Key points are not available for this paper at this time.
Detailed parametric analysis and measurements are required to reduce building energy usage while maintaining acceptable thermal conditions. This research suggested a system that combines Building Information Modeling (BIM), machine learning, and the non-dominated sorting genetic algorithm-II (NSGA II) to investigate the impact of building factors on energy usage and find the optimal design. A plugin is developed to receive sensor data and export all necessary information from BIM to MSSQL and Excel. The BIM model was imported to IDA Indoor Climate and Energy (IDA ICE) to execute an energy consumption simulation and then a pairwise test to produce the sample data set. To study the data set and develop a prediction model between building factors and energy usage, 11 machine learning algorithms are used. The best algorithm was Group Least Square Support Vector Machine (GLSSVM), later employed in NSGA II as the building energy consumption fitness function using Dynamo software. An NSGA II multi-objective optimization model is designed to reduce building energy consumption and optimize interior thermal comfort (measured by the predicted percentage of dissatisfied (PPD)). The Pareto front is calculated, and the optimum point approach is used to find the best combination of building envelope characteristics, HVAC setpoints, shading parameters, lighting, and air infiltration. The feasibility and effectiveness of the developed framework are demonstrated using a case study of an upper secondary school building in Norway; the results show that: (1) The GLSSVM has a unique capacity to forecast building energy use with high accuracy: R2 of 0.99, an RMSE of 1.2, MSE of 1.44, and MAE of 0.89; (2) Building energy consumption and thermal comfort may be successfully improved by the GLSSVM-NSGA II hybrid technique, which reduces energy consumption by 37.5% and increases thermal comfort by 33.5%, respectively.
Hosamo et al. (Wed,) studied this question.