区域综合能源系统短期电力负荷预测  

Short-term power load forecast for regional integrated energy system

作　　者：方雨兴 李梅[1] FANG Yuxing;LI Mei(College of Electrical and Information Engineering,Science and Technology of Anhui University,Huainan 232001,China)

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232001

出　　处：《延边大学学报(自然科学版)》2025年第1期111-114,共4页Journal of Yanbian University(Natural Science Edition)

基　　金：安徽省高校自然科学重点项目(KJ2021A0471).

摘　　要：为提高短期电力负荷预测的精度,提出了一种基于卷积神经网络(CNN)和长短期记忆网络(LSTM)混合预测模型.利用2017年安徽省小时级电力负荷数据进行算例分析表明,CNN-LSTM混合预测模型的预测精度能够达到99.99%,均方根误差值为0.04%,显著优于单一模型和其他组合预测模型.因此,CNN-LSTM混合预测模型在区域综合能源系统中具有良好的应用价值.In order to improve the accuracy of short-term power load prediction,a hybrid prediction model based on a convolutional neural network(CNN)and a long short-term memory(LSTM)is proposed.An arithmetic example analysis using the hourly-level power load data of Anhui Province in 2017 shows that the prediction accuracy of the CNN-LSTM hybrid prediction model can reach 99.99%,and the root-mean-square error value is 0.04%,which is significantly better than that of the single model and the other combined prediction models.Therefore,the CNN-LSTM hybrid prediction model has a good value of application in the regional integrated energy system.

关 键 词：短期电力负荷 综合能源系统 CNN-LSTM混合预测模型 CNN预测模型 LSTM预测模型 

分 类 号：TM715[电气工程—电力系统及自动化]