Wind turbine generator output step-by-step uncertainty prediction method and device

Abstract

The invention provides a wind turbine generator output step-by-step uncertainty prediction method, which comprises the steps of extracting wind condition feature information of a fan at a specific machine position of a wind power plant, performing unsupervised clustering based on the extracted wind condition feature information, and performing wind condition uncertainty prediction modeling and fanoutput uncertainty modeling step by step based on different wind condition categories; and finally, obtaining an uncertainty prediction model of the fan output, and performing prediction based on themodel. On the other hand, the invention provides a wind turbine generator output step-by-step uncertainty prediction device. According to the method, the observability and controllability of single-step prediction are fully utilized, and the flexibility and controllability of ultra-short-term or short-term output prediction of the fan at the specific position are enhanced; meanwhile, the prediction precision is improved through single-step prediction uncertainty control, and the final fan output prediction precision is improved. In addition, the step-by-step prediction model is updated basedon triggering modes such as regular time driving and event driving of prediction precision monitoring, and the reliability of fan output prediction is guaranteed.

Description

technical field [0001] The invention relates to a method and a device for predicting the output of a wind turbine, in particular to a method and a device for predicting the output of a wind turbine with stepwise uncertainty. Background technique [0002] Due to the random fluctuation of wind energy, large-scale wind power grid integration has brought severe challenges to grid dispatching, security and economic operation. Wind power prediction is an important means to enhance the knowability and controllability of wind power. With the continuous improvement of the accuracy of numerical weather prediction, the medium and long-term wind power prediction technology based on weather forecast has made great progress. However, limited to time and space scales, it is difficult to guarantee the accuracy of wind power prediction in short-term, ultra-short-term and small and micro spaces for mid- and long-term wind power forecasting. In recent years, after the rapid and large-scale g...

AI Technical Summary

Problems solved by technology

At present, most of the researches on wind power forecasting of specific machines are directly based on the forecast of wind turbine output time series, and fail to fully consider various uncertain factors affecting wind turbine output. and their use are restricted

Images