Genetic-algorithm based approach to optimize building envelope design for residential buildings

Abstract

A simulation–optimization tool is developed and applied to optimize building shape and building envelope features. The simulation–optimization tool couples a genetic algorithm to a building energy simulation engine to select optimal values of a comprehensive list of parameters associated with the envelope to minimize energy use for residential buildings. Different building shapes were investigated as part of the envelope optimization, including rectangle, L, T, cross, U, H, and trapezoid. Moreover, building envelope features were considered in the optimization analysis including wall and roof constructions, foundation types, insulation levels, and window types and areas. The results of the optimization indicate rectangular and trapezoidal shaped buildings consistently have the best performance (lowest life-cycle cost) across five different climates. It was also found that rectangle and trapezoid exhibit the least variability from best to worst within the shape.