- 文献要素
-
摘要:为了获得更好的建筑能耗预测精度,基于极限GAP深度学习方法,利用变体GRU结合Attention注意力机制,提出一种建筑能耗预测方法。分析表明,该方法预测性能相比其他方法,预测精度高,鲁棒性高,有助于管理者和相关工作人员对建筑设施进行更有效的节能操作。
关键词:建筑能耗;深度学习;节能;预测精度
Abstract:In order to obtain better prediction accuracy of building energy consumption,based on a deep learning method called extreme GAP,this paper uses variant GRU combined with the Attention mechanism to put forward a building energy consumption prediction method. The analysis shows that compared with other methods,the prediction performance of this method is more accurate and robust,which is helpful for managers and related staff to carry out more effective energy saving operation on building facilities.
Keywords:building energy consumption;deep learning;energy saving;prediction accuracy
参考文献
[1] H. Zhang,Y. Fu,L.B. Feng,Y. Zhang,etal. Implementation of Hybrid Alignment Algorithm for Protein Database Search on the SW26010 Many-Core Processor[J]. IEEE Access,2019(7):128054-128063.
[2] L.Q. Zuo,H.M. Sun,Q.C. Mao,R. Qi,R.S. Jia. Natural scene text recognition based on encoder-decoder framework[J]. IEEE Access,2019(7):62616-62623.
[3] Lv,Y,Duan,Y,Kang,W,etal. Traffic flow prediction with big data:A deep learning approach[J]. IEEE Trans. Intell. Transp. Syst,2015,16:865-873.
[4] Naji,S,Keivani,A,Shamshirband,S,etal. Estimating building energy consumption using extreme learning machine method[J]. Energy,2016,97:506-516.
建筑经济,2021(05):117-120