Hydropower station group power generation scheduling rule extraction method

Abstract

The invention belongs to the field of hydropower energy optimization, and particularly discloses a hydropower station group power generation scheduling rule extraction method. The method comprises thesteps of establishing an objective function by taking maximum annual power generation capacity of a hydropower station group as an objective and constraint conditions thereof, and performing solvingto obtain an output flow optimal solution of each reservoir in each time period; establishing a generalized regression network by taking the input flow and the reservoir water level corresponding to each time period of each reservoir as input and the output flow as output; and optimizing a generalized regression network smoothing factor to obtain a scheduling function by adopting a particle swarmmethod based on a community gravity center based on the known input flow and reservoir water level corresponding to each time period of each reservoir, the output flow optimal solution and the training error minimum target function. According to the method, deep learning and cascade hydropower station power generation scheduling are combined, the generalized regression network corresponding to thescheduling function is established, the cascade hydropower station power generation scheduling rule based on the community gravity center particle swarm and the generalized regression network is extracted, the defect that a basic traditional particle swarm algorithm is prone to falling into local optimum is overcome, and reliability is high.

Description

technical field [0001] The invention belongs to the field of hydropower energy optimization, and more specifically relates to a method for extracting power generation scheduling rules of a hydropower station group. Background technique [0002] The optimal dispatch of cascade hydropower stations is very important for maximizing the benefits of the basin. However, due to the uncertainty of runoff, especially the poor accuracy of runoff forecast in the flood season, it is difficult to make a dispatch plan based on the assumption of deterministic water inflow in the actual production environment. Promote apps. Dispatch rules are an important way to guide reservoir dispatch. This method inputs key decision-making elements such as forecasted runoff and water level, and outputs decision variables such as outflow flow and end-of-period water level, and is highly operable. Generally, scheduling rules are extracted by implicit random scheduling. The basic idea is to extract scheduli...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for extracting power generation dispatching rules of a hydropower station group, which is used to solve the problem of over-fitting in the existing hydropower station group power generation dispatching rule extraction method due to the neglect of the verification set and the complexity of parameter adjustment in neural network training, which leads to the reliability of the extracted dispatching rules. Poor technical issues

Images