Building energy consumption prediction and energy control of large-scale shopping malls based on a noncentralized self-adaptive energy management control system

Central air conditioning is the main energy-consuming equipment in modern large-scale commercial buildings. Its energy consumption generally accounts for more than 60% of the electricity load of an entire building, and there is a rising trend. Focusing on reducing central air conditioning energy consumption is a first priority to achieve energy savings in modern large-scale commercial buildings. To study the main influencing factors of central air conditioning energy consumption in large shopping malls, in-depth collection and analysis of energy consumption data of Shenzhen Tian-hong shopping mall were considered, and the impact of factors such as the basic composition of central air conditioning, time, and Shenzhen weather on the energy consumption of shopping malls was considered. The most representative Buji Rainbow store of the Rainbow Group is used as the research object. The influencing factors of central air conditioning on its energy consumption are divided into air conditioning pumps, host 1-1, host 1-2, host 2-1, and host 2-2. The power consumption of the freezer and the eight impact indicators of time and weather in Shenzhen were constructed using Pearson correlation coefficients and a long short-term memory neural network method to construct a regression model of the energy consumption prediction of the mall building. The average relative deviation between the predicted energy consumption values and the measured energy consumption values is less than 10%, which indicates that the main influencing factors selected in this paper can better explain the energy consumption of the mall, and the obtained energy consumption prediction model has high accuracy.