An upstream and downstream water level prediction method for cascade power stations

Abstract

The invention discloses a method for predicting upstream and downstream water levels of a cascade power station, which includes the following steps: Step 1, selecting input variables and output variables; Step 2, standardizing the data to eliminate the influence of dimensions; Step 3, determining the input Vector dimension, LSTM layer number, output vector dimension, and time step; step 4, LSTM forward propagation process and error back propagation process; forward propagation process is input into LSTM network in sequence according to time step, and corresponding output value is obtained ; Using the sum of the squares of the error between the output value and the true value as the loss function, the error is backpropagated along time to update the parameters; step 5, use the trained model for multi-moment continuous prediction. Applying LSTM to the water level prediction of cascade power stations can capture the lagging influence information of upstream power stations on downstream power stations, improve prediction accuracy, and provide more reliable theoretical support for scientific scheduling decisions.

Description

technical field [0001] The invention relates to a method for predicting upstream and downstream water levels of a cascade power station, and belongs to the technical field of water level prediction. Background technique [0002] Water level prediction refers to predicting the upstream or downstream water level of a hydropower station a certain time in advance. Accurate water level prediction is of great significance to hydropower station scheduling. However, hydropower stations are affected by many factors during their operation, resulting in large deviations in the prediction of water level changes in hydropower stations, which in turn affects the implementation effect of the dispatching plan. Especially for cascade hydropower stations with close hydraulic connections, the water level rises and falls with hysteresis, and the stable water levels after flooding, flat water, and receding water are also different, making it more difficult to accurately predict the water level o...

AI Technical Summary

Problems solved by technology

However, in terms of water level prediction of cascade power stations, especially the water level of downstream power stations, due to the close connection between cascade power stations, the operation of upstream power stations will affect the water level of lower power stations, and there is a time lag in the impact due to water flow propagation, while Common feed-forward neural networks such as BP neural network or RBF neural network are difficult to capture this feature

Moreover, if the water level and output data at several previous moments are used as input samples by window processing, there will be too many nodes in the input layer. If it is further necessary to continuously predict the upstream and downstream water levels at multiple moments, the number of nodes in the input layer will increase accordingly , leading to too many model training parameters, which will undoubtedly increase the difficulty of model training and reduce learning efficiency

Images