Error evaluation method of wind power forecasting

Abstract

The invention discloses an error evaluation method of wind power forecasting. The error evaluation method of wind power forecasting includes error evaluation index of wind power forecasting is calculated, wherein sample data includes predict data and measured data, according to sample data of the wind power forecasting. Principal component analysis is applied to the error evaluation index of wind power forecasting to choose main effective components. Weight coefficient is calculated by the corresponding main effective components. Comprehensive evaluation index is calculated by the main effective components and weight coefficient calculated by the main effective components accordingly. The error evaluation method of wind power forecasting has the advantages of evaluating the forecasting level of wind power in a comprehensive way, avoiding uncertainty created by different ranking produced from multiple indicators , and making the error evaluation more general and accurate.

Description

technical field [0001] The invention relates to the technical field of error evaluation of wind farm power prediction, in particular to an error evaluation method of wind farm power prediction. Background technique [0002] Wind power prediction is the core issue of economical and safe operation of new energy power system. Wind power is a random and fluctuating natural resource. When its penetration rate exceeds a certain percentage, the power quality and the operation of the power system may be seriously affected. The level of wind power forecasting is directly related to issues such as power grid peak regulation, unit combination, and unit economical operation. However, the current forecasting level of wind power power cannot meet the needs of the actual operation of the power system. [0003] In recent years, various institutions and scholars at home and abroad have carried out a lot of research work on wind power forecasting, mainly focusing on physical models and stati...

AI Technical Summary

Problems solved by technology

[0004] Compared with the increasingly accurate and complex wind power forecasting models, the wind farm power forecasting evaluation indicators used to test the forecasting level and service system operation are still relatively simple

At present, the evaluation indicators of wind farm power prediction level mostly use the two indicators of root mean square error and pass rate. These two indicators can reflect the degree of dispersion and reliability of the predicted value and the actual value to a certain extent, but they cannot fully evaluate the prediction results. , the evaluation results are not suitable to directly guide the dispatching operation of power grids such as unit combination, peak regulation and frequency regulation

Images