Draining pump station optimization scheduling method based on machine learning technology

The invention discloses a drainage pumping station optimization scheduling method based on a machine learning technology, and the method comprises the steps: taking an SWMM model as an individual particle in a particle swarm algorithm, and calculating the simulation results of different schemes. In the optimization iteration process, three machine learning models, namely an artificial neural network, a Kriging model and a radial basis function network, are dynamically embedded, and possible optimal particles are selected by adopting a model error-based maximum expectation improvement filling criterion, so that evaluation and accelerated convergence of all particles are avoided, and the accuracy of optimization is improved. The accurate evaluation frequency of the algorithm is greatly reduced, efficient and accurate urban drainage pumping station optimization scheduling is achieved, meanwhile, the number of water pump switches and the water level of the forebay of the pump station are limited within the allowa