Photovoltaic power prediction method

Abstract

The invention provides a photovoltaic power prediction method. The photovoltaic power prediction method comprises the steps of determining historical meteorological data and historical output power ofa photovoltaic power station; preprocessing the historical meteorological data and the historical output power; constructing a neural network model based on the preprocessed historical meteorologicaldata and historical output power; training the neural network model; judging whether network parameters in the neural network model fall into local optimum or not; if the network parameters in the neural network model fall into local optimum, performing heuristic search and adaptive adjustment on the network parameters; determining meteorological data prediction information of the next predictionperiod, and obtaining output power prediction information of the next prediction period through the model obtained through training. After the network parameters in the neural network model fall intolocal optimum, heuristic search and adaptive adjustment are performed on the network parameters. Therefore, the neural network model has the capability of jumping out of the local optimum, and the training error can be continuously reduced.

Description

Technical field [0001] The invention relates to the technical field of data processing, in particular to a photovoltaic power prediction method. Background technique [0002] The traditional photovoltaic power prediction method mainly uses neural networks to learn historical weather data and power generation data of photovoltaic power plants. Specifically, the parameters of the neural network are continuously adjusted through the gradient descent method to minimize the error of the training samples on the model. [0003] Theoretically, a neural network with hidden layers can fit any single-valued function. However, in the process of training the neural network using the traditional gradient descent method, it is easy to make the network parameters in the neural network fall into the local optimum. After falling into the local optimum, the network parameters will stop changing. Even if the neural network continues to be trained, the error on the training set will no longer decrease...

AI Technical Summary

Problems solved by technology

However, in the process of neural network training using the traditional gradient descent method, it is easy to make the network parameters in the neural network fall into local optimum

Images