PV (photovoltaic) systems are receiving the spotlight in Korea due to the Renewable Energy 3020 Implementation Plan (RE3020), which has the goal of reaching 20% for the proportion of renewable energy generation by 2030. Accordingly, the actual performance evaluation of PV systems to achieve the RE3020 has become more important. PV efficiency is mainly determined by various weather conditions (e.g., solar radiation) that affect the power generation of PV systems. However, the efficiency is also affected by changes in module surface temperature. In particular, the efficiency decreases when the module surface temperature rises. That is, the actual PV efficiency falls short of the rated efficiency. The estimation of module surface temperature is critical for evaluating the actual performance of PV systems. Many studies have been conducted to calculate the surface temperature. However, most of the previous studies focused on calculations of current surface temperatures using current environment data, which means that the previous studies have limitations related to timestep. That is, there is a lack of predictive models that calculate the future surface temperatures by using the current measured data. Therefore, this study developed a predictive model using an ANN (artificial neural network) algorithm to determine the surface temperature of PV modules for a future period of time. Then, this study evaluated the actual performance (i.e., power generation) with the predicted surface temperatures.

In Korea apartment buildings, most energy is consumed as heating energy. In order to reduce heating energy in apartment buildings, it is required to reduce the amount of energy used in heating systems. Energy saving in heating systems can be achieved through operation and control based on efficient operation plans. The efficient operation plan of the heating system should be based on the predicted heating load. Thus, various methods have been developed for predicting heating loads. Recently, artificial intelligence techniques (e.g., ANN: artificial neural network) have been used to predict heating loads. The process for determination of input data variables is necessary to obtain the accuracy of predicted results using an ANN model. However, there is a lack of studies to evaluate the accuracy level of the predicted results caused by the selection and combination of input variables. There is a need to evaluate the performance of an ANN model for prediction of residential heating loads. Therefore, the purpose of this study is, for a residential building, to evaluate the accuracy levels of predicted heating loads using an ANN model with various combinations of input variables. To achieve the study purpose, each case was classified according to the combination of the input variables and the prediction results were analyzed. Through this, the worst, mean, and best were selected according to the predicted performance. In addition, an actual case was selected consisting of variables that can be measured in an actual building. The derived cv(RMSE) of each case resulted in a percentage value of 38.2% for the worst, 7.3% for the mean, 3.0% for the best, and 5.4% for the actual. The largest difference between the best and worst resulted in 33.2%, and thus the precision of the predicted heating loads was highly affected by the selection and combination of the input variables used for the ANN model.

Among the envelope components (e.g., walls, roofs, floors, and windows, etc.) affecting the cooling and heating load of buildings, windows are the most thermally vulnerable. Shading devices can minimize the thermal load on windows due to solar radiation and decrease radiation effects. However, the load changes due to convection and conduction should be considered. Therefore, when a shading device is applied to a window, control logic for thermal blocking and heat retention is necessary to prevent the load changes. In addition, by combining the opposite features of photovoltaic (PV) that require solar radiation and the shading device to block solar radiation, energy-saving and production can be achieved simultaneously. Therefore, this study minimized the thermal effects of windows using a movable shading device integrated with PV and evaluated the PV power generation. This study evaluated the effects on window heat transfer by applying artificial intelligence techniques, which have recently attracted attention, to system operation. To achieve this, artificial neural network (ANN)-based control logic was developed, and the control performance of the system was assessed using simulations. In ANN control, the window heat transfer was 86.3% lower in a cooling period and 9.7% lower in a heating period compared with that of a shading device fixed at 45°. Furthermore, the PV system produced 3.0 to 3.1% more electric power under optimal control during the cooling period.

Office cooling systems are controlled with on/off control according to typical occupancy patterns. During unoccupancy, the cooling systems remain switched off to reduce unnecessary energy consumption. During occupancy, however, the cooling systems are in operation to decrease the indoor air temperature, which is increased during unoccupancy, to the cooling set-point temperature. The time required to decrease the indoor air temperature to the cooling set-point temperature is defined as the “recovery time”. According to the recovery time, the indoor thermal comfort at the occupancy start time may worsen, and unnecessary energy may be consumed. Moreover, a cooling system capacity affects the recovery time and the energy consumption because the amount of heat that the cooling system can remove varies according to its size. Therefore, it is necessary to analyze the indoor thermal environment and the energy consumption according to the capacity and the restart time of the cooling system. This study implemented a building system energy simulation using EnergyPlus to evaluate the indoor air temperature, recovery time, and energy consumption of the cooling system while varying the capacity and restart time. As a result, the recovery time was between 49 and 425 min. and energy consumption varied between 419.0 and 521.4 kWh for various capacities. The recovery time was between 26 and 153 min. and energy consumption was between 426.0 and 439.0 kWh for various restart times.

An air handling unit utilizes economizer control to reduce cooling energy consumption by intaking outdoor air (OA) at lower temperatures. This control modulates OA intake rates based on the OA temperature, adjusting to maximum and partial rates when the OA temperature is below the maximum limit set-point (MLSP), and to minimum rates when it exceeds the MLSP. The MLSP acts as a baseline for determining OA intake rates. However, current MLSPs do not account for the specific OA conditions in South Korea, leading to the intake of unnecessarily warm OA or underutilization of available cooler OA, both of which negatively impact cooling energy performance. Therefore, this study aims to identify the optimal MLSP for OA conditions in South Korea. Through evaluation of cooling energy performance and the indoor thermal environment at various MLSP, it was determined that an MLSP of 22 °C facilitates the lowest cooling energy consumption without adversely affecting the indoor thermal environment. Implementing this MLSP resulted in 5.9% energy savings compared to Case #1 (baseline). The findings indicate that setting an MLSP according to local OA conditions is crucial for maximizing energy savings through economizer control.

In the heating supply systems in apartment buildings utilizing district heating, the supply water temperature setting is a critical control for providing sufficient heating and effective usage of the heating energy. Conventional water temperature control methods such as fixed temperature (FT) control can result in energy wastage and outdoor air temperature reset (OTR) control cannot reflect the variation in the heating demands of households because it only considers the outdoor air temperature. Therefore, this study proposes an advanced control method called flow-based residential energy demand (f-RED) control, which sets the supply water temperature based on the outdoor air temperature and household heating demands (i.e., the changes in the circulated heating water flow). To determine the performance of the proposed method compared to the conventional one, this study utilizes building energy simulation. The simulation analysis results confirm that the f-RED control method appropriately sets the supply water temperature based on a combination of the two factors, supplies heat according to heating demands, and reduces the energy consumption of the circulation pump by approximately 1.6% and that of the secondary pump by 4.2%. Thus, the f-RED control method is able to utilize heat energy more effectively and efficiently than the conventional control method.