Abstract:
短期电力负荷预测的准确性对电力系统的运营和规划至关重要.提出一种基于相似日的多模型融合方法(Similarity-based Multi-Model Fusion Method,SMFM).首先,利用灰色关联分析法(Grey Relational Analysis,GRA)和平均基准负荷日选取相似日.其次,采用Stacking算法进行两阶段预测.第一阶段,采用极端梯度提升模型(Extreme Gradient Boosting,XGBoost)、轻量级梯度提升机(Light Gradient Boosting Machine,LightGBM)以及卷积神经网络与双向长短期记忆(Convolutional Neural Network combined with Bidirectional Long Short-Term Memory,CNN-BiLSTM)网络融合模型.第二阶段,采用了多层感知器(Multilayer Perceptron,MLP)模型,以进一步提高预测的准确性.实验结果表明,所提出的方法在均方误差(Mean Squared Error,MSE)、均方根误差(Root Mean Squared Error,RMSE)和平均绝对误差(Mean Absolute Error,MAE)方面,较其他负荷预测模型有所提升.
Keyword:
Reprint 's Address:
Email:
Version:
Source :
电脑与信息技术
ISSN: 1005-1228
Year: 2025
Issue: 1
Volume: 33
Page: 6-9,54
Cited Count:
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 0
Affiliated Colleges: