基于MIC-ResNet-LSTM-BP的短期电力负荷预测
Short-Term Power Load Forecasting Based on MIC-ResNet-LSTM-BP
简定辉 1李萍 1黄宇航 1梁志洋1
作者信息
- 1. 宁夏大学物理与电子电气工程学院,宁夏 银川 750021
- 折叠
摘要
电力能源的合理调度是关系民生的重要问题,而合理的电能调度离不开精准的负荷预测.为有效提高负荷预测精度,提出一种基于MIC-ResNet-LSTM-BP的短期电力负荷预测方法来预测未来1 天和3 天的负荷.首先,采集6 维负荷特征数据,利用最大信息系数(MIC)分析各影响因素与负荷的关联程度从而进行特征选择;其次,采用残差网络(ResNet)对数据进行特征提取;然后,将重构数据输入到长短时记忆网络(LSTM)挖掘数据时序特征;最后,采用Dropout层增加模型泛化能力,通过改进BP神经网络学(BPNN)习数据特征并利用Adam优化器训练模型.将以上模型与BPNN、KNN、LSTM、LSTM-BPNN作对比实验,有力验证了上述模型在负荷预测领域的精准性.
Abstract
Reasonable dispatch of electric energy is an important issue related to people's livelihood,and reasona-ble electric energy dispatch is inseparable from accurate load forecasting.In order to effectively improve the accuracy of load forecasting,this paper proposes a short-term power load forecasting method based on MIC-ResNet-LSTM-BP to improve the accuracy of load forecasting for the next 1 day and 3 days.First,the 6-dimensional load characteristic data were collected,and the maximum information coefficient(MIC)was used to analyze the correlation between each influencing factor and the load,so as to carry out feature selection;secondly,residual network(ResNet)was used to extract features from the data;then,the reconstructed data was input into the short and long duration memory network(LSTM)to mine the temporal features of the data;finally,the Dropout layer was used to increase the generalization ability of the model,and the data features of BP Neural Network Science(BPNN)were improved and the Adam opti-mizer was used to train the model.Compared with BPNN,KNN,LSTM and LSTM-BPNN,the accuracy of this model in the field of load prediction is verified.
关键词
最大信息系数/负荷预测/残差网络/长短时记忆网络/神经网络Key words
Maximum information coefficient/Load forecasting/Residual network/Short and long duration mem-ory network/Neural network引用本文复制引用
基金项目
宁夏回族自治区自然科学基金(2021AAC03073)
出版年
2024
NETL
NSTL
万方数据