法[J].浙江电力，2019,38(5):77-82.QIAN Zhongwen,CHEN Hao,JI Deliang.A monthly load forecasting method based on XGBoost algorithm[J].Zhejiang Electric Power,2019,38(5):77-82.
• [15]范玲.基于萤火虫算法的光伏配电网负荷过载预测研究[J].电子设计工程，2023,31(23):95-99.FAN Ling.Research on load overload prediction of photovoltaic distribution network based on firefly algorithm[J].Electronic Design Engineering,2023,31(23):95-99.
• [16]刘瑾，赵晶，冯瑛敏，等.基于梯度提升决策树的电力物联网用电负荷预测[J].智慧电力，2022,50(8):46-53.LIU Jin,ZHAO Jing,FENG Yingmin,et al.Power load forecasting in power Internet of Things based on gradient boosting decision tree[J].Smart Power,2022,50(8):46-53.
• [17]黄晓燕，郭洒洒，陈成优，等.考虑时空关联及气象耦合的区域分布式光伏功率预测[J].浙江电力，2025,44(3):79-89.HUANG Xiaoyan,GUO Sasa,CHEN Chengyou,et al.Regional distributed photovoltaic power forecasting considering spatiotemporal correlation and meteorological coupling[J].Zhejiang Electric Power,2025,44(3):79-89.
• [18] HU J X,DUAN P F,CAO X D,et al. A multi-energy load forecasting method based on the Mixture-of-Experts model and dynamic multilevel attention mechanism[J].Energy,2025,324:135947.
• [19]温静.基于RNN的电力负荷波动分析及预测研究[J].电气开关，2024,62(5):13-15.WEN Jing.Analysis and prediction of power load fluctuation based on RNN[J].Electric Switchgear,2024,62(5):13-15.
• [20]张淑娴，江文韬，陈玉花，等.基于二次模态分解的LSTM短期电力负荷预测[J].科学技术与工程，2024,24(7):2759-2766.ZHANG Shuxian,JIANG Wentao,CHEN Yuhua,et al.Short-term power load forecasting based on quadratic mode decomposition through LSTM[J].Science Technology and Engineering,2024,24(7):2759-2766.
• [21]葛亚明，仇晨光，谢丽荣，等.基于K-means聚类与LSTM模型的多能源耦合电力负荷预测[J].现代电力，2025,42(2):369-376.GE Yaming,QIU Chenguang,XIE Lirong,et al.Research on multi-energy coupled power load prediction based on Kmeans clustering and LSTM model[J]. Modern Electric Power,2025,42(2):369-376.
• [22] WANG N E,LI Z M.Short term power load forecasting based on BES-VMD and CNN-Bi-LSTM method with error correction[J].Frontiers in Energy Research,2023,10:1076529.
• [23]周磊，竺筱晶.基于MA-CNN-LSTM和自注意力机制的单变量短期电力负荷预测[J].科学技术与工程，2024,24(22):9408-9416.ZHOU Lei,ZHU Xiaojing.Univariate short-term electrical load based on MA-CNN-LSTM-self attention[J].Science Technology and Engineering,2024,24(22):9408-9416.
• [24]杨坚，赵洁，汤义勤，等.基于序列分解的母线负荷降噪预测方法[J].浙江电力，2023,42(12):81-87.YANG Jian,ZHAO Jie,TANG Yiqin,et al.A noise reduction forecasting method of bus load based on sequence decomposition[J].Zhejiang Electric Power,2023,42(12):81-87.
• [25]唐竹，肖宇航，郭淳，等.基于CEEMDAN模态分解和TCN-BiGRU的短期电力负荷预测[J].智慧电力，2024,52(12):59-64.TANG Zhu,XIAO Yuhang,GUO Chun,et al.Short-term electricity load forecasting based on CEEMDAN decomposition and TCN-BIGRU model[J].Smart Power,2024,52(12):59-64.
• [26]李志军，徐博，张家安，等.基于TD3可变长度时间窗口最优加权的短期负荷预测策略[J].电力建设，2024,45(6):140-148.LI Zhijun,XU Bo,ZHANG Jiaan,et al. Short-term load optimal weighted forecasting strategy based on TD3 variable length time window[J].Electric Power Construction,2024,45(6):140-148.
• [27]庄立生.融合气象特征的BP神经网络电力系统短期负荷预测[J].山东电力技术，2023,50(11):51-59.ZHUANG Lisheng.Short-term load forecasting for power systems based on BP neural networks[J].Shandong Electric Power,2023,50(11):51-59.
• [28]寿绍安，罗海荣，王晓康，等.基于VMD-ISODATADBN的配电台区短期负荷预测方法[J].智慧电力，2023,51(11):53-60.SHOU Shaoan,LUO Hairong,WANG Xiaokang,et al.Forecasting method of short-term load in distribution station area based on VMD-ISODATA-DBN[J]. Smart Power,2023,51(11):53-60.
• [29]袁郁，杨超，郑伟铭，等.基于Bi-SRNN的联邦学习区域电力短期负荷预测模型[J].电网与清洁能源，2023,39(10):45-55.YUAN Yu,YANG Chao,ZHENG Weiming,et al. The federated learning power short term load forecasting model based on Bi-SRNN[J]. Power System and Clean Energy,2023,39(10):45-55.
• [30]朱海南，李丰硕，孙华忠，等.基于改进AlexNet-GRU深度学习网络的配电网短期负荷预测方法[J].电力电容器与无功补偿，2023,44(4):48-54.ZHU Hainan,LI Fengshuo,SUN Huazhong,et al.Shortterm load prediction method of distribution network based on improved AlexNet-GRU deep learning network[J].Power Capacitor&Reactive Power Compensation,2023,44(4):48-54.
• [31]向德军，张维静，冯歆尧，等.考虑特征值细分的广义加性短期负荷预测模型[J].电力需求侧管理，2023,25(1):46-51.XIANG Dejun,ZHANG Weijing,FENG Xinyao,et al.Generalized additive short-term load forecasting model considering eigenvalue subdivision[J]. Power Demand Side Management,2023,25(1):46-51.
• [32]唐晓，陈芳，许强，等.改进鲸鱼算法优化的多维度深度极限学习机短期负荷预测[J].山东电力技术，2023,50(1):1-7.TANG Xiao,CHEN Fang,XU Qiang,et al. Short-term load forecasting based on multi-dimensional deep extreme learning machine optimized by improved whale algorithm[J].Shandong Electric Power,2023,50(1):1-7.
• [33]付泉泳，秦骁，张导，等.基于GCN-Informer模型的电力负荷短期预测[J].电力大数据，2024,27(7):22-34.FU Quanyong,QIN Xiao,ZHANG Dao,et al.Short term forecasting of power load based on GCN-informer model[J].Power Systems and Big Data,2024,27(7):22-34.
• [34]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.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.
• [35]曹帅，尹杰，李艺丰，等.基于VMD-SSA-BiLSTM的多维时序电力负荷预测[J].电力需求侧管理，2024,26(6):88-93.CAO Shuai,YIN Jie,LI Yifeng,et al. Multi-featured power load forecasting based on VMD-SSA-Bi LSTM[J]. Power Demand Side Management,2024,26(6):88-93.
• [36]袁玉宝，屈海云，任庆峰.考虑分时段变化趋势的PCASABO-BiLSTM短期电力负荷预测方法研究[J].电气自动化，2025,47(1):82-85.YUAN Yubao,QU Haiyun,REN Qingfeng.Research on PCA-SABO-BiLSTM short term power load forecasting method considering time period trends[J].Electrical Automation,2025,47(1):82-85.
• [37]杨城，刁艳美，刘颂.基于VMD-希尔伯特变换的机车信号解调方法[J].铁路计算机应用，2025,34(2):76-82.YANG Cheng,DIAO Yanmei,LIU Song.Cab signal demodulation method based on VMD and Hilbert transform[J].Railway Computer Application,2025,34(2):76-82.
• [38]张征鑫，张笃振.基于键值注意力机制的目标检测算法性能优化[J].计算机系统应用，2025,34(4):195-206.ZHANG Zhengxin,ZHANG Duzhen.Performance optimization of object detection algorithm based on key-value attention mechanism[J]. Computer Systems and Applications,2025,34(4):195-206.
• [39]韩宝慧，陆玲霞，包哲静，等.基于多头概率稀疏自注意力模型的综合能源系统多元负荷短期预测[J].电力建设，2024,45(2):127-136.HAN Baohui,LU Lingxia,BAO Zhejing,et al.Short-term forecasting of multienergy loads of integrated energy system based on multihead probabilistic sparse self-attention model[J].Electric Power Construction,2024,45(2):127-136.
• [40]张钰声，曹敏，雷宇，等.基于SSA-BiGRU-CNN神经网络和波动数据修正的电动汽车短期负荷预测模型[J].电网与清洁能源，2025,41(2):67-74.ZHANG Yusheng,CAO Min,LEI Yu,et al.A short-term load forecasting model for electric vehicles based on the SSA-BiGRU-CNN neural network and fluctuation data correction[J].Power System and Clean Energy,2025,41(2):67-74.