Soolyeon Cho

This project is to develop optimal control algorithms of building Heating, Ventilating, and Air-Conditioning (HVAC) systems. There are many systems and components in HVAC systems that need to be optimally controlled for energy efficiency and human comfort. Artificial Intelligence (AI) algorithms are developed to predict future energy use, especially using Artificial Neural Network (ANN) modeling. Digital Twin technologies are utilized to test and verify the effectiveness of the optimal control algirithms. The optimal control algorithms are tested in four buildings both in South Korea and in the US.

This project is to develop optimal control algorithms to supply necessary energy efficiently to a smart city. The energy supplies are from various new and renewable energy resources, including solar PV, solar thermal, wind, geothermal, fuel cell, Energy Storage System (ESS), and Thermal Energy Storage (TES). The energy supply control algorithms will be developed based on the Artificial Intelligence (AI) technologies, which have capabilities of generating optimal control solutions at the time of energy demand. Among AI technologies, Recurrent Neural Network (RNN) are utilized with the application of Long Short Term Memory Network (LSTM). The energy demand and supply will be predicted using the RNN (LSTM) algorithms to optimally operate the energy systems in a smart city, which will result in energy savings and contribute to energy independence.

This research is to improve indoor environmental quality and develop energy optimization technologies for smart city living labs (public buildings). The objectives are 1) to improve the thermal comfort of occupants through the optimal control of the air flow and discharge temperature of the air conditioner installed in the actual target building and 2) to develop and apply optimal control algorithms based on artificial intelligence technologies.

This project is to develop the thermal load prediction models in buildings, which are based on Artificial Neural Network (ANN) technologies, for optimal control of the Multi-use, Multi-source Heat Pump (MMHP) systems. The performance prediction model of the MMHP systems will utilize renewable energy sources such as solar and geothermal as well as a conventional heat source (or air). A machine learning technology, Artificial Neural Network (ANN), will be used to develop load prediction models for both Air-source Heat Pump (ASHP) and MMHP systems. Finally, an automated optimization module will be developed for load prediction of ASHP and MMHP systems based on ANN technology.

This project is to develop optimal control algorithms and systems for Smart Envelope Packages (SEPs) that will be developed and implemented in old apartment complexes (20-30 years old) in South Korea.

The project team will gather one full year of data for the test of BCVTB platform from the EPA Admin-A building, including operational status data, energy consumption data, and weather conditions information. The BCVTB platform will be tested with an updated simulation model, which has been calibrated to the measured energy consumption data as well as building operating status data of the EPA Admin-A building. The project team will verify the effectiveness of the BCVTB in terms of commissioning process, Energy Conservation Measures (ECMs), and performance Measurement and Verification (M&V). A virtual BCVTB platform will be developed and tested for the City Hall building of Kyunggido using the data gathered in advance.

This project is to test and research the impact of ITC ceramic coatings applied to building construction materials. As the first phase of the project, the research team will conduct literature review on this topic, specifically looking for the cases where any ceramic coatings have been applied to building materials. The ceramic coatings have potential benefits as fire retardant and insulator. However, there is little evidence available for practitioners to use as reference at the time of applying these to building materials, especially concerned about fire ratings. The state-of-the-art of the ceramic coatings will be identified and precedents presented. The findings through the literature review will include 1) currently available commercial products (or building materials) that include ceramic coatings, 2) patents pending in the US, 3) state-of-the-art, problems, and issues that should be addressed for the testing of ceramic coatings, 4) potential risks/challenges and contingency plans for testing, and 5) detailed plan for the simulation modeling and experiment of ITC 100HT coating.

The research is to develop an advanced building controls platform that integrates simulation models. The platform will include the inter-connectivity with Building Automation System (BAS) and the Energy Management and Control Systems (EMCS). The purpose of this research is to achieve at least 30% energy savings in buildings through smart building management systems. Specifically, the scope of this research is to develop a technology that makes possible to measure and verify the performance of buildings in real-time basis, which in turn enables the commissioning process continuous.

The proposed research is 1) to analyze the monitored performance data from the case stydy building, 2) to develop simulation models (EnergyPlus & EQUEST), which are calibrated to the energy consumption data of the case study building, 3) to develop key commissioning parameters that can improve the energy performance of the case study building and that will be integrated in the Mini-BEMS platform, and 4) to develop algorithms of the BCVTB platform for the application of IPMVP Option-D.

This research is to create initial Energy Use Intensity (EUI) benchmarks by gathering data to measure, estimate, or model energy end uses in airport passenger terminals. These benchmarks will assist in managing energy usage and evaluating business decisions for replacing or retrofitting equipment and systems. EUI profiles will also be developed for energy end uses for several representative airport terminal