Multi-Objective Optimal Scheduling of Water Transmission and Distribution Channel Gate Groups Based on Machine Learning

This study develops a synergistic optimization method of multiple gates integrating hydrodynamic simulation and data-driven methods, with the goal of improving the accuracy of water distribution and regulation efficiency. This approach addresses the challenges of large prediction deviation of hydraulic response and unclear synergy mechanisms in the coupled regulation of multiple gates in irrigation areas. The NSGA-II multi-objective optimisation algorithm is used to minimise the water distribution error and the water level deviation before the gate as the objective function in order to achieve global optimisation of the regulation of the complex canal system. A one-dimensional hydrodynamic model based on St. Venant’s system of equations is built to generate the feature dataset, which is then combined with the random forest algorithm to create a nonlinear prediction model. An example analysis demonstrates that the optimal feedforward time of the open channel gate group is negatively connected with the flow condition and that the method can manage the water distribution error within 13.97% and the water level error within 13%. In addition to revealing the matching mechanism between the feedforward time and the flow condition, the study offers a stable and accurate solution for the cooperative regulation of multiple gates in irrigation districts. This effectively supports the need for precise water distribution in small irrigation districts.