Construction and Application of public Building Virtual Generator Based on Multiple Nonlinear Regression

As the main power consumption system of public buildings, central air-conditioning can be constructed as a virtual generator unit to participate in the operation of power system because of its flexible and adjustable characteristics. There are many electrical devices in the central air conditioning system, and the coupling relationship between the subsystems is complex. It is difficult to express the functional relationship between the adjustable power and various environmental parameters, which makes it difficult to construct the output model of the virtual generator. Based on this, this paper analyses the operation principle of central air-conditioning, and uses multiple nonlinear regression method to construct the virtual unit based on historical meteorological information and power consumption data. The results show that under the premise of meeting the accuracy requirements, the expression of the virtual generator can effectively analyze its regulation potential under different outdoor temperatures and the temperature consumption characteristics of the virtual generator.