Photovoltaic power station short-term power prediction method based on recurrent neural network

Abstract

The invention relates to a photovoltaic power station short-term power prediction method based on a recurrent neural network, and the method comprises the following steps: S1, obtaining a corresponding NWP meteorological parameter according to the weather type of a to-be-predicted day; S2, collecting historical data of a plurality of days before a to-be-predicted day; S3, processing the historicaldata, and taking the processed historical data as a training data set; S4, learning the training data set by using a recurrent neural network, and adjusting parameters of the network by using a stochastic gradient descent method to obtain a prediction model; and S5, taking the NWP meteorological parameters of the day to be predicted as the input of the prediction model to obtain a predicted powervalue. The method can remarkably improve the precision and reliability of short-term power prediction of the photovoltaic power station.

Description

technical field [0001] The invention belongs to short-term prediction technology of photovoltaic power station power, in particular to a short-term power prediction method of photovoltaic power station based on cyclic neural network. Background technique [0002] In recent years, fossil fuels have been gradually depleted and environmental pollution has become increasingly serious, which has attracted widespread attention from all over the world. For the continuation of human civilization, taking the road of sustainable development is the only way in the future. At present, it is urgent to find new energy to bear the burden of human society The energy required for operation, solar energy is the most attention-grabbing new energy, but due to the strong volatility and randomness of solar energy, this will not be conducive to the safe and stable operation of the power grid, so the photovoltaic power forecasting technology is used to advance the production capacity of photovoltaic...

AI Technical Summary

Problems solved by technology

[0002] In recent years, fossil fuels have been gradually depleted and environmental pollution has become increasingly serious, which has attracted widespread attention from all over the world. For the continuation of human civilization, taking the road of sustainable development is the only way in the future. At present, it is urgent to find new energy to bear the burden of human society The energy required for operation, solar energy is the most attention-grabbing new energy, but due to the strong volatility and randomness of solar energy, this will not be conducive to the safe and stable operation of the power grid, so the photovoltaic power forecasting technology is used to advance the production capacity of photovoltaic power plants Estimated as the basis for deploying the grid, making the grid operation more stable and reliable

Images