Times series forecasting for urban building energy consumption based on graph convolutional network

•Develop a Spatiotemporal graph convolutional network for hourly energy predictions.•Inter-building impacts are considered in graph-based method for prediction.•Test ST-GCN on campus buildings and validate its improved performance.•Discuss the interpretability of the ST-GCN modelling results. The wo...

Celý popis

Podrobná bibliografie

Vydáno v:	Applied energy Ročník 307; s. 118231
Hlavní autoři:	Hu, Yuqing, Cheng, Xiaoyuan, Wang, Suhang, Chen, Jianli, Zhao, Tianxiang, Dai, Enyan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.02.2022
Témata:	algorithms Building interdependency energy conservation energy efficiency Graph neural network prediction summer time series analysis Time-series prediction Urban-scale building simulation winter Time-series prediction Building interdependency Graph neural network Urban-scale building simulation
ISSN:	0306-2619, 1872-9118
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!