Skip to content
Bowen Yang

Bowen Yang

Bowen is a postdoctoral researcher in the IDOBE group at the University of Alberta. His research focuses on building power demand prediction for energy efficiency and demand flexibility, using reliable and explainable artificial intelligence methods: probabilistic forecasting with Bayesian additive regression trees, hierarchical and transfer learning under data scarcity, and comparing deep learning and tree-based models for accuracy, interpretability and computational efficiency. His earlier MSc work at Concordia University predicted occupancy in residential buildings using machine learning.

Education

  • PhD in Building Engineering, University of Alberta
  • MSc in Building Engineering, Concordia University (2021)

Publications

Journal Articles

  • Yang, B., & Chen, Y. (2026). A hierarchy learning strategy for probabilistic power demand prediction for buildings. Building Simulation, 19(7), 1867-1889. https://doi.org/10.1007/s12273-026-1460-x
  • Yang, B., Ardakanian, O., Gül, M., & Chen, Y. (2026). A novel MSTL-BART method for probabilistic power demand prediction for residential buildings. Building Simulation, 19(4), 1109-1129. https://doi.org/10.1007/s12273-026-1402-7
  • Jordan, A., Yang, B., & Chen, Y. (2025). In-Situ Evaluation of a Fuel-Switching Heating System in Edmonton, Alberta, Canada: Lessons Learned. Journal of Building Physics. https://doi.org/10.1177/17442591251403223
  • Yang, B., Gül, M., & Chen, Y. (2025). Comparative analysis of deep learning and tree-based models in power demand prediction: Accuracy, interpretability, and computational efficiency. Journal of Building Physics, 49(1), 127-169. https://doi.org/10.1177/17442591251333144
  • Qu, W., Jordan, A., Yang, B., & Chen, Y. (2024). In Situ Performance Analysis of Hybrid Fuel Heating System in a Net-Zero Ready House. Sustainability, 16(3), 964. https://doi.org/10.3390/su16030964
  • Yang, B., Haghighat, F., Fung, B. C. M., & Panchabikesan, K. (2021). Season-based occupancy prediction in residential buildings using machine learning models. e-Prime – Advances in Electrical Engineering, Electronics and Energy, 1, 100003. https://doi.org/10.1016/j.prime.2021.100003

Conference Papers

  • Yang, B., & Chen, Y. (2026). A Hierarchy Learning Strategy for Probabilistic Prediction of Power Demand Under Data Scarcity. 2026 ASHRAE Winter Conference. https://doi.org/10.63044/w26yan80
  • Yang, B., Gül, M., & Chen, Y. (2025). Probabilistic Power Demand Forecasting Using Bayesian Additive Regression Trees in Residential Building. 2025 ASHRAE Winter Conference. https://doi.org/10.63044/w25yan119
  • Yang, B., Gül, M., & Chen, Y. (2024). Multi-Perspective Evaluations for Power Demand Prediction Models: Balancing Prediction Accuracy, Interpretability, and Computational Efficiency. eSim 2024: 13th Conference of IBPSA-Canada. https://publications.ibpsa.org/conference/paper/?id=esim2024_153
  • Yang, B., Chen, Y., Gül, M., Yu, H., & Shields, C. (2023). Ensemble transfer learning strategy in forecasting power consumption for residential buildings. Proceedings of Building Simulation 2023: 18th Conference of IBPSA. https://doi.org/10.26868/25222708.2023.1400

Technical Reports

  • Chen, Y., Yang, B., Jordan, A., & Shields, C. (2023). What Can Performance Monitoring Tell You About Your Home? Building Science Perspective (Alberta Building Envelope Council North and South), Fall 2023, 30-35. https://heyzine.com/flip-book/f44384eaa7.html

Thesis

Skip to content