Yu-Wei Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu-Wei Fan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Xin-Rong Zhang
Peking University
2 shared publications - Yi-Zhou Wang
Department of Energy and Resources Engineering, School of Mechanics and Engineering Science, Peking University, Beijing 100871, China
2 shared publications - Jian-Guo Yang
Jingkelun Refrigeration Equipment Co., Ltd., Beijing 101302, China
1 shared publication - Jie-Ru Li
Ordos Research Institute of Energy, Peking University, Ordos 017000, China
1 shared publication - Xiao-Long Li
Jingkelun Refrigeration Equipment Co., Ltd., Beijing 101302, China
1 shared publication - Xiao-Yu Xie
Department of Energy and Resources Engineering, School of Mechanics and Engineering Science, Peking University, Beijing 100871, China
1 shared publication
Latest Publications
- Open Access
A Cluster- and Temperature-Aware Auto-Ensemble Model for Airport Cooling Load Forecasting
Accurate cooling load forecasting supports energy-efficient operation in large public buildings such as airports. Cooling load time series are often nonlinear and temporally dependent, with frequent operating condition changes and pronounced thermal inertia, which limits the reliability of single-model forecasting. This study proposes a cluster- and temperature-aware auto-ensemble model (CATS-Ens) for short- and long-term cooling load prediction. CATS-Ens learns condition-dependent model contributions within temperature-based operating intervals and distinct load regimes, enabling collaborative prediction across complementary experts and avoiding reliance on a single globally optimal predictor. The proposed model is evaluated on a real-world hourly cooling load dataset collected from an airport terminal. Results show that CATS-Ens achieves consistently better performance than representative baselines under multiple metrics, including MAE, RMSE, MAPE, sMAPE, and . Compared with the best individual baseline, CATS-Ens reduces MAE by 8.5%, RMSE by 8.4%, MAPE by 12.6%, and sMAPE by 7.1%, with an of 0.967. The model maintains stable accuracy under varying operating conditions and alleviates false-positive predictions during zero-load and low-load periods, demonstrating its practical value for cooling load forecasting in complex building energy systems.Open AccessA Cluster- and Temperature-Aware Auto-Ensemble Model for Airport Cooling Load Forecasting
Accurate cooling load forecasting supports energy-efficient operation in large public buildings such as airports. Cooling load time series are often nonlinear and temporally dependent, with frequent operating condition changes and pronounced thermal inertia, which limits the reliability of single-model forecasting. This study proposes a cluster- and temperature-aware auto-ensemble model (CATS-Ens) for short- and long-term cooling load prediction. CATS-Ens learns condition-dependent model contributions within temperature-based operating intervals and distinct load regimes, enabling collaborative prediction across complementary experts and avoiding reliance on a single globally optimal predictor. The proposed model is evaluated on a real-world hourly cooling load dataset collected from an airport terminal. Results show that CATS-Ens achieves consistently better performance than representative baselines under multiple metrics, including MAE, RMSE, MAPE, sMAPE, and . Compared with the best individual baseline, CATS-Ens reduces MAE by 8.5%, RMSE by 8.4%, MAPE by 12.6%, and sMAPE by 7.1%, with an of 0.967. The model maintains stable accuracy under varying operating conditions and alleviates false-positive predictions during zero-load and low-load periods, demonstrating its practical value for cooling load forecasting in complex building energy systems. - Open Access
Experimental Validation of a Novel CO2 Refrigeration System for Cold Storage: Achieving Energy Efficiency and Carbon Emission Reductions
To address the high energy consumption and carbon emissions associated with cold storage operations, a novel refrigeration system is proposed, which utilizes the natural refrigerant CO2 and integrates an innovative control strategy. Experimental validations were conducted in Changsha (a subtropical monsoon climate) and Changchun (a continental monsoon climate), which are two regions representing typical climatic zones in China, to assess the system’s energy-saving potential, temperature stability, and environmental impacts with the total equivalent warming impact and life cycle carbon performance methods. For Changchun, the total equivalent warming impact reached 78.3 kg CO2e/kg, reflecting reductions of 99.5% in direct emissions and 58.6% in indirect emissions compared with R410A systems, as mentioned in the reference. The life cycle carbon performance was reduced by 85.1% and 72.2% compared with the two experiment cases, with indirect emissions from energy consumption comprising the largest share. The system maintained exceptional temperature stability, with vertical-layer variations remaining under 1 °C. These findings demonstrate this system’s adaptability to achieve energy and emission reductions across diverse climates, providing a sustainable framework for future cold storage design aligned with global carbon neutrality goals.
Open AccessExperimental Validation of a Novel CO2 Refrigeration System for Cold Storage: Achieving Energy Efficiency and Carbon Emission Reductions
To address the high energy consumption and carbon emissions associated with cold storage operations, a novel refrigeration system is proposed, which utilizes the natural refrigerant CO2 and integrates an innovative control strategy. Experimental validations were conducted in Changsha (a subtropical monsoon climate) and Changchun (a continental monsoon climate), which are two regions representing typical climatic zones in China, to assess the system’s energy-saving potential, temperature stability, and environmental impacts with the total equivalent warming impact and life cycle carbon performance methods. For Changchun, the total equivalent warming impact reached 78.3 kg CO2e/kg, reflecting reductions of 99.5% in direct emissions and 58.6% in indirect emissions compared with R410A systems, as mentioned in the reference. The life cycle carbon performance was reduced by 85.1% and 72.2% compared with the two experiment cases, with indirect emissions from energy consumption comprising the largest share. The system maintained exceptional temperature stability, with vertical-layer variations remaining under 1 °C. These findings demonstrate this system’s adaptability to achieve energy and emission reductions across diverse climates, providing a sustainable framework for future cold storage design aligned with global carbon neutrality goals.