An unbalanced sample prediction algorithm based on LSTM and CNN in the new power systems

ZHANG Qi; LI Zhihao; FAN Yeping; MA Jianbo

doi:10.11959/j.issn.1000-0801.2025182

您当前的位置：

首页 >

文章列表页 >

An unbalanced sample prediction algorithm based on LSTM and CNN in the new power systems

Engineering and Application | 更新时间：2025-11-06

- An unbalanced sample prediction algorithm based on LSTM and CNN in the new power systems
- Telecommunications Science Vol. 41, Issue 10, Pages: 210-221(2025)
- 作者机构：
  
  安徽继远软件有限公司，安徽合肥 230093
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2025182
  CLC： TP183
- Received：02 February 2025，
  
  Revised：2025-08-05，
  
  Published：20 October 2025
- 稿件说明：
移动端阅览
张琦,李志浩,范叶平等.新型电力系统中一种基于LSTM和CNN的倾斜样本预测算法[J].电信科学,2025,41(10):210-221.

ZHANG Qi,LI Zhihao,FAN Yeping,et al.An unbalanced sample prediction algorithm based on LSTM and CNN in the new power systems[J].Telecommunications Science,2025,41(10):210-221.
张琦,李志浩,范叶平等.新型电力系统中一种基于LSTM和CNN的倾斜样本预测算法[J].电信科学,2025,41(10):210-221. DOI： 10.11959/j.issn.1000-0801.2025182.

ZHANG Qi,LI Zhihao,FAN Yeping,et al.An unbalanced sample prediction algorithm based on LSTM and CNN in the new power systems[J].Telecommunications Science,2025,41(10):210-221. DOI： 10.11959/j.issn.1000-0801.2025182.

摘要

基于电力数字空间技术体系，提出了一种基于特征关联性分析与改进卷积神经网络（convolutional neural network，CNN）-长短期记忆（long short-term memory，LSTM）网络的预测算法。首先，在注意力层，对用户关联性进行分析，将与电力负荷用户强相关的影响因素进行加权求平均，调整这些类别在用户电力负荷预测中的权重大小，加强少且重要的电力样本特征对电力负荷算法的影响并避免冗余特征的干扰，实现特征选择；其次，在CNN层，通过构建2层神经网络，提取样本的空间特征，并将该空间特征输入LSTM网络中；最后，通过LSTM网络层提取序列的时间特征，输出预测结果。实验基于北方某城市供应电力资源的6个重要用户的保密数据进行预测，实验结果表明，基于关联性分析与改进CNN-LSTM模型的MAPE在5类用户测试的误差均低于LSTM、随机森林和BP神经网络的误差。

Abstract

A prediction algorithm based on feature correlation analysis and improved CNN (convolutional neural network)-LSTM (long short-term memory) network was proposed based on the power digital space technology system. Firstly

in the attention layer

the user correlation was analyzed

and the influencing factors strongly related to power load users were weighted and averaged. The weight of these categories in user power load prediction was adjusted to strengthen the influence of few and important power sample features on power load calculation and avoid the interference of redundant features

achieving feature selection. Secondly

in the CNN layer

by constructing a two-layer neural network

the spatial features of the samples are extracted and inputted into LSTM. Finally

LSTM extract the temporal features of the sequence through the LSTM layer and output the prediction results. The experiment was based on confidential data from six important users supplying power resources in a northern city for prediction. The experimental results show that the MAPE based on correlation analysis and improved CNN-LSTM model was lower than the error of LSTM

random forest

and BP neural network in five types of user tests.

关键词

Keywords

references

SHI H , XU M H , LI R . Deep learning for household load forecasting: a novel pooling deep RNN [J ] . IEEE Transactions on Smart Grid , 2017 , 9 ( 5 ): 5271 - 5280 .

KONG W C , DONG Z Y , HILL D J , et al . Short-term residential load forecasting based on resident behaviour learning [J ] . IEEE Transactions on Power Systems , 2017 , 33 ( 1 ): 1087 - 1088 .

KUO P H , HUANG C J . A high precision artificial neural networks model for short-term energy load forecasting [J ] . Energies , 2018 , 11 ( 1 ): 213 .

陈振宇 , 刘金波 , 李晨 , 等 . 基于LSTM与XGBoost组合模型的超短期电力负荷预测 [J ] . 电网技术 , 2020 , 44 ( 2 ): 614 - 620 .

CHEN Z Y , LIU J B , LI C , et al . Ultra short-term power load forecasting based on combined LSTM-XGBoost model [J ] . Power System Technology , 2020 , 44 ( 2 ): 614 - 620 .

李玉志 , 刘晓亮 , 邢方方 , 等 . 基于Bi-LSTM和特征关联性分析的日尖峰负荷预测 [J ] . 电网技术 , 2021 , 45 ( 7 ): 2719 - 2730 .

LI Y Z , LIU X L , XING F F , et al . Daily peak load prediction based on correlation analysis and bi-directional long short-term memory network [J ] . Power System Technology , 2021 , 45 ( 7 ): 2719 - 2730 .

史含笑 , 王雷春 . 结合LSTM和自注意力机制的图卷积网络短期电力负荷预测 [J ] . 计算机应用 , 2024 , 44 ( 1 ): 311 - 317 .

SHI H X , WANG L C . Short-term power load forecasting by graph convolutional network combining LSTM and self-attention mechanism [J ] . Journal of Computer Applications , 2024 , 44 ( 1 ): 311 - 317 .

李焱 , 贾雅君 , 李磊 , 等 . 基于随机森林算法的短期电力负荷预测 [J ] . 电力系统保护与控制 , 2020 , 48 ( 21 ): 117 - 124 .

LI Y , JIA Y J , LI L , et al . Short term power load forecasting based on a stochastic forest algorithm [J ] . Power System Protection and Control , 2020 , 48 ( 21 ): 117 - 124 .

赵兵 , 王增平 , 纪维佳 , 等 . 基于注意力机制的CNN-GRU短期电力负荷预测方法 [J ] . 电网技术 , 2019 , 43 ( 12 ): 4370 - 4376 .

ZHAO B , WANG Z P , JI W J , et al . A short-term power load forecasting method based on attention mechanism of CNN-GRU [J ] . Power System Technology , 2019 , 43 ( 12 ): 4370 - 4376 .

赵佩 , 代业明 . 基于实时电价和加权灰色关联投影的SVM电力负荷预测 [J ] . 电网技术 , 2020 , 44 ( 4 ): 1325 - 1332 .

ZHAO P , DAI Y M . Power load forecasting of SVM based on real-time price and weighted grey relational projection algorithm [J ] . Power System Technology , 2020 , 44 ( 4 ): 1325 - 1332 .

王克杰 , 张瑞 . 基于改进BP神经网络的短期电力负荷预测方法研究 [J ] . 电测与仪表 , 2019 , 56 ( 24 ): 115 - 121 .

WANG K J , ZHANG R . Research on short-term power load forecasting method based on improved BP neural network [J ] . Electrical Measurement & Instrumentation , 2019 , 56 ( 24 ): 115 - 121 .

刘亚珲 , 赵倩 . 基于聚类经验模态分解的CNN-LSTM超短期电力负荷预测 [J ] . 电网技术 , 2021 , 45 ( 11 ): 4444 - 4451 .

LIU Y H , ZHAO Q . Ultra-short-term power load forecasting based on cluster empirical mode decomposition of CNN-LSTM [J ] . Power System Technology , 2021 , 45 ( 11 ): 4444 - 4451 .

陈卓 , 孙龙祥 . 基于深度学习LSTM网络的短期电力负荷预测方法 [J ] . 电子技术 , 2018 , 47 ( 1 ): 39 - 41 .

CHEN Z , SUN L X . Short-term electrical load forecasting based on deep learning LSTM networks [J ] . Electronic Technology , 2018 , 47 ( 1 ): 39 - 41 .

李冲 . 随机森林模型预测岩溶区酸性煤矿井水锰污染 [J ] . 中国煤炭地质 , 2021 , 33 ( 3 ): 43 - 47, 59 .

LI C . Prediction of karst region acidic coalmine water manganese pollution based on random forest [J ] . Coal Geology of China , 2021 , 33 ( 3 ): 43 - 47, 59 .

魏健 , 赵红涛 , 刘敦楠 , 等 . 基于注意力机制的CNN-LSTM短期电力负荷预测方法 [J ] . 华北电力大学学报(自然科学版) , 2021 , 48 ( 1 ): 42 - 47 .

WEI J , ZHAO H T , LIU D N , et al . Short-term power load forecasting method by attention-based CNN-LSTM [J ] . Journal of North China Electric Power University (Natural Science Edition) , 2021 , 48 ( 1 ): 42 - 47 .

SRIVASTAVA A K , PANDEY A S , SINGH D . Notice of violation of IEEE publication principles: short-term load forecasting methods: a review [C ] // Proceedings of the 2016 International Conference on Emerging Trends in Electrical Electronics & Sustainable Energy Systems (ICETEESES) . Piscataway : IEEE Press , 2016 : 130 - 138 .

王红亚 , 王旭红 , 孙俊敏 , 等 . 混合蛙跳算法优化神经网络的同步电机转子故障检测 [J ] . 微电机 , 2017 , 50 ( 9 ): 22 - 26 .

WANG H Y , WANG X H , SUN J M , et al . Synchronous machine rotor inter-turn short circuit fault detection based on ISFLA-BP neural network [J ] . Micromotors , 2017 , 50 ( 9 ): 22 - 26 .

Views

529

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Analysis and research on the impact of medium voltage power line carrier communication

Research on 5G core network service model intelligent prediction

An LSTM auto-encoder based anomaly detection for industrial system

Prediction of power grid fault repair time based on multi-model fusion

Sentiment analysis of telecom official micro-blog users based on LSTM deep learning model

Related Author

ZHAO Tonghan

SU Yuzhong

Helin LIU

Nan FENG

Daping ZHONG

Mineng FU

Haijun YANG

Quan ZHOU

Related Institution

Guyuan Power Supply Company, State Grid Ningxia Electric Power Co., Ltd.

China Mobile Research Institute

China Mobile Communications Co., Ltd.

State Grid Zhejiang Electric Power Company

Zhejiang University of Technology

⁰