| 引用本文: | 吴方权,李斯琦,胡骏涵,汤成佳,邹建业.基于VMD-SE-CNN-BiLSTM的电动汽车充电负荷短期预测[J].电力系统保护与控制,2025,53(22):153-161.[点击复制] |
| WU Fangquan,LI Siqi,HU Junhan,TANG Chengjia,ZOU Jianye.Short-term forecasting of electric vehicle charging load based on VMD-SE-CNN-BiLSTM[J].Power System Protection and Control,2025,53(22):153-161[点击复制] |
|
| 摘要: |
| 近年来，随着电动汽车保有量的快速增长，准确预测电动汽车充电负荷已成为电网规划和充电设施优化的重要研究课题。针对传统预测方法难以处理负荷数据复杂非线性特征和多因素动态影响的问题，提出了一种基于数据预处理、结合变分模态分解-样本熵(variational mode decomposition-sample entropy, VMD-SE)数据重构和卷积神经网络-双向长短期记忆网络(convolutional neural network-bidirectional long short-term memory, CNN-BiLSTM)深度学习框架的充电负荷预测模型。首先，利用高斯混合模型-K最近邻(Gaussian mixture model-K-nearest neighbor, GMM-KNN)方法检测并填补数据中的异常值和缺失值，提升数据质量。然后，采用VMD对负荷数据进行分解，并通过 SE筛选重要模态重构信号以提取多尺度特征。最后，结合CNN和BiLSTM模型，构建混合深度学习框架，捕捉负荷的局部特征和时序依赖关系以实现准确预测。实验结果表明，该方法在多季节负荷预测中表现出较高的精度和鲁棒性，显著优于传统方法，为电动汽车充电负荷预测提供了有效解决方案。 |
| 关键词: 电动汽车 充电负荷预测 VMD-SE CNN-BiLSTM 深度学习 |
| DOI：10.19783/j.cnki.pspc.241701 |
| 投稿时间：2024-12-20修订日期：2025-02-19 |
| 基金项目:南方电网公司科技项目资助(066700KC23100032)“电动汽车有序充电需求响应潜力分析及优化运营技术” |
|
| Short-term forecasting of electric vehicle charging load based on VMD-SE-CNN-BiLSTM |
| WU Fangquan1,LI Siqi1,HU Junhan1,TANG Chengjia1,ZOU Jianye2 |
| (1.?Information Communication Branch of Guizhou Power Grid Company, Guiyang 550003, China;
2. Beijing Kedong Electric Power Control System Co., Ltd., Beijing 100194, China) |
| Abstract: |
| In recent years, with the rapid growth of electric vehicle (EV) ownership, accurate forecasting EV charging loads has become a crucial research topic for power grid planning and charging infrastructure optimization. To address the challenges of traditional forecasting methods in handling the complex nonlinear characteristics and dynamically coupled influencing factors in load data, this paper proposes a charging load forecasting model that integrates data preprocessing, variational mode decomposition-sample entropy (VMD-SE) data reconstruction, and a convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) deep learning framework. First, the Gaussian mixture model-K-nearest neighbor (GMM-KNN) method is utilized to detect and fill abnormal and missing values in the data, improving data quality. Next, VMD is employed to decompose the load data, and SE is applied to select and reconstruct important modal signals to extract multi-scale features. Finally, a hybrid deep learning framework combining CNN and BiLSTM models is constructed to capture local features and temporal dependencies for accurate forecasting. Experimental results demonstrate that the proposed method exhibits high accuracy and robustness in multi-season load forecasting, significantly outperforming traditional methods. This provides an effective solution for EV charging load forecasting. |
| Key words: EV charging load forecasting VMD-SE CNN-BiLSTM deep learning |
