| 14 | 0 | 6 |
| 下载次数 | 被引频次 | 阅读次数 |
目的:对居民区充电桩充电负荷进行精准化的预测。方法:首先基于皮尔逊相关系数(Person)筛选预测模型的输入特征，并采用滑动窗口法构建输入矩阵；然后利用集合经验模态分解(ensemble empirical mode decomposition, EEMD)将原始充电负荷序列分解为多个稳定、有规律的时序模态函数(intrinsic mode function, IMF),突出负荷数据的时序特征；最后针对每个IMF分别构建CNN-Transformer模型，对各个模型的预测结果进行加权得到最终充电负荷预测值。结果:基于某居民区的实际充电负荷数据进行算例分析，本研究所提模型与Transformer相比，均方根误差(root mean square error, RMSE)降低22.90%,预测效果显著提升。结论:实验对比证明，采用EEMD分解和卷积神经网络模块能够更有效地提升模型捕捉负荷数据中时序、局部特征的能力，本研究所提预测方法可以准确预测居民区的充电需求，为充电桩未来规划提供可靠的理论依据。
Abstract：Aims: This paper studies the method to accurately predict the charging pile load in residential areas. Methods: First, the input features of the prediction model were selected based on the Pearson correlation coefficient; and the input matrix was constructed using the sliding window method. Then the original charging load sequence was decomposed into multiple stable and regular intrinsic mode functions through EEMD to highlight the time series characteristics of the load data. Finally, a CNN-Transformer model was constructed for each IMF; and the final predicted charging load was obtained by weighting the prediction results of each model. Results: An example analysis was conducted based on the actual charging load data of a residential area. Compared with the transformer, the root mean square error of the proposed model was reduced by 22.90%. Conclusions: It is experimentally proved that the EEMD decomposition and convolutional neural network modules can more effectively improve the ability of the model to capture the time series and local features in the load data; and the prediction method proposed in this paper can accurately predict the charging demand in residential areas and provide a reliable theoretical basis for the future planning of charging piles.
[1] CHEN J,LI F Y,YANG R R,et al.Impacts of increasing private charging piles on electric vehicles' charging profiles:A case study in Hefei City,China[J].Energies,2020,13(17):4387.
[2] ZHANG K Y,TIAN Y J,SHEN B,et al.Orderly charging strategy for residential areas taking into account demand from both sides of supply and demand[C]//2022 4th International Conference on Smart Power & Internet Energy Systems (SPIES).Beijing:IEEE,2022:1744-1748.
[3] TAO P,ZHAO J P,LIU X Y,et al.Grid load forecasting based on hybrid ensemble empirical mode decomposition and CNN-BiLSTM neural network approach[J].International Journal of Low-Carbon Technologies,2024,19:330-338.
[4] HE Z L,CHEN S Y,PAN N,et al.Short-term power load forecasting of multi-charging piles based on improved gated recurrent unit[J].IEEE Access,2023,12:2490-2499.
[5] LI H T,TANG M A,MU Y F,et al.Achieving accurate and balanced regional electric vehicle charging load forecasting with a dynamic road network:A case study of Lanzhou City[J].Applied Intelligence,2024,54(19):9230-9252.
[6] 罗卓伟，胡泽春，宋永华，等.电动汽车充电负荷计算方法[J].电力系统自动化，2011,35(14):36-42.LUO Z W,HU Z C,SONG Y H,et al.Study on plug-in electric vehicles charging load calculating[J].Automation of Electric Power Systems,2011,35(14):36-42.
[7] ZHANG L,HUANG Z J,WANG Z P,et al.An urban charging load forecasting model based on trip chain model for private passenger electric vehicles:A case study in Beijing[J].Energy,2024,299:130844.
[8] 崔杨，朱晗，王议坚，等.基于CNN-SAEDN-Res的短期电力负荷预测方法[J].电力系统自动化设备，2024,44(4):164-179.CUI Y,ZHU H,WANG Y J,et al.Short-term power load forecasting method based on CNN-SAEDN-Res[J].Electric Power Automation Equipment,2024,44(4):164-179.
[9] 张铭玮，李正权，方志豪.基于量子粒子群优化的CNN-LSTM水质预测模型[J].中国计量大学学报，2022,33(3):303-309,323.ZHANG M W,LI Z Q,FANG Z H.A CNN-LSTM water quality prediction model based on quantum particle swarm optimization[J].Journal of China University of Metrology,2022,33(3):303-309,323.
[10] 彭曙蓉，黄士峻，李彬，等.基于深度学习分位数回归模型的充电桩负荷预测[J].电力系统保护与控制，2020,48(2):44-50.PENG S R,HUANG S J,LI B,et al.Charging pile load prediction based on deep learning quantile regression model[J].Power System Protection and Control,2020,48(2):44-50.
[11] UNTERLUGGAUER T,RAUMA K,J?RVENTA-USTA P,et al.Short-term load forecasting at electric vehicle charging sites using a multivariate multi-step long short-term memory:A case study from Finland[J].IET Electrical Systems in Transportation,2021,11(4):405-419.
[12] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[J].Advances in Neural Information Processing Systems,2017,30:5998-6008.
[13] 张亚丽，王聪，张宏立，等.基于非平稳Transformer的超短期风电功率多步预测[J].智慧电力，2024,52(1):108-115.ZHANG Y L,WANG C,ZHANG H L,et al.Multi-step prediction of ultra-short-term wind power based on non-stationary transformer[J].Smart Power,2024,52(1):108-115.
[14] 黄莉，甘恒玉，刘兴举，等.基于Transformer编码器的超短期光伏发电功率预测[J].智慧电力，2024,52(5):16-22,59.HUANG L,GAN H Y,LIU X J,et al.Ultra-short-term photovoltaic power generation prediction based on transformer encoder[J].Smart Power,2024,52(5):16-22,59.
[15] CHEN Y B,CHEN X M,XU A L,et al.A hybrid CNN-Transformer model for ozone concentration prediction[J].Air Quality,Atmosphere & Health,2022,15(9):1533-1546.
[16] WEN L,LI X Y,GAO L,et al.A new convolutional neural network-based data-driven fault diagnosis method[J].IEEE Transactions on Industrial Electronics,2017,65(7):5990-5998.
[17] 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.
[18] PENG D G,LIU Y,WANG D H,et al.Multi-energy load forecasting for integrated energy system based on sequence decomposition fusion and factors correlation analysis[J].Energy,2024,308:132796.
[19] 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 of the Royal Society A:Mathematical,Physical and Engineering Sciences.,1998,454(1971):903-995.
[20] KONG W,DONG Z Y,JIA Y,et al.Short-term residential load forecasting based on LSTM recurrent neural network[J].IEEE Transactions on Smart Grid,2017,10(1):841-851.
[21] ZHOU D H,LI Z Y,ZHU J L,et al.State of health monitoring and remaining useful life prediction of lithium-ion batteries based on temporal convolutional network[J].IEEE Access,2020,8:53307-53320.
[22] 卢忠山，袁建华.基于EEMD-LSTM方法的光伏发电系统超短期功率预测[J].中国测试，2022,48(12):125-132.LU Z S,YUAN J H,et al.Ultra-short term power prediction of photovoltaic power generation system based on EEMD-LSTM method[J].China Measurement & Test,2022,48(12):125-132.
[23] 刘辉，凌宁青，罗志强，等.基于TCN-LSTM和气象相似日集的电网短期负荷预测方法[J].智慧电力，2022,50(8):30-37.LIU H,LING N Q,LUO Z Q,et al.Power grid short-term load forecasting method based on TCN-LSTM and meteorological similar day sets[J].Smart Power,2022,50(8):30-37.
基本信息:
DOI：
中图分类号:U491.8;TM910.6
引用信息:
[1]陈倩楠,李璟,李灵至等.基于模态分解与CNN-Transformer的居民区充电桩充电负荷预测方法[J].中国计量大学学报,2025,36(01):53-60.
基金信息:
国家自然科学基金项目(No.12404539)