Short-term load probability forecasting based on VaR and integrated neural network quantile regression

陈 腾; 阮 舟; 郑志敏

doi:10.3969/j.issn.1009-1831.2023.06.010

您当前的位置：

首页 >

文章列表页 >

Short-term load probability forecasting based on VaR and integrated neural network quantile regression

更新时间：2026-03-05

- Short-term load probability forecasting based on VaR and integrated neural network quantile regression
- Vol. 25, Issue 6, (2023)
- 作者机构：
  
  1. 国网浙江省电力有限公司杭州供电公司,杭州,310000
  2. 浙大宁波理工学院信息科学与工程学院,浙江,宁波,315000
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2023.06.010
  CLC：
- Published：2023
- 稿件说明：
移动端阅览
陈腾, 阮舟, 郑志敏. Short-term load probability forecasting based on VaR and integrated neural network quantile regression[J]. 2023, 25(6).
DOI：

陈腾, 阮舟, 郑志敏. Short-term load probability forecasting based on VaR and integrated neural network quantile regression[J]. 2023, 25(6). DOI： 10.3969/j.issn.1009-1831.2023.06.010.

摘要

短期负荷预测在电力系统规划与运行中起着重要作用。提出一种融合注意力机制和分位数回归的混合卷积双向长短期神经网络短期负荷概率预测模型。首先

利用相关性分析选取合适的天气变量和历史负荷。其次

通过Copula模型计算出风险阈值

该值被用于构造峰值二进制指示输入特征。接着

将所选特征集输入到卷积双向长短期神经网络预测模型

引入注意力机制给予数据不同关注。然后

采用核密度估计对负荷进行概率预测。最后

使用平均绝对百分比误差和均方根误差对模型预测性能进行评估。仿真结果表明

该模型具有更高的预测精度。

Abstract

Short-term load forecasting plays an important role in power system planning and operation. A hybrid short-term load probability density forecasting method based on convolutional bi-directional long short-term memory quantile regression blending attention mechanism is proposed. Firstly

the weather variables and historical loads are selected by using relevant mechanisms.Next

the Copula model is used to calculate the risk threshold

which is used to construct the peak binary indicator input characteristics. Then

the selected feature sets are input into the convolutional bi-directional long short-term memory quantile regression blending attention mechanism prediction model. Then

kernel density estimation is used to fit the load probabilistic prediction. Finally

the prediction performance is evaluated using the mean absolute percentage error and root mean square error. The simulation results show that proposed model has higher prediction accuracy.

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

Sentiment analysis of 95598 work orders based on parallel hybrid neural networks

Multi-featured power load forecasting based on VMD-SSA-BiLSTM

Short-term power load forecasting based on parallel sequential convolutional neural network

Adaptive multi ⁃ scence single ⁃ user flexible load control effect evaluation algorithm

Related Author

杨彤

孟涛

曹万雄

唐聪

马国瀚

任明远

刘晓捷

王恭玥

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

国网江苏省电力有限公司常州供电分公司

东南大学电气工程学院

国网江苏省电力有限公司

AI问答

⁰