Building Energy & Optimal Control

Building (Plant systems) performance and diagnostics

• The purpose of this study is to analyze building energy performance considering both passive and active (including new & renewable energy sources) systems, and to perform an economic feasibility study dealing with energy consumption optimization of the building (plant) systems considering total life cycle cost with national energy energy policy.

• This study deals with building energy simulation (EnergyPlus, Design builder)-based performance analysis, development of SW evaluation module and energy decision support system for built environment.

A study on IoT based building facility control, intelligent building energy management system, and MPC based real-time energy optimal control method.

• This study aims to develop core technologies for Deep Learning MPC (Deep Energy MPC, Model Predictive Control) that combines artificial intelligence (AI) and energy big data for optimal real-time operational control of grid-connected buildings and building groups.

• It aims to achieve 'real-time optimization' and develop a model that can predict stochastic energy patterns more accurately considering the characteristics of the buildings, facilities and residents. It is expected to optimize building energy performance and control through machine learning, heuristic rule-based energy evaluation, and MPC-based scheduling for buildings.

• This research presents GIS & bigdata based building energy analysis framework and analysis tool. Results of this work can help decision support for energy policy-making as well as deliver priceless insights from the huge amount of energy big data.

• This study presents GIS-based Korean energy DB systems combining dynamic and static data, producing energy prediction results by machine learning, and supporting visualized web applications.

• This study proposes a DQN-based real-time feedback control scheme to advance simulation automation using EnergyPlus and predict control strategies considering building energy consumption and thermal comfort.

• This study proposes a probabilistic-based optimization method to integrate thermal comfort in energy-efficient buildings. This study produces proper schedule and maintenance methods including various types of HVAC operations, occupant rates, and clothing types for thermal comfort optimization.