Wind Power Forecasting Method Based on Continuous Time Period Clustering and Support Vector Machine Modeling

Abstract

The invention discloses a wind power prediction method based on continuous time slice clustering and support vector machine (SVM) modeling. The method comprises the following steps of: (1) performing annual similar day unsupervised clustering according to the wind characteristic; (2) partitioning an entire year into n continuous time slices according to a similar day clustering result obtained in the step (1), and clustering and classifying every time slice according to the frequency of each type of date within every time slice and the wind characteristic in the continuous time slices; and (3) modeling the time slices of the same type in the step (2) by using an SVM for predicting the same time of future years. An annual continuous time slice clustering method is adopted on the basis of day similarity, so that day similarity and time continuity are considered simultaneously, and the similarity of a training sample in a prediction model and the accuracy of wind power prediction are increased greatly. Compared with the conventional method, the wind power prediction method has the advantages that: the relative power prediction error is decreased by 7.2 percent, and the prediction accuracy of the wind power is up to 83.96 percent.

Description

technical field [0001] The invention relates to a wind power prediction method, in particular to a wind power prediction method for performing cluster analysis and support vector machine modeling on the actual data of a wind farm. Background technique [0002] As an intermittent energy source, due to its randomness and uncontrollability, the amplitude of output power varies greatly and the frequency is unstable, which has a great impact on the power grid. With the increase of wind power installed capacity, the proportion of wind power grid connection is gradually increasing, so it is very important to predict the output power of wind farms. [0003] Wind power prediction methods mainly include physical methods [ and statistical methods. The physical method does not require a large amount of historical data, but it is generally difficult to model. It needs to analyze and study various conditions of the geographical location of the wind farm, and is suitable for new wind far...

AI Technical Summary

Problems solved by technology

These two methods only consider the similarity law of the day from the horizontal, and do not consider the influence of the continuity of the date on the power prediction from the vertical. Since the atmospheric motion is a long-term continuous and gradual process, the commonly used above-mentioned statistical prediction methods do not take both into account The similarity and continuous change of wind speed lacks effective classification of modeling data, so the similarity of training samples in the prediction model and the accuracy of prediction are not ideal, which cannot meet the requirements of wind power grid integration

[0006] In addition, when clustering similar days throughout the year, the traditional K-means algorithm, the total number of categories C is determined, through continuous calculation, the position of the center of category C is adjusted to achieve optimal classification, but due to wind Uncertainty and randomness, the optimal value of the total number C of categories cannot be determined artificially before classification, and the C values ​​of different wind farms may not be the same, so the traditional K-means algorithm has certain limitations

Images