A super-short-term chaotic prediction method for photovoltaic output power

Abstract

The invention relates to an ultra short-term chaos prediction method for photovoltaic output power. The duration of the ultra short-term lasts from zero to four hours, and the method comprises the following steps: using the C-C method to obtain the optimal delay amount l and the optimal embedding dimension m for the time sequence of photovoltaic output power; reconstructing the phase space for the time sequence of the photovoltaic power; determining the predicted center phase space point Pk according to the phase space for the time sequence of the photovoltaic power; selecting the adjacent phase space point Pkj corresponding to the predicted center phase space point and calculating the weight Wj of the adjacent phase space point Pkj; according to the weight Wj of the adjacent phase space point Pkj, building a photovoltaic weight first-order local linear regression model; calculating the optimal linear fitting coefficient matrix; and calculating the predicted photovoltaic output power value according to the optimal linear fitting coefficient matrix. Compared with the prior art, the method of the invention does not have to obtain metrological data in advance and does not need to establish prediction models for different weather patterns. The model can be built simply. The prediction consumes a short time but higher prediction accuracy can be achieved.

Description

technical field [0001] The invention relates to the field of photovoltaic power generation, in particular to an ultra-short-term chaotic prediction method for photovoltaic output power. Background technique [0002] In recent years, photovoltaic power generation has developed rapidly as a clean and renewable energy source, moving from independent power generation to grid-connected power generation. In the future, a large number of distributed photovoltaic power generation systems will be connected to the grid, and the penetration rate of photovoltaic power generation in the grid will continue to increase. The intermittent and random problems of photovoltaic output power will have an adverse impact on the stability of the grid connected to it. It will also cause difficulties in the scheduling work of the power sector. Therefore, by accurately predicting the output power of distributed photovoltaic power generation and coordinating with the charging and discharging of the ene...

AI Technical Summary

Problems solved by technology

However, the above method does not conduct an in-depth analysis of the fluctuation characteristics of photovoltaic output. At the same time, the model of the above prediction method is complicated, and the improvement of prediction accuracy depends on accurate weather forecast data. Considering the current forecast level limit, the prediction accuracy has not achieved satisfactory results. , affecting the safe and economical operation of the power system

Images