Wind power system reliability estimation method using neural network and cross entropy sampling

Abstract

The invention discloses a method for estimating the reliability of a wind power system by using a neural network and cross entropy sampling. Training the power system network model by using the historical wind power data, and estimating the probability distribution of the wind speed of the wind power plant; gaussian random noise is sampled, the output wind speed of the sampled Gaussian random noise is processed through a generation network of the power system network model, and efficient reliability estimation of the power system containing the wind power plant is achieved by solving and calculating two reliability parameters of the power shortage time probability and the power shortage expectation. On the premise of considering the spatial correlation of the wind speeds of a plurality ofwind power plants, the probability distribution of the wind speeds of the wind power plants is estimated, and efficient system state sampling and reliability estimation are realized.

Description

technical field [0001] The invention belongs to a method for estimating power data in the field of power systems, and in particular relates to a method for estimating reliability of a wind power system using neural networks and cross-entropy sampling. Background technique [0002] Due to the strong randomness and instability of wind power, its access will disturb the supply and demand balance of the power system, thereby affecting the reliability of the power system. Therefore, it is of great significance to estimate the reliability of the power system including wind farms. [0003] At present, for the reliability estimation of the power system including wind farms, the mainstream method is to use the Monte Carlo method to sample the operating state of the power system and calculate the corresponding reliability parameters. However, the problem with this method is that for high-reliability systems, the Monte Carlo method requires a large number of samples to achieve converg...

AI Technical Summary

Problems solved by technology

However, the problem with this method is that for high-reliability systems, the Monte Carlo method requires a large number of samples to achieve convergence, which requires high computing resources.

[0004] Therefore, in the prior art, there is a lack of effective reliability estimation for power systems containing wind farms, and there is also a lack of stable improvement based on accurate reliability results.

Images