.png){kind=icon}
.png){kind=icon}
Return
A physics-guided multi-task framework for joint forecasting of heating load and return temperatures at building-side district heating substations
.png){kind=icon}
PRE
AI
Z
张
J
DOI：10.1016/j.buildenv.2026.115090.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A physics-guided multi-task framework for district heating substations. • A physics-aware channel attention mechanism for dynamic feature reweighting. • A physics-constrained loss function promoting physically plausible predictions. • Heating-load RMSE reduced by 7.0–14.4% and return-temperature MAE kept below 0.6 ∘C .
Journal
IF:
7.6
Papers:
1.3W
Citations:
6.6W
Organization
Cited Papers