Design of Energy Consumption Prediction and Optimization Algorithm for Central Air Conditioning Systems Integrating Deep Learning

Indoor comfort parameters and outdoor environmental parameters are adjusted by controlling the compressor speed to adjust the refrigerant circulation and flow rate entering the indoor heat exchanger, timely meeting the indoor cooling and heating load requirements, and achieving summer cooling and winter heating. The problem of energy waste caused by the operation of CAC (Central Air Conditioning) systems also comes with it. In this regard, this article integrates DL (Deep Learning) to design energy consumption prediction and optimization algorithms for CAC systems. The results indicate that the energy consumption varies with the equipment speed at different optimal settings, and the overall energy consumption optimization effect is significant. Without optimization control, the average hourly power consumption was 264.7kw, and after optimization, the average hourly power consumption was 252.4kw. However, in the testing of system efficiency, it can be found that the data comparison before and after improving system efficiency optimization shows that the system efficiency improved by about 5% after using the algorithm in this paper. This article aims to help managers control energy consumption, save costs, and ultimately achieve the goal of reducing operational management costs through the study of optimizing energy consumption control in CAC systems using DL. Indoor comfort parameters and outdoor environmental conditions are regulated by adjusting the compressor speed to control the refrigerant circulation and flow rate entering the indoor heat exchanger. This ensures the timely fulfillment of indoor cooling and heating load requirements, enabling effective summer cooling and winter heating. Additionally, it addresses the issue of energy wastage resulting from the operation of CAC systems. In response to this challenge, this paper integrates DL techniques to develop energy consumption prediction and optimization algorithms tailored for CAC systems. The findings reveal that energy consumption fluctuates with equipment speed under various optimal settings, demonstrating a substantial overall improvement in energy consumption optimization. In the absence of optimization control, the average hourly power consumption stood at 264.7 kW, which decreased to 252.4 kW after implementing optimization measures. However, during the system efficiency testing, it was observed that the comparison of data before and after implementing system efficiency optimization revealed an approximate 5% enhancement in system efficiency through the utilization of the algorithm presented in this paper. This article's objective is to assist managers in effectively managing energy consumption, reducing costs, and ultimately achieving the goal of minimizing operational management expenses by investigating energy consumption optimization in CAC systems through the application of DL.