Ruijun Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ruijun Zhang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Xuyang Zhong
School of Architecture and Urban Planning, Chongqing University, Chongqing 400045, China
2 shared publications - Zhiang Zhang
Department of Architecture and Built Environment, University of Nottingham Ningbo China, Ningbo 315100, China
2 shared publications - Chenlu Zhang
Center for Building Performance and Diagnostics, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA
1 shared publication - Wei Wu
School of Energy and Environment City University of Hong Kong Hong Kong China
1 shared publication
Latest Publications
- Open Access
Estimating Space-Cooling Energy Consumption and Indoor PM2.5 Exposure across Hong Kong Using a City-Representative Housing Stock Model
High-quality data on building energy use and indoor pollution are critical to supporting government efforts to reduce carbon emissions and improve the population’s health. This study describes the development of a city-representative housing stock model used for estimating space-cooling energy use and indoor PM2.5 exposure across the Hong Kong housing stock. Archetypes representative of Hong Kong dwellings were developed based on geographically-referenced housing databases. Simulations of unique combinations of archetype, occupation, and environment were run using EnergyPlus, estimating the annual space-cooling energy consumption and annual average PM2.5 exposure concentrations under both non-retrofit and retrofit scenarios. Results show that modern village houses and top-floor flats in high-rise residential buildings, on average, used 19% more space-cooling energy than other archetypes. Dwellings in urban areas had lower exposure to outdoor-sourced PM2.5 and higher exposure to indoor-sourced PM2.5 compared to those in rural areas. The percentage decrease in space-cooling energy consumption caused by energy efficiency retrofits, including external wall insulation, low-e windows, and airtightening, varied significantly based on archetype. The implementation of external wall insulation in the housing stock led to an average decrease of 3.5% in indoor PM2.5 exposure, whilst airtightening and low-e windows resulted in 7.9% and 0.2% average increases in exposure, respectively.
Open AccessEstimating Space-Cooling Energy Consumption and Indoor PM2.5 Exposure across Hong Kong Using a City-Representative Housing Stock Model
High-quality data on building energy use and indoor pollution are critical to supporting government efforts to reduce carbon emissions and improve the population’s health. This study describes the development of a city-representative housing stock model used for estimating space-cooling energy use and indoor PM2.5 exposure across the Hong Kong housing stock. Archetypes representative of Hong Kong dwellings were developed based on geographically-referenced housing databases. Simulations of unique combinations of archetype, occupation, and environment were run using EnergyPlus, estimating the annual space-cooling energy consumption and annual average PM2.5 exposure concentrations under both non-retrofit and retrofit scenarios. Results show that modern village houses and top-floor flats in high-rise residential buildings, on average, used 19% more space-cooling energy than other archetypes. Dwellings in urban areas had lower exposure to outdoor-sourced PM2.5 and higher exposure to indoor-sourced PM2.5 compared to those in rural areas. The percentage decrease in space-cooling energy consumption caused by energy efficiency retrofits, including external wall insulation, low-e windows, and airtightening, varied significantly based on archetype. The implementation of external wall insulation in the housing stock led to an average decrease of 3.5% in indoor PM2.5 exposure, whilst airtightening and low-e windows resulted in 7.9% and 0.2% average increases in exposure, respectively.
- Open Access
End-to-End Deep Reinforcement Learning Control for HVAC Systems in Office Buildings
The heating, ventilation, and air conditioning (HVAC) system is a major energy consumer in office buildings, and its operation is critical for indoor thermal comfort. While previous studies have indicated that reinforcement learning control can improve HVAC energy efficiency, they did not provide enough information about end-to-end control (i.e., from raw observations to ready-to-implement control signals) for centralized HVAC systems in multizone buildings due to the limitations of reinforcement learning methods or the test buildings being single zones with independent HVAC systems. This study developed a model-free end-to-end dynamic HVAC control method based on a recently proposed deep reinforcement learning framework to control the centralized HVAC system of a multizone office building. By using the deep neural network, the proposed control method could directly take measurable parameters, including weather and indoor environment conditions, as inputs and control indoor temperature setpoints at a supervisory level. In some test cases, the proposed control method could successfully learn a dynamic control policy to reduce HVAC energy consumption by 12.8% compared with the baseline case using conventional control methods, without compromising thermal comfort. However, an over-fitting problem was noted, indicating that future work should first focus on the generalization of deep reinforcement learning.
Open AccessEnd-to-End Deep Reinforcement Learning Control for HVAC Systems in Office Buildings
The heating, ventilation, and air conditioning (HVAC) system is a major energy consumer in office buildings, and its operation is critical for indoor thermal comfort. While previous studies have indicated that reinforcement learning control can improve HVAC energy efficiency, they did not provide enough information about end-to-end control (i.e., from raw observations to ready-to-implement control signals) for centralized HVAC systems in multizone buildings due to the limitations of reinforcement learning methods or the test buildings being single zones with independent HVAC systems. This study developed a model-free end-to-end dynamic HVAC control method based on a recently proposed deep reinforcement learning framework to control the centralized HVAC system of a multizone office building. By using the deep neural network, the proposed control method could directly take measurable parameters, including weather and indoor environment conditions, as inputs and control indoor temperature setpoints at a supervisory level. In some test cases, the proposed control method could successfully learn a dynamic control policy to reduce HVAC energy consumption by 12.8% compared with the baseline case using conventional control methods, without compromising thermal comfort. However, an over-fitting problem was noted, indicating that future work should first focus on the generalization of deep reinforcement learning.