Journal of the Korean Solar Energy Society ISSN:1598-6411(Print) 2508-3562(Online) 한국태양에너지학회 논문집

In this study, we use the monitoring information of the 214.5RT ammonia screw refrigeration system to show that it is possible to analyze operation patterns based power load usage, predict power usage, and save energy. We further propose an algorithm to this end. Accidents occur frequently, such as the leaking of ammonia in a recently dilapidated freezer warehouse, and management is an important point of focus because most of the power load in freezer warehouses is drawn by refrigerators. It is important to save energy and predict accidents by using the temperature information of the Meteorological Agency and taking into consideration the pressure and temperature of the refrigerator. In particular, the pressure of the refrigerator changes rapidly according to seasonal changes, and this information could be used to reduce accidents. In addition, as interest in energy saving is increasing worldwide and the reduction of carbon dioxide emissions comes into focus, research on energy saving is being conducted in various fields. In this paper, a prediction algorithm is implemented by analyzing data from the past two years among the monitoring information of a large-scale animal center refrigeration system in Incheon area using deep learning, a type of AI algorithm that has recently attracted attention, as a prediction technique. Among the deep-learning models, an algorithm is designed using RNN (Recurrent Neural Network) and LSTM (Long Short-Term Memory). The RNN and LSTM models have strengths in continuous data pattern analysis. Through this model, data are predicted and performance evaluations are conducted by comparing the power load of refrigerators that have been actually consumed recently, considering the current limiting situation and the direction to move forward.