| Title |
A Study on the Development of Decision Support Tools Based on Simulation Using Machine Learning to Improve Energy Performance of Urban Rail Stations |
| Authors |
신승권(Seung-Kwon Shin) ; 송한솔(Han-Sol Song) |
| DOI |
https://doi.org/10.5370/KIEE.2023.72.10.1275 |
| Keywords |
Urban rail station; Machine learning; Multiple regression analysis; Energy performance simulation |
| Abstract |
According to the "Roadmap for Zero Energy in Urban rail Buildings", the goal is to promote zero energy building certification for all urban rail stations starting in 2025. However, it is not realistic to evaluate urban rail stations with existing evaluation tools.
Therefore, this study developed a decision support tool to achieve ZEB rating. The research methodology is to perform energy simulation for three urban rail stations, and then calibrate the energy simulation model by comparing the results with the actual energy usage. Multiple regression analysis was performed with the calibrated model to build a prediction model for energy usage.
The reliability of the model was verified through regression performance evaluation indicators. Finally, a web-based visualization dashboard on energy usage was developed. The visualization dashboard developed through this study provides a basis for decision-making for improving the energy performance of urban rail stations and obtaining ZEB rating |