深度学习在建筑物用电预测中的应用研究  

Application of deep learning in building power consumption prediction

作　　者：杨明智[1] 杨昭[1] 夏乾洋 Yang Mingzhi;Yang Zhao;Xia Qianyang(School of economics and management,China University of mining and technology,Xuzhou Jiangsu,221116)

机构地区：[1]中国矿业大学经济管理学院,江苏徐州221116

出　　处：《电子测试》2021年第20期63-65,共3页Electronic Test

摘　　要：本文使用深度学习技术构建一种新的短期电力负荷预测模型,该模型将注意力机制和seq2seq神经网络相结合,能够显著提升预测的准确度。为了验证模型的有效性,使用一所国内大学宿舍楼的真实用电数据进行实验,并与传统预测模型GBRT和LSTM进行了对比,结果证明新模型相较于传统模型有明显改进。This paper uses deep learning technology to build a new short-term power load forecasting model,which combines attention mechanism and seq2seq neural network,and can significantly improve the accuracy of forecasting.In order to verify the effectiveness of the model,the real power consumption data of a domestic university dormitory building is used for experiment,and compared with the traditional prediction models gbrt and LSTM.The results show that the new model has obvious improvement compared with the traditional model.

关 键 词：深度学习 建筑物能耗 负荷预测 

分 类 号：TU111.195[建筑科学—建筑理论] TP18[自动化与计算机技术—控制理论与控制工程]