Heat supply system dispatching automation implementation method based on machine learning and predictive control

The invention discloses a heat supply system dispatching automation implementation method based on machine learning and predictive control. The method comprises the following steps: establishing a heat supply system end user heat load prediction model and a heat supply system energy efficiency prediction model by adopting a machine learning algorithm; a neural network controller is arranged, wherein input variables are state variables and comprise the heat supply system energy efficiency ratio, outdoor meteorological parameters and heat supply system end user heat loads; the output variables are control variables and comprise the secondary side water supply temperature of a heat supply system, the control frequency of a circulating pump and the opening degree of an electric control valve; a heat supply system prediction control optimization objective function and equipment state constraint conditions are set; performing rolling optimization on the control variable in a limited prediction time domain by using