| The daily life of urban residents and the development of economic construction are inseparable from the normal operation of the urban water supply system.With the rapid development of cities and the continuous increase of residents’ water demand,the water supply pipeline network has been continuously transformed and become more and more complex.At present,most urban water supply scheduling is still based on manual experience decision-making and scheduling,and there is a certain amount of energy waste.In response to the national "dual carbon" policy,it is very necessary to optimize the scheduling of the water supply system to achieve energy saving and consumption reduction,and it is also the development trend of smart water affairs in recent years.In this paper,the application research of two-level optimal scheduling of water supply system is carried out,mainly including urban water supply prediction,macro pressure prediction of pipe network,performance prediction of pumping station,primary and secondary optimal scheduling of water supply and so on.Firstly,the ABC-MGRU algorithm based on wavelet decomposition is used to establish a water supply forecast model,and the variables that have a great influence on water supply are selected as model input variables and compared with the prediction results of other algorithms.The model prediction accuracy meets the needs of optimal scheduling.Then the macro hydraulic model of the water supply network is established,including the outlet pressure model of the water plant and the pressure model of the pressure measuring point based on the ABC-ELM algorithm,and compared with other methods,the results show that the established macro hydraulic model is reliable and accurate,and can be used as Constraint function for optimal scheduling of water supply.Then,taking the maximum profit of water supply as the optimization goal,taking the water supply and outlet pressure of the water plant as the decision variables,and the pressure at the pressure measuring point as the constraint condition,a first-level optimal scheduling model was established,and the artificial bee colony algorithm was used to optimize the water supply and outlet pressure.As a result,the profit of water supply increased by 5.4% compared with that before optimization.Then,on the premise of the water supply and pressure obtained from the first-level optimal scheduling,a second-level optimal scheduling model is established based on the pumping station performance model,and constraints are added to the objective function according to the operating conditions.Optimal scheduling is carried out to find the optimal pump combination to meet the operating conditions of the water plant.Compared with before optimization,the energy consumption of the water plant pumping station is reduced by 7.9%. |
