Abstract The frequent start–stop scheme in the operation management of large pumping stations causes several problems, e.g., energy consumption and a potential safety hazard. We therefore established a mathematical model for the optimal operation of a large-scale pumping station considering the start-stop loss of machine. The objectives of the optimization model included electricity charges for a pumping station operation and the start-stop loss of a pumping station. The blade angle and start-stop scheme were taken into account as the double-decision variables, while the target water extraction (equality constraint), start-stop scheme, and power were the constraint conditions. A combination of an orthogonal experiment and a 0-1 integer programming algorithm was proposed to explore the optimal solution of the model. A real case of a single-unit pump station in China was applied to prove the effectiveness of the algorithm. The results showed that the optimization efficiency of the proposed algorithm was 4%–10% higher than that of the genetic algorithm. Additionally, the maximum optimization benefit was obtained when there were fewer than three start-stops during the operation process. The proposed algorithm provided a reference for similar complex nonlinear models.