Enhancing Zero-Energy Building Operations for ESG: Accurate Solar Power Prediction through Automatic Machine Learning

Solar power systems, such as photovoltaic (PV) have become a necessary feature of zero-energy buildings because efficient building design and construction materials alone are not sufficient to meet the building’s energy consumption needs. However, solar generation is subject fluctuations based on weather conditions, these higher than other renewable sources. This phenomenon has emphasized importance predicting through forecasting. In this paper, an Automatic Machine Learning (AML)-based method proposed create multiple prediction models data. Then, best model predict daily selected from models. The data used in study was obtained actual system installed building, while open provided by Korea Meteorological Administration. addition, To verify validity method, ideal with high accuracy but difficult apply comparison relatively low suitable for application were created. performance compared created method. Based validation process, approach shows 5–10% accuracies model.