A method for predict photovoltaic probability

Abstract

The invention discloses a photovoltaic probability prediction method, which comprises the following steps: (1) collecting historical data of a photovoltaic power station and performing sequence decomposition on the historical output data; (2) randomly generating input layer-Hidden layer weight and offset; (3) Setting the expected coverage rate of probability prediction interval; (4) Training the network to determine the hidden layer Weights of the output layer; (5) inputting data to obtain output prediction interval. As that historical output of the photovoltaic power station is taken as a model input, the invention solves the influence of the randomness of the mount position of the photovoltaic array and the use time of the photovoltaic array on the conversion efficiency, and improves theprediction accuracy; Decomposition of historical data can more effectively distinguish the influence of different factors on output and enhance the characteristics of data. Introducing the idea of limit learning machine ELM, the training speed is greatly improved while the precision is guaranteed; Quantile regression is used to predict the probability of photovoltaic output interval, which has astronger reference value for the formulation of dispatch plan.

Description

technical field [0001] The invention belongs to the technical field of electrical engineering, and more specifically relates to a photovoltaic probability prediction method. Background technique [0002] With the global energy shortage and environmental protection issues becoming more and more prominent, the utilization of renewable energy has attracted extensive attention. As an important form of renewable energy, photovoltaic power generation is one of the power generation methods with the most large-scale development conditions and commercial development prospects in renewable energy. At present, large-scale photovoltaic power generation systems have been built in large numbers at home and abroad. However, since the output of the photovoltaic power generation system is affected by the intensity of solar radiation and weather factors, the change of its power generation is a non-stationary random process. At the same time, due to the diurnal periodicity of sunlight, photov...

AI Technical Summary

Problems solved by technology

[0003] In view of the defects of the prior art, the purpose of the present invention is to provide a photovoltaic power probability prediction method, which aims to solve the problem that the photovoltaic output is difficult to predict due to the randomness of the output of the existing photovoltaic power plant system

Images