Reservoir Basin Runoff Forecasting Method and System

Abstract

The invention, which relates to the field of hydrological forecasting, discloses a method and system for runoff forecasting of a reservoir basin, thereby improving the accuracy of runoff forecasting of a reservoir basis. The method comprises: step one, on the basis of an entropy theory, calculating historical entropy weights of all precision evaluation indexes of historical runoff forecast data corresponding to at least two forecasting models; step two, according to the entropy theory, calculating current entropy weights of all precision evaluation indexes of the current session of forecasting data corresponding to all forecasting models; step three, combining the historical entropy weights corresponding to all precision evaluation indexes with the current entropy weights to obtain entropy weighted values of all the forecasting models and then carrying out calculation to obtain correction weights of all the forecasting models; and step four, according to the correction weights of all the forecasting models, carrying out calculation by using an arithmetic weighted average method to obtain a runoff forecasting result of a reservoir basin based on combination of all the forecasting models. Therefore, with comprehensive utilization of forecasting performance advantages of a plurality of models, the reservoir basin runoff forecasting precision can be improved effectively.

Description

technical field [0001] The invention relates to the technical field of hydrological forecasting, in particular to a method and system for forecasting runoff in a reservoir basin. Background technique [0002] In recent years, with the change of global climate and the frequent occurrence of extreme weather events such as torrential rains and floods, the optimal dispatch of reservoirs is an important means to realize the utilization of flood resources and effectively improve the comprehensive benefits of reservoirs such as flood control and power generation. The optimal operation of reservoirs must be supported by accurate reservoir runoff forecasting. The existing runoff forecasting models are difficult to accurately describe the process of runoff production and confluence in different types of watersheds due to the generalization of the characteristics of runoff production and confluence in reservoir basins. Due to the different emphases of generalization processing, the for...

AI Technical Summary

Problems solved by technology

The optimal operation of reservoirs must be supported by accurate reservoir runoff forecasting. The existing runoff forecasting models are difficult to accurately describe the process of runoff production and confluence in different types of watersheds due to the generalization of the characteristics of runoff production and confluence in reservoir basins. Due to the different emphases of the generalization process of the forecasting model, the forecasting accuracy rate for various types of runoff processes is not the same

Images