Short-term load forecasting method based on weather classification and convolutional neural network

戴明明; 王 康; 李 强; 石炬烽; 邓亚伟; 张荣荣; 刘蓉晖; 孙改平

doi:10.3969/j.issn.1009-1831.2023.03.015

您当前的位置：

首页 >

文章列表页 >

Short-term load forecasting method based on weather classification and convolutional neural network

更新时间：2026-03-05

- Short-term load forecasting method based on weather classification and convolutional neural network
- Vol. 25, Issue 3, (2023)
- 作者机构：
  
  1. 国网安徽省电力有限公司亳州供电公司,安徽,亳州,236800
  2. 上海电力大学电气工程学院,上海,200082
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2023.03.015
  CLC：
- Published：2023
- 稿件说明：
移动端阅览
戴明明, 王康, 李强, et al. Short-term load forecasting method based on weather classification and convolutional neural network[J]. 2023, 25(3).
DOI：

戴明明, 王康, 李强, et al. Short-term load forecasting method based on weather classification and convolutional neural network[J]. 2023, 25(3). DOI： 10.3969/j.issn.1009-1831.2023.03.015.

摘要

为减少天气因素对短期电力负荷预测效果的影响，提高模型的预测精度，提出了一种基于天气分类和卷积神经网络的短期负荷预测模型。首先通过天气类型初分将原始数据样本集划分为晴天、阴天、多云和雨天4种类型。其次，为了识别相似气象条件，运用相关系数和k均值聚类方法，找到对新型负荷出力影响最大的气象因素，并对其聚类，选取高相似度的数据样本。之后根据特征选择的结果，构造神经网络输入数据集。最后，将该数据集输入至卷积神经网络训练并预测。通过算例验证分析所提模型具有更高的预测精度。

Abstract

In order to reduce the impact of weather factors on short-term power load forecasting and improve the forecasting accuracy of the model

a short-term load forecasting model based on weather classification and convolutional neural networks is proposed. Firstly

through the preliminary classification of weather types

the model divides the original data sample set into four types such as sunny

cloudy

cloudy and rainy days. Secondly

in order to identify similar meteorological conditions

the correlation coefficient and k- means clustering method are used to find the meteorological factors that have the greatest impact on the new load output

cluster them

and select high similarity data samples. Then

according to the result of feature selection

the neural network input data set is constructed. Finally

the data set is input to the convolutional neural network for training and prediction. The proposed model has higher prediction accuracy through verification and analysis of numerical examples.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Load forecasting and adjustable potential analysis of silicon carbide enterprises based on CNN-Attention-BiLSTM

Operating fault diagnosis method for power load management terminals based on auto-encoder multilayer perception

Electrical load forecasting model based on hybrid deep learning

Dynamic assessment of multi-customer load adjustable potential of BP neural network based on particle swarm

细木工板生产工艺的探讨

Related Author

杨彤

孟涛

曹万雄

唐聪

马国瀚

任明远

滕姗姗

苏慧玲

Related Institution

国网甘肃省电力公司

国网甘肃省电力公司兰州供电公司

国网电力科学研究院武汉能效测评有限公司

国网电力科学研究院有限公司

国网江苏省电力有限公司营销服务中心

AI问答

⁰