Hydroelectric generation prediction method based on extreme learning machine

Abstract

The invention discloses a hydroelectric generation prediction method based on an extreme learning machine. The method comprises the following steps: obtaining parameter data information from a hydroelectric generation system and preprocessing data; dividing the data into two mutually exclusive parts, performing data training on one part, and performing data testing on the other part; acquiring training data, and establishing a model by adopting the training data; performing module training by adopting methods of cross validation, grid search and model evaluation and obtaining an optimal model;using the trained optimal ELM model to predict test data, acquiring and outputting a prediction result, and ELM being an extreme learning machine model. Through the method, higher learning speed andbetter generalization ability are displayed; the hydroelectric generation is more accurately and effectively predicted, the cost is reduced, and the learning rate is improved.

Description

technical field [0001] The invention relates to the technical field of electric energy, in particular to a hydroelectric power generation prediction method based on an extreme learning machine. Background technique [0002] As a new energy source, hydropower mainly uses the drop of rivers to convert the potential energy at high places into electrical energy through water turbines. Hydropower generation has multiple advantages. It is a renewable energy source that is inexhaustible, energy-saving and environmentally friendly, and has little impact on the environment. Therefore, hydropower generation has been vigorously promoted. But at the same time, since hydropower generation uses natural water flow, it is very dependent on the flow conditions. The uncertainty of water flow and environmental factors will lead to the instability of hydropower generation and affect the efficiency of power generation. Therefore, the prediction research of hydropower generation is particularly i...

AI Technical Summary

Problems solved by technology

However, even with the most advanced prediction methods based on artificial neural networks, some inherent shortcomings are still unavoidable, such as excessive training, high operating costs, slow learning speed, and easy to fall into local optimal solutions.

The key disadvantage is that the learning algorithm is slow and parameters need to be adjusted iteratively, so this prediction method cannot improve the prediction effect by changing the algorithm structure and continuous training.

Images