Medium-and-long-term runoff forecasting method considering regulation and storage of upstream reservoir

Abstract

The invention discloses a medium-and-long-term runoff forecasting method considering upstream reservoir regulation and storage, which comprises the following steps of: firstly, collecting reservoir parameters in a current horizontal year, and then constructing a medium-and-long-term optimal scheduling model according to different scheduling task requirements of each upstream reservoir; simulation optimization scheduling is carried out according to the natural runoff process and medium and long term optimization scheduling models of different scheduling task requirements, and the scheduling process obtained through optimization is stored according to different incoming water scenes to form a scheduling strategy set; then constructing a runoff forecasting model based on a BP neural network according to the collected meteorological factors and hydrological factors to predict the annual runoff process considering the regulation and storage influence of the upstream reservoir, and verifying and evaluating the runoff forecasting result by adopting various evaluation indexes; the medium and long-term runoff forecasting level can be improved, and the guiding effect of medium and long-term runoff forecasting on reservoir operation is achieved.

Images