摘要
通过预测空调负荷,提前改变空调运行状态可以有效提高空调系统的运行效率、改善室内热环境。本文提出基于深度学习LSTM模型短期空调负荷预测方法,对某建筑空调冷负荷进行预测,结果证明相对于传统预测模型,LSTM模型的误差更低,预测效果更好。
The operating efficiency of air conditioning system and the indoor thermal performance could be effectively improved by presetting air conditioning system based on predicted cooling load.This paper proposes a LSTM model based deep learning method to predict the short-term building cooling load of a specified building.The results suggest that compared to traditional prediction models,the LSTM model could provide better prediction results with minor errors.
作者
邓翔
陈文景
邓仕钧
DENG Xiang;CHEN Wen-jing;DENG Shi-jun(Shenzhen DAS Intellitech Co.,Ltd.;School of Automation Science and Engineering,South China University of Technology;School of Architecture,Tsinghua University)
出处
《建筑热能通风空调》
2021年第11期25-27,51,共4页
Building Energy & Environment
基金
中国博士后科学基金(2020M672758)。
关键词
空调冷负荷预测
长短期记忆网络
传统预测模型
air conditioning cooling load prediction
long-short term memory
traditional prediction model
