Photovoltaic generated power forecasting device and method

Abstract

The invention discloses a photovoltaic generated power forecasting device and method. The invention relates to the technical field of photovoltaic power generation. The photovoltaic generated power forecasting device comprises a PM10 (Particulate Matter) sensor, a PM2.5 sensor, a humidity sensor, a visibility sensor, a temperature sensor, a RS232 (Recommend Standard) communication interface, a single chip, a power circuit, a clock circuit, a 3G (The 3rd Generation Telecommunication) communication module, a FPGA (Field Programmable Gate Array) chip and a FLASH chip. Based on acquiring a large number of actual samples of PM2.5 concentration-PM10 concentration-humidity-visibility-AOD (Aerosol Optical Depth), the power forecasting method forecasts the AOD by using a BP (Back-Propagation) neural network method; the AOD and the precipitable water are selected as main change parameters; the two-band atmospheric radiation transmission model is adopted to calculate the solar direct radiation intensity and the scattering radiation intensity; thus, the total radiation intensity received by the photovoltaic cell panel is forecasted; at last, the photovoltaic generated power is precisely forecasted in real time through the photovoltaic conversion model; the output power of the photovoltaic power generation is forecasted; and the method is advantaged in clear calculation process and high forecasting precision.

Description

technical field [0001] The invention relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power generation power prediction device and method. Background technique [0002] Photovoltaic power forecasting is of great significance for power system scheduling. Existing photovoltaic power generation prediction methods can be divided into statistical prediction methods and physical prediction methods based on atmospheric radiative transfer models. Compared with statistical forecasting methods, physical forecasting methods have the advantages of simple calculation and no dependence on historical data, but their forecasting accuracy is greatly affected by model parameters. [0003] Atmospheric aerosol optical depth (Aerosol Optical Depth, AOD) is the most important parameter in the atmospheric radiative transfer model, which is used to describe the attenuation effect of aerosol on light, and its acquisition methods include satellite obse...

AI Technical Summary

Problems solved by technology

The satellite observation method is to retrieve the AOD based on the monitoring data of the Moderate Resolution Imaging Spectrometer (MODIS) carried by the remote sensing satellite. Due to the influence of the satellite transit time and the data release cycle, the real-time performance of the retrieval is poor; the ground-based observation is through ground observation. The station uses the photometer measurement data to invert the AOD, and the inversion accuracy is high, but the calibration of the photometer is quite complicated, and there are few observation stations; therefore, how to obtain AOD in real time, accurately and conveniently has become an Key Issues in Physical Prediction Methods

Images