• +1-619-344-7513
  • info@atelieracosta.com

Using Linear Regression to Gain Insights Into Building Energy Efficiency

Using Linear Regression to Gain Insights Into Building Energy Efficiency

Using Linear Regression to Gain Insights Into Building Energy Efficiency

With this project, our aim was to answer the following question: How should we design buildings (with respect to heating load) in the future?
 
Some additional questions that needed to be answered include:
 

  1. Is there a relationship between building features and heating load?
  2. How strong is that relationship?
  3. Which are the strongest contributing features to heating load?
  4. Can heating load be predicted given a particular building design?

 
Features Information
 
The dataset contains eight attributes (or features, denoted by X1X8) and two responses (or outcomes, denoted by y1 and y2). Our aim was to use the eight features to predict each of the two responses. More specifically:
 
X1 Relative Compactness
X2 Surface Area
X3 Wall Area
X4 Roof Area
X5 Overall Height
X6 Orientation
X7 Glazing Area
X8 Glazing Area Distribution
 
y1 Heating Load
y2 Cooling Load
 
NOTE:
 
Feature names were changed to facilitate human readability.
 
Upon completion of our regression analysis, we made some interesting discoveries and gained insights into the relationship between the features and responses in the dataset. We also arrived at conclusions that could possibly impact future architectural designs, or at least, be of use to those faced with similar considerations and decisions.
 
Relationship between heating load & relative compactness
 
View project here.

Spread the love
joaquinacosta

You must be logged in to post a comment.