Sustainable Building Design: A Challenge at the Intersection of Machine Learning and Design Optimization

摘要: Residential and commercial buildings are responsible for about 40% of primary energy consumption in the United States, hence improving their efficiency could have important sustainability benefits. The design a building has tremendous effect on its profile, recently there been an increased interest developing optimization methods that support high performance buildings. Previous approaches either based simulation or training accurate predictive model is queried during optimization. We propose method more tightly integrates machine learning components, by employing active In particular, we use Gaussian Process (GP) prediction multi-objective genetic algorithm NSGA-II develop comprehensive publicly available benchmark evaluate 5 our dataset, show GP competitive, addition to being well-suited setting. compare approach against 2-stage Our results produces solutions at Pareto frontier compared other two approaches, while using only fraction simulations time.