Artificial intelligence (AI) technology has rapidly advanced and transformed the nature of scientific inquiry. The recent release large language model Chat Generative Pre-Trained Transformer (ChatGPT) attracted significant attention from public various industries. This study applied ChatGPT to autonomous building system operations, specifically coupling it with an EnergyPlus reference office simulation model. operational objective was minimize energy use systems, including four air-handling...

Performance gap between predicted and measured building energy use can be caused by simplifications assumptions introduced in the modeling process, uncertainties operation such as heating cooling setpoint temperature, operational hours, occupant behavior, heat generated from lights equipment, etc. In South Korea, efficiency certification system evaluates annual intensity (EUI, kwh/m2) using ECO2 developed Korean government that is based on ISO 52016 DIN V 18599. This study analyzes...

The Building Energy Efficiency Certification (BEEC) program is a crucial government policy aimed at reducing building energy consumption and greenhouse gas emissions in numerous countries, including South Korea. This study aims to evaluate the achievable BEEC level by designing typical with construction permit analyze appropriateness of awarded level. We collected 327 samples non-residential buildings from Korea's architectural administration system established reference models these...

Blind systems have been introduced to provide visual and thermal comfort, as well reduce energy use in buildings. A wide variety of such exist terms optical properties, location physical configuration. The current problem with blinds is that their operation not based on the dynamics room but static or manual control operated by occupants, although many studies recognized dynamic can far outperform control. One reason for lack it easy combine any possible optimization algorithm. Hence, this...

Indoor CO2 concentration is considered a metric of indoor air quality that affects the health occupants. In this study, hybrid model was developed for forecasting varying levels in residential apartment unit presence occupants by controlling ventilation rates heat recovery ventilator. model, mass balance equation single zone as white-box combined with Bayesian neural network (BNN) black box model. During learning process BNN estimated an aggregated unknown rate and transferred estimation to...

This paper addresses an application of the Kalman filter for estimating a time-varying process disturbance in building space. The means synthetic composite heat gains and losses caused by internal sources e.g., people, lights, equipment), airflows. It is difficult to measure quantify airflows due their dynamic nature time-lag impact on indoor environment. To address this issue, estimation method was used study. filtering well suited situations when state variables interest cannot be...

End-use consumption provides more detailed information than total and reveals the mechanism of energy flow through a given building. Specifically, for weather-sensitive end-uses, it enables prioritization selection heating cooling areas requiring investigation actions. One major barriers to acquiring such small- medium-sized buildings or low-income households is high cost related submetering maintenance. The end-use data, especially such-sized are national blind spot. In this study,...

This study introduces a hybrid model that combines physics and machine learning (ML) models to describe the behaviour of variable refrigerant flow (VRF) systems. The standalone ML was developed with identical data conditions for comparison between models. A Bayesian neural network (BNN) used both models, predictive abilities uncertainties were investigated. For experimental dataset, performances similar. example, performance showed mean absolute error 0.73 0.78 kW, respectively. However,...

With the increasing focus on low energy buildings and need to develop sustainable built environments, Building Energy Performance Simulation (BEPS) tools have been widely used. However, many issues remain when applying BEPS existing buildings. This paper presents that be solved for application of an office building. The selected building is with 33 stories above ground, six underground levels, a total floor area 91,898 m2. discussed in this are as follows: (1) grey data not ready simulation;...

It is important for South Korea to set a roadmap the reduction of greenhouse gas emissions keep pace with newly established target from United Nations Framework Convention on Climate Change. Building energy consumption major source nation’s emissions. Hence, there rising interest in developing reference buildings which can be used as simulator represent building stocks. The paper introduces development eleven models based national statistics. Input data preparation and model validation are...

This paper summarizes the recent post-occupancy evaluation (POE) method studies and latest literature reviews. According to research trends, data visualization of an occupant’s feedback is important perspective surveys through POE methods have provided a quick cost-effective approach for gathering analyzing feedback. Therefore, objective this study establish web-based building occupant survey system that incorporates new approaches based on geographic information (GIS) tool open-source...

This study reports the development of a Gaussian Process (GP) model based on BEMS data. The GP is data driven and requires few dominant inputs. It provides quick prediction with far less computation than whole building simulation tools (e.g. EnergyPlus). developed in this capable predicting behavior system (fan energy consumption). paper how authors model. In particular, addresses to deal outliers existing set. study, RANdom Sample Consensus (RANSAC) was selected for detecting from RANSAC...

Comprehensively monitoring indoor environmental quality (IEQ) parameters and their dynamic relations is essential to ensure improved productivity a healthy environment for building occupants. Although IEQ significantly influences working efficiency, studies addressing this aspect with researchers in institutes as the focal point are limited. Thus, study employed drill-down analyses, such floor-by-floor building-by-building examinations used an occupant survey approach evaluate conditions...

This study aims to support building energy policymaking for office buildings in South Korea through regression models by considering the global temperature rise. The key variables representing standards and codes are selected, their impact on annual consumption is simulated using EnergyPlus reference models. Then, simplified built basis of selected variables. prediction performance developed model forecasting each good, error negligible. An additional coefficient estimated address increased...

The building sector is responsible for more than one-third of total global energy consumption; hence, increasingly efficient use in this will contribute to achieving carbon neutrality. Most existing building-energy-benchmarking methods evaluate performance based on intensity; however, usage buildings varies with the seasons, and as such, approach renders evaluation cooling heating difficult. In study, an information gain-based temporal segmentation (IGTS) method was used identify seasonal...