Multi-objective optimization of building energy performance and indoor thermal comfort by combining artificial neural networks and metaheuristic algorithms

During the last few years, multi-objective optimization processes have become one of main challenges for energy efficiency in buildings. In this work, a new efficient method, based on Building Performance Optimization (BPO) technique, has been developed to improve indoor thermal comfort and performance residential buildings, i.e. Moroccan ground floor + first (GFFF) house located Marrakech region (5th climatic zone according Thermal Code Morocco). The most influential design variables well explored order find optimal trade-off between these two objectives. Indeed, technique is integration Artificial Neural Networks (ANNs), particular Multilayer Feedforward (MFNN), coupled with commonly used metaheuristic algorithms, Non-dominated Sorting Genetic Algorithm (NSGA-II), Multi-Objective Particle Swarm (MOPSO) (MOGA), minimize computation time as much possible. TRNSYS software was establish various dynamic simulations required create database, from which ANNs were able set up their learning. results show that methodology being successfully, leading different proposed solutions terms building envelope design. However, only using MOPSO are finally retained, they shown greatest desired compared others. Thus, needs, particularly those heating cooling, significantly reduced 74.52% total, while improving by 4.32% base Finally, we strongly recommend actors field, including designers, engineers, architects, engineering offices, etc., when several objectives need be contrasted simultaneously considering variables.