The performance of air conditioning systems deteriorate due to the natural aging and wear caused by operating the devices. This is termed “aging degradation,” and it results from a lack of appropriate maintenance which accelerates the degree of performance degradation. The performance degradation of an air conditioning system can cause problems such as increased energy consumption, deteriorated indoor heating environment, and shortened lifespan of air conditioning equipment. To prevent such problems, it is important to establish a long-term maintenance plan to recover degraded performance, such as predicting an appropriate maintenance time by identifying the real-time performance degradation rate based on a system’s operation data. In this study, the performance degradation rate, according to the operating time, was estimated using long-term operation data for devices constituting a heat source system, and the effect of performance degradation of the heat source system’s operation and energy consumption was reviewed using a simulation. The performance degradation rate of the target device was estimated by analyzing the variation trend of the calibration coefficient, which was calculated when the initial performance prediction model was calibrated through operating data. Using this approach, it was confirmed that the annual performance degradation rate was 1.0–1.4% for the heat source equipment, 0.4–1.2% for the cooling towers, and 0.8–1.3% for the pumps. In addition, a heat source system energy simulation calculated the 15-year performance degradation of the heat source equipment to be 34–52% and 7–19% for both the cooling towers and pumps. Due to the equipment performance deterioration, the number of operating heat source equipment and cooling tower fans, and the pump flow rate gradually increased every year, thus accelerating the performance deterioration even further. As a result, energy consumption in the 15th year increased by approximately 41% compared with the initial energy consumption.

Many countries adopt a time-of-use (TOU) rate system, in which electricity rates vary by season and time of day, to reduce power usage during peak power consumption hours. South Korea offers a TOU rate plan that depends on the electricity usage of a building and its contracted power; in this plan, the electricity rate reaches up to 300% depending on the time of day. Hence, electrically powered variable refrigerant flow (VRF) systems are increasingly being installed in small- and medium-sized buildings requiring individual cooling and heating operations. This study aims to develop a new control algorithm to reduce electricity consumption and electricity rates for cooling and heating by VRF systems in university buildings adopting the TOU rate plan and apply it to actual buildings to verify the reduction effect. The proposed control algorithm primarily consists of a module that controls the refrigerant evaporation temperature (cooling) and high pressure (heating) according to the indoor heat load and a module that controls the indoor set temperature based on the hourly electricity rate. The developed algorithm was installed in the controller of a VRF system installed in an actual university building and the annual effect was verified using the method proposed by the International Performance Measurement and Verification Protocol. As a result, power consumption was reduced by 17.8% for heating and 4.0% for cooling due to the application of the control algorithm, and the electricity rates reduced by 19.2% and 7.3%, respectively.

This study presents the development and field application of a DNN-based control algorithm for optimizing cooling water temperature to reduce cooling energy consumption in an office building. The DNN prediction model was trained using actual operating data and validated in accordance with ASHRAE Guideline 14. An optimization algorithm was then developed to determine the cooling water temperature that minimizes the operating cost of the heat source system, and the algorithm was deployed in the building's HVAC system. Using 2022 data as the baseline, the algorithm was applied during the 2023 and 2024 cooling seasons, resulting in operating cost reductions of 26.4% and 19.5%, respectively. The findings, based on three years of operational data, demonstrate the effectiveness of the proposed algorithm in achieving energy cost savings under real building conditions.