Data-driven performance analysis of a residential building applying artificial neural network (ANN) and multi-objective genetic algorithm (GA)

Residential buildings account for nearly 60% of electrical energy consumption in hot climates as in Kuwait. As a result, this study proposes a reliable multi-objective model to obtain the optimal design for a typical residential Kuwaiti building by integrating an Artificial Neural Network (ANN) model with Genetic Algorithm (GA) optimization method. The ANN model was investigated and verified using the results of building performance simulations applying EnergyPlus software. The effects of sample size of dataset on performance of ANN were evaluated. The final optimal building design was optimized using the GA method after ensuring the convergence of the final ANN model. Several design and operation parameters were considered as decision variables, while cooling energy consumption, discomfort hours, and equivalent carbon emissions were selected as objective functions. In addition, sensitivity analysis was conducted to evaluate the impacts of decision variables on objective functions. The sensitivity results indicated that insulation highly affect energy consumption and carbon emission, while cooling setpoint played a key role in discomfort hours. Furthermore, Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method was applied for decision-making among Pareto optimal solutions. The results showed that the optimal solution suggested by TOPSIS methods using ANN-based model provided a substantial reduction in energy consumption, discomfort hours, and carbon emission up to 39.3%, 62.8%, and 40.5% compared with the base case, respectively. It is recommended that further research be undertaken in considering uncertainty parameters on optimization process and applying the developed framework for building in different climate. [Display omitted] •An ANN based framework developed for residential building energy performance optimization.•Energy consumption, discomfort hours, and carbon emission optimized simultaneously.•Sensitivity analysis conducted for design and operation parameters.•TOPSIS method applied to suggest optimal point among Pareto front solutions.•Energy consumption, discomfort hours, and carbon emission reduced up to 39.3%, 62.8%, and 40.5%, respectively.