A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Research on applying machine learning models to predict the electricity generation capacity of rooftop solar energy systems on buildings
During the current process of constructing and developing infrastructure systems, constructing energy-efficient buildings is highly advantageous thanks to the readily available resource such as solar energy—abundant renewable energy source that can be harnessed to develop green building projects. However, buildings using solar energy systems face some challenges such as high initial investment costs and longer than expected payback periods, indicating the necessity of solar electricity generation capacity prediction tools during the building design and operation stages. To address this issue, this paper proposes machine learning models to predict the power generation capacity of rooftop solar energy systems in building construction, including regression models, ensemble models, and artificial neural network models. The study utilizes a real dataset in Ho Chi Minh City, Vietnam containing weather data and data on rooftop solar energy systems that were recorded every 30 min. The test results show that the gradient boosting regressor (GBR) model achieves the highest accuracy, with an MAE of 0.637514 and RMSE of 0.566153. The study concludes with a proposal for an ensemble machine learning model that can accurately predict the electricity generation capacity of rooftop solar energy systems on buildings.
Research on applying machine learning models to predict the electricity generation capacity of rooftop solar energy systems on buildings
During the current process of constructing and developing infrastructure systems, constructing energy-efficient buildings is highly advantageous thanks to the readily available resource such as solar energy—abundant renewable energy source that can be harnessed to develop green building projects. However, buildings using solar energy systems face some challenges such as high initial investment costs and longer than expected payback periods, indicating the necessity of solar electricity generation capacity prediction tools during the building design and operation stages. To address this issue, this paper proposes machine learning models to predict the power generation capacity of rooftop solar energy systems in building construction, including regression models, ensemble models, and artificial neural network models. The study utilizes a real dataset in Ho Chi Minh City, Vietnam containing weather data and data on rooftop solar energy systems that were recorded every 30 min. The test results show that the gradient boosting regressor (GBR) model achieves the highest accuracy, with an MAE of 0.637514 and RMSE of 0.566153. The study concludes with a proposal for an ensemble machine learning model that can accurately predict the electricity generation capacity of rooftop solar energy systems on buildings.
Research on applying machine learning models to predict the electricity generation capacity of rooftop solar energy systems on buildings
Asian J Civ Eng
Pham, Vu Hong Son (author) / Tran, Hoang Duy (author)
Asian Journal of Civil Engineering ; 24 ; 3413-3423
2023-12-01
11 pages
Article (Journal)
Electronic Resource
English
Evaluation of rooftop photovoltaic electricity generation systems for establishing a green campus
| Taylor & Francis Verlag | 2015
| Elsevier | 2024
Research on applying machine learning models to predict and assess return on assets (ROA)
| Springer Verlag | 2024