Probabilistic prediction method of wind power based on chaotic firefly algorithm and Bayesian network

Abstract

The invention discloses a wind power probabilistic prediction method based on chaotic firefly algorithm and Bayesian network. The steps include: 1. Obtain wind speed, wind direction, air temperature and wind power actual power data, preprocess the data, select training set and Test set data; 2. Perform empirical mode decomposition on the original wind power data to make the wind power time series more stable; 3. Build a Bayesian network model to obtain the initial prediction interval; 4. Calculate the range of interval change amplitude and use the chaotic firefly algorithm to obtain Optimal interval variation amplitude; 5. Perform chaotic search near the optimal interval variation amplitude to obtain the final prediction interval. The invention can measure the uncertainty of wind power by constructing a prediction interval, thereby providing an effective reference for power dispatching decision-making.

Description

technical field [0001] The invention relates to the technical field of wind power generation, and mainly relates to a wind power prediction model method based on EMD decomposition, Bayesian network and chaotic firefly algorithm. Background technique [0002] In recent years, with the development of society and economy, the demand for energy is increasing day by day. Fossil energy is gradually facing the risk of depletion. At the same time, the use of a large number of fossil fuels has brought serious pollution problems. In order to deal with the problems of fuel energy and environmental pollution, renewable energy has been widely used. Among them, wind energy, as a clean, renewable, and most potential energy source, has been rapidly developed and applied in the past few decades. With the gradual expansion of the scale of wind power generation, wind power occupies an increasing proportion in the power system. However, the weak controllability of wind power caused by the int...

AI Technical Summary

Problems solved by technology

However, due to the uncertainty of wind energy itself and the inherent defects of the model, the traditional deterministic point prediction method has problems such as point prediction errors that cannot be eliminated, uncertainty in the results cannot be measured, and the fluctuation range of wind power cannot be given.

[0005] In the current probabilistic prediction methods of wind power, evolutionary algorithms are mostly used to optimize the model. However, although the traditional evolutionary algorithms have a strong global search ability and can effectively improve the convergence speed of the model, they generally have a slow convergence speed in the later stage. The model is prone to prematurity, and it is easy to fall into the defect of local optimal solution

In wind power forecasting, the algorithm will run for a long time and fail to meet the time availability requirements; the prediction accuracy is not high and cannot meet the accuracy and availability requirements

Images