Surface Area (515 to 809 m2)
Wall Area (245 to 417 m2)
Roof Area (110 to 221 m2)
Overall Height (3.5 to 7 m)
Orientation (2:North, 3:East, 4:South, 5:West)
Glazing Area (0%,10%,25%,40% (0 to 0.4))
Glazing Area Distribution (1:Uniform, 2:North, 3:East, 4:South, 5:West)
The demo was developed using Python Tensorflow utilising the public domain dataset available at:
Kaggle
The model used feed forward artificial neural network with 8 inputs, one hidden layer with 10 nodes and 1 output node (original dataset have 2 outputs).
The model performance for training/testing:
Train MSE: 0.0098 RMSE: 0.0018
Test MSE: 0.0115 RMSE: 0.0000
Buildings energy consumption is put away around 40% of total energy use. Predicting heating and cooling loads of a building in the initial phase of the design to find out optimal solutions amongst different designs is very important, as well as in the operating phase after the building has been finished for efficient energy.
Input variables are:
- relative compactness,
- roof area,
- overall height,
- surface area,
- glazing area,
- wall area,
- glazing area distribution of a building,
- orientation.
Output variables:
- cooling loads of the building.