Photovoltaic annual generating capacity calculation method based on machine learning

Abstract

The invention relates to the technical field of photovoltaics, and discloses a photovoltaic annual generating capacity calculation method based on machine learning, which comprises the following steps: S1, applying a time sequence correlation model to predict irradiance: a1, collecting monthly actual measurement meteorological data of all meteorological stations in a region where a power station is located in history of 10 years, averaging the data, and fitting the data by utilizing an ARp-order autoregressive process; a2, calculating parameter items through simulation, and predicting the monthly average radiation value and temperature of the next year; a3, calculating an illumination intensity distribution curve of the photovoltaic power station in the past year, namely the ratio of illumination time to annual illumination time under each illumination intensity; s2, predicting the generating capacity by utilizing a sample plate assembly method: b1, taking ten sample plate assemblies from different matrixes of a power station, and determining an IV curve and a temperature coefficient of the sample plate assemblies in a laboratory; the photovoltaic annual generating capacity calculation method based on machine learning can solve the problem that simulation carried out by existing mainstream photovoltaic power station simulation software is rough at present.

Description

technical field [0001] The invention relates to the field of photovoltaic technology, in particular to a method for calculating annual photovoltaic power generation based on machine learning. Background technique [0002] With the gradual exhaustion and withering of non-renewable energy sources such as petroleum and coal and the increasing pollution to the environment, photovoltaic power generation has become a major development trend in the power industry. However, with the increasing number of photovoltaic power plants across the country, the installed capacity of distributed photovoltaic power plants is also expanding, resulting in the continuous expansion of the impact of the grid-connected operation of photovoltaic power plants on the power grid. [0003] From the perspective of power grid dispatching and improving power quality of the power grid, accurate photovoltaic power generation forecasting can provide data support for the power grid dispatching department when p...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a machine learning-based calculation method for photovoltaic annual power generation, which has the advantages of high efficiency and solves the problem that the current mainstream photovoltaic power plant simulation software performs rough simulations

Images