A Wind Power Prediction Method Based on Distributed Optimization and Spatial Correlation

Abstract

The present invention relates to a wind power prediction method based on distributed optimization and spatial correlation, comprising the following steps: 1. Normalize the historical data of wind power in the same period of each wind farm in a certain area, and then divide the output state into intervals, Generate and store basic data sets and wind power output state libraries. 2. Each wind farm exchanges historical space-related data, and generates and stores a space-time Markov state transition matrix in the target wind farm to be predicted. 3. Based on the local time series and the space-time Markov state transition matrix, the sparse space-time wind power prediction model of each wind farm is established and solved. 4. Exchange real-time measurement data between each wind farm. According to the output value of each wind farm at the current moment, use the prediction model to predict the power value of the wind farm, and regularly use the latest measured data to predict the time-space Markov state transition matrix and prediction. The parameters of the model are updated. The invention effectively improves the prediction accuracy of wind power and significantly improves the calculation efficiency.

Description

technical field [0001] The invention relates to the field of power system operation and control, in particular to a wind power prediction method based on distributed optimization and spatial correlation. Background technique [0002] With the depletion of non-renewable resources such as coal and oil and the increasingly serious energy dilemma, renewable energy such as wind energy, solar energy, tidal energy and biomass energy has attracted more and more attention worldwide. Wind power is the renewable energy with the most mature technology and the most development value in the renewable energy generation technology. The development of wind power is of great significance to ensure energy security, adjust energy structure, reduce environmental pollution, and achieve sustainable development. [0003] The intermittent nature of wind energy in nature determines that wind power has strong fluctuations. As the number and installed capacity of wind farms continue to increase, once ...

AI Technical Summary

Problems solved by technology

This feature brings convenience to historical data collection and real-time data collection in the forecasting process. The required data is single and easy to implement. However, this type of method ignores the spatial correlation between different wind farms in an area, and the prediction accuracy needs improvement

[0005] In addition, the traditional method usually needs to establish an independent and different form of prediction model for each wind farm. The prediction models of each wind farm need to set and adjust parameters separately. With the continuous expansion of wind power scale, wind farms in a region The number has increased sharply. This modeling method is cumbersome and consumes a lot of time and computer resources. It is not conducive to the rapid deployment and unified deployment of wind power forecasting systems, and cannot adapt to large-scale wind power grid integration.

Images