A two-stage stochastic optimal operation method of a hydropower station reservoir based on the residual period benefit function approximation

Abstract

The invention discloses a two-stage stochastic optimal operation method of a hydropower station reservoir based on the residual period benefit function approximation, which comprises the following steps of dividing the hydropower station reservoir operation period into a current stage and a residual period, and constructing a two-stage decision model framework; considering the influence of residual water situation and residual storage capacity on residual benefit, constructing the approximate function of residual benefit; based on stochastic dynamic programming (SDP), proposing a stepwise iterative method to obtain the approximate residual benefit function; according to the actual runoff forecasting level, establishing a two-stage stochastic optimal scheduling model. The method of the invention avoids the dimension disaster of the SDP, takes the artificial neural network as the approximator of residual period benefit function, avoids the artificial assumption of residual period benefitfunction, and can obtain the continuous curved surface of residual period benefit. The two-stage stochastic optimal dispatching model transforms the multi-stage reservoir dispatching decision-makingproblem into a two-stage optimal decision-making problem, which can be directly used to guide the rolling updating of medium and long-term generation plans.

Description

technical field [0001] The invention relates to a reservoir scheduling method, in particular to a two-stage stochastic optimal scheduling method for a hydropower station reservoir based on the approximation of the residual period benefit function. Background technique [0002] The preparation of mid- and long-term power generation plans for hydropower stations has always been an important and difficult point in the field of reservoir optimization and dispatching. When formulating the dispatching plan, not only the runoff change at the moment, but also the long-term runoff change law should be taken into consideration, and both the short-term benefit and the long-term benefit should be considered. Considering the actual situation that the accuracy of medium and long-term runoff forecasting is not high enough and the forecast period is limited, in order to make appropriate room for power generation planning, in the power balance of the power system, the usual guarantee rate fo...

AI Technical Summary

Problems solved by technology

[0010] From the rolling update process of the medium- and long-term power generation plan above, it can be seen that there are two problems in the formulation of the current medium- and long-term power generation plan: ① The optimization scheduling model does not consider the uncertainty of runoff forecast

② The forecast period of runoff forecast is limited, which does not match the reservoir regulation period

[0011] The existing method of using an optimization model to formulate medium and long-term power generation plans does not consider the uncertainty of runoff forecast, and there is a problem that the forecast period of runoff forecast does not match the reservoir dispatching period

Images