The invention discloses a sewage treatment lift pump optimization scheduling control method based on incoming water prediction. The method comprises the steps that a prediction model of the incoming sewage amount is established according to historical data of a sewage pool water level database and a local 24-hour precipitation amount database; parameters of a sewage pool are collected, wherein theparameters comprise the maximum water level and the minimum water level allowed by the sewage pool, and the rated displacement, quantity and expected running duration of lift pumps; the current waterlevel of the sewage pool is monitored in real time, and the current water level is utilized to predict the incoming sewage amount in future preset time by establishing the prediction model of the incoming sewage amount; the number of the lift pumps which need to be started at corresponding moments is calculated by utilizing a prediction result. According to the method, a control center intelligently controls the start and stop of the lift pumps, unattended operation of the sewage lift pumps is realized, and the labor cost is reduced.