A short-term scheduling rule extraction method based on variable structure deep learning framework

Abstract

A short-term scheduling rule extraction method based on a variable structure deep learning framework, comprising: step 1, constructing a deep learning network; step 2, input factor-decision variable sample pair selection; step 3, normalizing the sample data in step 2 ; Step 4, key hyperparameter selection and optimization; Step 5, network reconstruction; Step 6, network training: use the reconstructed network obtained in step 5, input the samples obtained in step 3 for network learning, and obtain the final deep learning network. The network is the extracted short-term scheduling rule. Based on the actual historical operation data of the power station, the present invention constructs a deep learning network model based on long-term and short-term memory networks, excavates the inherent laws contained in the actual operation process, establishes the short-term dispatching rules of the power station, and calculates the water level at the beginning and end of the dispatching period of the power station, the water flow process during the period, and the power station The load process of the power grid is used as the input factor, and the water level at the end of the power station period is used as the decision variable, so that the output results of the model are more suitable for the actual dispatching process.

Description

technical field [0001] The invention relates to the field of hydropower energy optimization, in particular to a short-term scheduling rule extraction method based on a variable structure deep learning framework. Background technique [0002] The deterministic optimal dispatching of hydropower stations takes the future water and power grid load as a definite time series input. However, both runoff forecasting and power grid load forecasting have the characteristics of limited accuracy and limited forecast period. Difficult to apply well. [0003] The main idea of ​​implicit stochastic optimal scheduling is to extract the physical causal relationship between input factors and scheduling decisions by mining the inherent laws contained in the long sequence results of deterministic optimal scheduling, omitting the complicated model solving process, and then forming scheduling rules. However, since the training data source of this method is still the optimal scheduling result, it...

AI Technical Summary

Problems solved by technology

However, since the training data source of this method is still the optimal scheduling result, it is difficult to obtain the training sample data of the model, which also makes it difficult to apply the obtained scheduling results to the actual production process.

Images