Hybrid neural network power load forecasting based on ensemble model

裴星懿; 黄陈蓉; 张建德; 霍 瑛

doi:10.3969/j.issn.1009-1831.2022.05.011

您当前的位置：

首页 >

文章列表页 >

Hybrid neural network power load forecasting based on ensemble model

更新时间：2026-03-05

- Hybrid neural network power load forecasting based on ensemble model
- Vol. 24, Issue 5, (2022)
- 作者机构：
  
  1. 南京工程学院电力工程学院,南京,211100
  2. 南京工程学院计算机工程学院,南京,211100
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2022.05.011
  CLC：
- Published：2022
- 稿件说明：
移动端阅览
裴星懿, 黄陈蓉, 张建德, et al. Hybrid neural network power load forecasting based on ensemble model[J]. 2022, 24(5).
DOI：

裴星懿, 黄陈蓉, 张建德, et al. Hybrid neural network power load forecasting based on ensemble model[J]. 2022, 24(5). DOI： 10.3969/j.issn.1009-1831.2022.05.011.

摘要

为了提高负荷预测的精度与泛化能力，提出了一种基于Bagging集成算法的GRU-BiLSTM-Self-attention模型。为充分提取高维输入数据的多个特征，该模型采用BiLSTM-Self-attention模型提取局部特征，采用GRU模型提取时序特征，从同一训练集中独立抽取样本子集并进行训练，对输出结果集成处理并得到最终的预测结果。选取南京某供电公司真实数据进行实验，并与LSTM神经网络、GRU神经网络、BiLSTM神经网络等预测模型进行对比。实验数据表明，该模型的均方根误差为50.770 3，准确率为97.36%。相较于其它用于对比的模型，该结果表明本模型在预测效果上具有一定程度的优势，说明所提出的模型具有更好的泛化能力与预测精度。

Abstract

In order to improve the accuracy and generalization ability of load forecasting

a GRU-BiLSTM-Self-attention model based on Bagging integrated algorithm is proposed. In order to fully extract multiple features of high-dimensional input data

the model uses BiLSTM- Self- attention model to extract local features and GRU model to extract temporal features

independently extract sample subsets from the same training set and train them

integrate the output results and obtain the final prediction results. The real data of a power supply company in Nanjing are selected for the experiment and compared with the prediction models such as LSTM neural network

GRU neural network and BiSTM neural network.The experimental data show that the root mean square error of the model is 50.770 3

and the accuracy is 97.36% . Compared with other models used for comparison

the results show that this model has certain advantages in prediction effect

which shows that the proposed model has better generalization ability and 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

Design and implementation of virtual power plant system supporting dynamic aggregation of equipment

Short-term power load forecasting based on load decomposition and identification

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

Study on the influence of environmental climate change on the load of fishery electrical equipment

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

Related Author

王孟强

黄澍

孟洪民

诸葛雪迎

刘泽三

徐哲男

李子钰

朱俊澎

Related Institution

国网信息通信产业集团有限公司

国网河南省电力公司经济技术研究院

河海大学电气与动力工程学院

国网甘肃省电力公司兰州供电公司

国网甘肃省电力公司

AI问答

⁰