THE IMPACT OF WINDOW CHARACTERISTICS ON GAS AND ELECTRIC COSTS IN EDUCATIONAL BUILDINGS: APPLICATION OF SUPPORT VECTOR MACHINES

Toward  green  educational  building  development,  windows  are  important  design elements  as  the  source  of  natural  lighting  and  heating  in  classrooms.  The  amount  of  natural lighting and net heating received by a classroom in a year depends on the school location, weather conditions,  as  well  as  the  window  orientation  and  size.  Schools  in  Iran  consume  a  considerable amount of energy which is mostly supplied using nonrenewable fossil fuel resources. This energy consumption can be reduced through a well-designed daylighting approach. In this paper, in order to  investigate  the  effects  of  window  characteristics  on  construction  and  operational  costs  of schools, by varying the Window-to-Wall Ratio (WWR) and window  orientation, 288 daylighting scenarios  are  generated  for  a  typical  standard  classroom  in  a  warm-dry  climatic  zone  in  central Iran.  The  DOE-2  software  is  utilized  to  estimate  annual  gas  and  electric  consumption,  for  the generated scenarios over a period of 50 years. Considering the operation and construction cost, the best window facing and optimal range of WWR in each orientation is determined for the studied standard classroom. The results of simulated daylighting scenarios are then used to train regression based Support Vector Machines (SVMs) in order to show the feasibility  of applying the Support Vector Regression (SVR) as an artificial intelligent system. The obtained results show that SVR as an  architectural  assistant  performs  well  and  the  SVR-based  predictor  can  rapidly,  easily  and accurately  predict  the  operational  and  construction  cost  of  a  classroom  just  by  determining  the window size and installation face.