An effective control of air handling unit (AHU) systems is crucial not only for managing the energy consumption of buildings but ensuring indoor thermal comfort for occupants. Although the initial control schema of AHU is appropriate at installation and testing, it is frequently necessary to adjust the control variables due to the changing thermal response of the building envelope and space usage. This paper presents a novel optimization process for the control parameters of old AHU systems in existing commercial buildings without system downtime and massive operational data. First, calibrating the building and system simulator with limited system operation data and unknown building parameters can provide identical responses to the system operation with the Hooke–Jeeves algorithm during the cooling season. The deep deterministic policy gradient algorithm is employed to determine the optimal control parameters for the valve opening position of the cooling coil within less than three hours of training based on the calibrated simulator. By using actual implementations with the developed optimal control variables for an old AHU in a real building, the proposed auto-tuned PID control in the simulator and with machine learning improves thermal environments with a steady room temperature (23.5 ± 0.5 °C) by 97% in occupied periods. It is also proved that this can reduce cooling energy consumption by up to 13.71% on a daily average. The successful AHU controller can improve not only the stability of AHU systems but the efficiency of a building’s energy use and indoor thermal comfort.

Although the accuracy of short-term prediction of building-integrated photovoltaics is essential to making an optimal decision on the management of the generated electricity, the weather forecasting service in many countries provides insufficient features for improving the prediction accuracy of the photovoltaics power output. This study suggests a machine learning model incorporated with feature engineering to improve the prediction performance of day-ahead hourly power outputs using a simple weather forecast service. A new synthetic feature, the modified sky condition, is derived to infer onsite sky condition and solar irradiation, which is not supported by the typical weather forecasting services. It evaluated the prediction performance with different training and hyper-parameter conditions for 60 days. By using the derived modified sky condition, the model outperformed other predictor configurations in most daily sky conditions; particularly, the accuracy improved by more than 50% on overcast days compared to when it used the original weather forecasting service data. The result demonstrates the feasibility and ability of the model to enable more efficient energy management of building-integrated photovoltaic power output in buildings without an onsite weather station, thus contributing toward the optimized dispatch of the integrated electricity energy storage system and other distributed energy resources.

This study proposes an occupant-centric control strategy for residential heating systems, aiming to enhance thermal comfort and reduce energy consumption. A sensor station utilizing a frequency-modulated continuous wave radar sensor was developed to detect occupancy and infer activities within residential spaces. By analyzing field measurement data, schedules for occupancy and activities were established. These schedules were then used to implement a variable control strategy for the hydronic radiant heating system, adjusting its operating characteristics based on the identified activities. The proposed control strategy, which includes resetting the indoor set temperature during unoccupied periods and adjusting it during sleep to account for changes in metabolic rate and clothing insulation, resulted in significant energy savings. Compared to continuous operation, the hydronic radiant heating system’s energy consumption was reduced by approximately 21% on peak load days and up to 34% over three winter months. This study demonstrates the potential of occupant-centric control for achieving substantial energy savings in residential buildings while maintaining occupant thermal comfort.

The energy used in buildings accounts for approximately 30% of the total energy consumption worldwide. HVAC (Heating, Ventilation, and Air Conditioning) systems are essential for creating indoor environments tailored to the building's purpose and maintaining the occupants comfort. However, in commercial buildings, HVAC systems consume between 30% and 50% of the building's total energy usage. Therefore, many studies aim to reduce this energy consumption. This study focuses on Automated Fault Detection and Diagnosis (AFDD), which can detect and diagnose issues in HVAC systems early, whether due to faults or aging, to reduce wasted energy. Recent trends in FDD research reveal a focus on data-driven approaches that align with AI or automatic control keywords, evaluating or enhancing fault diagnosis performance using machine learning techniques. In this study, we developed an FDD module using an Artificial Neural Network (ANN) model, known for its high predictive accuracy and capability to handle high-dimensional data. We analyzed which hyperparameters need to be optimized to improve diagnostic performance and the extent of performance improvement achieved through optimization. As a results, by analyzing the optimal performance through adjustments of hyperparameters such as number of hidden layers and train function of the ANN, we were able to develop an AFDD module with classification performance of over 96%.