Seoul National University · Engineering
Professor Cheol Soo Park's research lab specializes in intelligent building energy systems, focusing on the integration of machine learning, reinforcement learning, and physics-informed modeling to optimize energy efficiency in commercial buildings. The lab develops advanced data-driven and hybrid models—such as deep reinforcement learning, transfer learning, and artificial neural networks—for real-time control and inverse modeling of HVAC systems, building envelope properties, and energy consumption. Their work bridges simulation, real-world data, and predictive analytics to improve building performance, indoor air quality, and sustainability. The lab also explores novel sensing and classification techniques, such as Raman spectroscopy and kernel optimization, for health-related applications in smart environments.
Figures are computed from collected data and may differ slightly.
A deep Q-network (DQN) was applied for model-free optimal control balancing between different HVAC systems. The DQN was coupled to a reference office building: an EnergyPlus simulation model provided by the U.S. Department of Energy. The building was air-conditioned with four air-handling units (AHUs), two electric chillers, a cooling tower, and two pumps. EnergyPlus simulation results for eleven days (July 1–11) and three subsequent days (July 12–14) were used to improve the DQN policy and test
This article compares two modeling approaches for optimal operation of a turbo chiller installed in an office building: (1) a machine learning model developed with artificial neural network (ANN) and (2) a hybrid machine learning model developed with the ANN model and available physical knowledge of the chiller. Before developing the ANN model of the chiller, the authors used Gaussian mixture model in order to check the validity of measured data. Then, the hybrid model was developed by combining
Nematic circular drops of the liquid crystals 5CB and MBBA suspended in their isotropic phases exhibit an electric-field-induced deformation into an elliptical shape extended normal to the applied field which is many times larger than that found in nonliquid crystal systems, a result of the low nematic-isotropic interfacial tension. Isotropic drops suspended in a nematic phase also exhibit large deformation, but of opposite sign. In both cases the deformation is proportional to the applied field
This study proposes a transfer learning (TL)-based inverse modelling to identify unknown building properties. This study examines the transfer from virtual buildings to existing buildings, especially for identifying wall U-value, HVAC efficiency and lighting power density (LPD). For this purpose, synthetic data were generated from simulation results of sampled EnergyPlus models, and then we developed artificial neural network (ANN) models using this data. By adopting TL, the ANN models were tran
In order to detect minute amounts of glucose in diluted urine, we applied the Raman spectroscopy method. To simulate abnormal diluted urine in a toilet bowl, we diluted normal urine ten-fold with water and added glucose up to 8 mg dl(-1). Data were collected using a low-resolution Raman spectrometer that was preprocessed with the optimizing kernel method. We also applied the neural network algorithm to classify abnormal and normal urine samples according to their glucose concentrations. The kern
The purpose of the present study was to investigate the relevance of building thermal performance and characteristics to building energy consumption. This paper reports an energy analysis of 4625 office buildings in Seoul, South Korea, using data from the Korean national building energy database and architectural database. The following four research questions were investigated: (1) Do old buildings consume more energy than new ones? (2) Have strict prescriptive building energy codes contributed
Although it is widely acknowledged that reinforcement learning (RL) can be beneficial for building control, many RL-based control actions remain unexplainable in the daily practice of facility managers. This paper reports a rule reduction framework using explainable RL to enhance the practicality of the control strategy. First, deep Q-learning was applied to explore the optimal control strategies of a parallel cooling system (ice-based thermal system + geothermal heat pump system) of an existing
Existing studies have treated variable refrigerant flow (VRF) control as a local control problem where control variables are determined using only local state information. This study investigates an integrated VRF control in which the VRF control actions are determined based on not only local information but also the dynamics of the room it serves. For this purpose, two artificial neural network simulation models were developed: one to predict indoor air temperature of the room and the other to
Open papers in the app to read, cite, and organize with AI.
