Wind power climbing event direct forecasting method for improving training sample category imbalance

Abstract

The invention discloses a wind power climbing event direct forecasting method for improving training sample category imbalance, and the method comprises the following steps: 1, setting a threshold value of a wind power climbing event according to the installed capacity of a wind power plant, and carrying out the climbing event recognition of original wind power data; 2, defining a layered oversampling method based on wind power characteristics, and setting corresponding sampling parameters according to actual wind power data; 3, processing the original sample by using the original sample obtained in the step 1 and the layered oversampling method based on the wind power characteristics established in the step 2; and 4, establishing a data-driven prediction model by using the sample processed in the step 3, and predicting a wind power climbing event. According to the method, the problem of sample class imbalance between a wind power climbing event and a non-climbing event is effectively improved, and the problem of sample distribution imbalance of a high-power climbing event and a low-power climbing event in a climbing event sample is also improved.

Description

technical field [0001] The invention relates to a method for direct forecasting of wind power ramping events, in particular to a method for direct forecasting of wind power ramping events for improving the unbalanced categories of training samples. Background technique [0002] With the development of the times, "clean energy" and "renewable energy" have become the main direction of energy development; among them, wind power generation just meets the requirements of cleanliness and regeneration, and has become a very important way of generating electric energy. However, large-scale wind power development and utilization also face some corresponding problems and challenges. Most of the wind farms are built in remote areas with rich wind resources. The extreme weather in the region can easily cause wind power climbing events, which seriously affects the safe and stable operation of the power system. Therefore, predicting wind power ramp events and formulating effective contro...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of unbalanced categories of training samples in the direct prediction modeling of wind power ramp events and improve the accuracy of the wind power ramp event prediction model, the present invention provides a method for direct forecasting of wind power ramp events that improves the category imbalance of training samples

Images