Short-term photovoltaic power prediction method based on similar daily wavelet transform and multilayer perceptron

Abstract

The invention provides a short-term photovoltaic power prediction method based on similar day wavelet transform and a multi-layer perceptron, a power prediction model is established by adopting an artificial intelligence technology, and a short-term photovoltaic power prediction model based on similar day wavelet transform and the multi-layer perceptron is established. According to the model provided by the invention, the advantages of various algorithms are combined, and the prediction accuracy can be effectively improved. The main innovation point of the method is that similar daily wavelet transform and a multilayer perceptron are combined to be used for the research of predicting the output power of the photovoltaic power station.

Description

technical field [0001] The invention belongs to the technical field of short-term prediction of photovoltaic power station power, in particular to a short-term photovoltaic power prediction method based on similar day wavelet transform and multi-layer perceptron. Background technique [0002] In recent years, solar energy has attracted extensive attention due to its clean, non-polluting, abundant and inexhaustible properties. According to a report released by the International Energy Agency (IEA), by the end of 2019, the installed capacity of global photovoltaic systems will be at least 627GW, of which 115GW in 2019. However, the uncertainty, intermittency, volatility and uncontrollability of solar energy are not conducive to the safe and stable operation of the power grid, and hinder the large-scale application of photovoltaic power generation. Accurate prediction of photovoltaic power is a prerequisite for large-scale application of photovoltaic systems and rational plann...

AI Technical Summary

Problems solved by technology

Time series analysis is based on the time series data obtained by systematic observation, and establishes a mathematical model through curve fitting and parameter estimation (such as nonlinear least squares). future trend, but as the time scale and output dimension increase, the prediction results will get worse

Fuzzy logic imitates the uncertainty concept judgment and reasoning thinking mode of the human brain, realizes fuzzy comprehensive judgment, solves the conventional fuzzy information problem that is difficult to deal with by traditional methods, and does not need to establish an accurate mathematical model of the research object, thus making the model simple and Easy to accept, understand and apply, however, it is very difficult and time-consuming to establish fuzzy rules and membership functions for complex systems

Markov chain is a typical stochastic process, the current state of the model is only related to its state at the previous moment, it uses the transition probability matrix to predict the state of the system and its development trend, although in some cases it can be very good Forecasting the state of the system, but not suitable for medium and long-term forecasting

Images