Optimization of energy-saving renovation technology for existing buildings in a hot summer and cold winter area

Abstract

Retrofitting existing buildings significantly improves indoor thermal comfort and reduces building energy consumption and greenhouse gas emissions. The optimal combination of energy-saving technologies can improve the energy performance of a specific building. The effective energy-saving renovation of existing buildings is vital for improving the poor indoor comfort and high building energy consumption caused by the inadequate thermal performance of the external enclosure structure. This study proposed a new multi-objective optimization model based on Latin hypercube sampling (LHS). It combines a genetic algorithm (GA) with an artificial neural network (ANN) to evaluate and optimize the technology used for retrofitting projects, aiming to provide solutions for the energy-saving renovation of existing buildings. This study selected an old building in a hot-summer and cold-winter area for the retrofitting project, aiming to optimize indoor comfort, building energy consumption, and retrofitting cost. The proposed model was used to determine the optimum energy-saving technology combinations suitable for the building. The results showed that the optimized model could be used to explore conflicting objectives and determine the Pareto front when retrofitting existing buildings. Subsequently, the optimal technology combinations included using energy-efficient PVC Low-E double-glazed windows (5+6A+5) and XPS insulation with a thickness of 0.315m for the roof and external walls.