presented
a novel multi-objective genetic algorithm model using
NSGA-II to optimize the energy efficiency and thermal comfort in
buildings. Magnier and Haghighat [19] used TRNSYS simulations,
the multi-objective genetic algorithm, and the artificial neural network
to optimize the building design. In another work, Wright
et al. [20] investigated the application of a multi-objective genetic
algorithm search method in the identification of the optimum payoff
characteristic between the energy cost of a building and the
occupant thermal discomfort. In addition, Lu et al. [21] presented
a comparison study on two design optimization methods for
renewable energy systems in buildings, including a single objective
genetic algorithm and a multi-objectives non-dominated sorting
genetic algorithm (NSGA-II). Recently, Hamdy et al. [22] proposed
a modified multi-objective optimization approach based on
the genetic algorithm coupled with IDA ICE building performance
simulation program to minimize the carbon dioxide equivalent
emissions and the investment cost of a two-story house and its
HVAC system. Karaguzel et al. [23] integrated the whole building
energy simulation program, EnergyPlus, with GenOpt tool to minimize
the life cycle cost of a reference commercial office building
model.