Photometric network real-time correction self-learning arma model photovoltaic power prediction method

Abstract

The invention discloses a photometric network real-time correction self-learning ARMA model photovoltaic power prediction method, including input data to obtain autoregressive sliding average model parameters, that is, model training; input optical resource monitoring system data and operation monitoring system data, and according to the operation monitoring Data real-time correction of start-up capacity; establishment of autoregressive sliding average model to obtain ultra-short-term forecast results of photovoltaic power; real-time correction of ultra-short-term photovoltaic power forecast results by introducing real-time photometering station data; post-evaluation and analysis of real-time corrected forecast results The error between the predicted value and the measured value, if the predicted error is greater than the maximum allowed error, the model training will be performed again. Real-time correction of ultra-short-term prediction results of photovoltaic power generation by introducing data from real-time photometering stations overcomes the defect of low ultra-short-term prediction accuracy of photovoltaic power generation in the existing ARMA technology, and achieves the purpose of ultra-short-term prediction of photovoltaic power generation with high precision.

Description

technical field [0001] The invention relates to the technical field of photovoltaic power prediction in the process of new energy power generation, in particular to a self-learning ARMA model photovoltaic power ultra-short-term prediction method for real-time correction of photometric networks. Background technique [0002] After my country's photovoltaic power generation enters the stage of large-scale development, most of the large-scale new energy bases are located in the "three north regions" (Northwest, Northeast, and North China). Large-scale new energy bases are generally far away from the load center, and their power needs to be transmitted through long distances and high voltages. Go to the load center for consumption. Due to the intermittence, randomness and volatility of wind and light resources, the output of wind power and photovoltaic power generation in large-scale new energy bases will fluctuate in a large range, which will further lead to fluctuations in the ...

AI Technical Summary

Problems solved by technology

The ARMA method has many advantages, so it is widely used in the ultra-short-term prediction of photovoltaic power generation, but the biggest disadvantage of ARMA is the hysteresis of its prediction—that is, when the output of photovoltaic power generation changes, the change speed of the result predicted by ARMA is generally slower than the actual Variation speed of photovoltaic power generation output

Therefore, it seriously affects the prediction accuracy of ARMA

Images