On the optimization of building energy, material, and economic management using soft computing

Abstract

This paper provides energy and economic analysis relevant to the cooling season in building enclosures. For a whole year, an Energy Plus thermal transfer model has been created and simulated. Simulations were made from the cities in five different areas of climate in China using weather data files. Energy savings were done from natural cold (e.g., outdoor air), and electricity reductions were performed from air-conditioning electricity devices. This research has investigated the relationship between the cost and building energy while finding a strong and positive correlation. This study has used the Artificial Intelligence (AI) model as Extreme Learning Machine (ELM) and Teaching Learning Based Optimization (TLBO) to calculate the accurate measurement. Three regression models as Pearson correlation coefficient (r), root mean square (RMSE), and coefficient of determination (R2) was used to calculate the results. Following the results of (R2) and RMSE, ELM has shown its higher performance in predicting the strength, energy, and cost of building materials. Based on the simulation results, for office buildings situated in cold areas, the energy savings resulting from phase change materials (PCM) are more prevalent. The test findings demonstrate that the energy savings from PCM applications for the cool area and hot summers and cold winter office buildings were increased. Simple payback time indicated that PCMBs in inhabited buildings could be used costeffectively in a mild temperature environment.