Data-driven air conditioner set temperature correlation simulation method and device and medium

The invention discloses a data-driven air conditioner set temperature correlation simulation method and device and a medium, and belongs to the technical field of air conditioner temperature control. According to the data-driven air conditioner set temperature correlation simulation method, one or more important features related to the air conditioner set temperature are obtained by constructing a data cleaning model, a feature expansion model, a collinear feature screening model, a nonlinear feature model and a feature screening model; according to the method, the characteristic factors influencing the air conditioner set temperature can be accurately evaluated, the needed factor correlation can be obtained, a characteristic selection basis is further provided for predicting the air conditioner set temperature, the air conditioner load demand can be accurately evaluated conveniently, and the method has the advantages of being high in practicability and easy to popularize. Therefore, the power supply and dema