基于EMD-RVM的风电场机组分组功率预测
摘要:通过识别不同风电机组的相似性将风电场内各机组区分为不同的机组群，对每组机群分别建立功率预测模型，既提高了计算效率，又改善了大型风电场短期功率预测精度，较好解决了风电波动性和间歇性对电力系统安全运行的影响。提出了一种基于戴维森堡丁指数与聚类算法的风电场机组分组功率预测方法，以实际测量风速，测量功率以及两者的组合作为机组分组模型输入，分析其对聚类精度的影响程度。首先，采用经验模态分解方法将风电功率序列分解后，将与原信号具有高相关性的固有模态函数(intrinsic mode function，IMF)分量重构，作为K-means聚类算法的输入重新进行场内机组分组。然后，对每组机群分别构建经验模态分解－相关向量机(empirical mode decomposition-relevance vector machine，EMD-RVM)模型。最后，将预测功率分量叠加获得总功率的预测值。仿真实验结果表明，风速是影响聚类结果的主要因素，功率可作为不同聚类模型输入变量的重要补充；基于EMD-RVM的分组功率预测提升了预测精度，提高了预测效率。
Abstract：By identifying the similarity of different wind turbines in the wind farm unit of each unit is divided into different groups, each group of fleet power prediction model is set up, respectively, can not only improve the computing efficiency, improved at the same time a large wind farm short-term power prediction precision, better solved the volatility and intermittent wind effects on safe operation of power system. A wind farm grouping power prediction method based on Davidson-Boding index and clustering algorithm was proposed. The actual measured wind speed, measured power and the combination of the two were taken as the input of the grouping model, and the influence degree on the clustering accuracy was analyzed. After the wind power sequence is decomposed by the empirical mode decomposition method, the intrinsic mode function (IMF), which is highly correlated with the original signal, is reconstructed and used as the input of the k-means clustering algorithm to regroup the units in the field. Empirical Mode Decomposition and Relevance Vector Machine (EMD-RVM) models were constructed for each cluster, and the predicted power components were superimposed to obtain the predicted value of total power. The simulation results show that the wind speed is the main factor affecting the clustering results, and the power can be used as an important supplement to the input variables of different clustering models. Packet power prediction based on EMD-RVM improves the prediction accuracy and efficiency.
标题：基于EMD-RVM的风电场机组分组功率预测
title:Power Prediction for Groups of Wind Farm Units Based on EMD-RVM
作者：张晋华, 冯源, 黄远为, 阎洁
authors:ZHANG Jinhua, FENG Yuan, HUANG Yuanwei, YAN Jie
关键词：风电场机组分类,聚类算法,经验模态分解,戴维森堡丁指数,风电功率预测,
keywords:wind farm unit classification,clustering algorithm,empirical mode decomposition,Davies-Bouldin index,wind power forecast,
发表日期：2021-06-02
- 文件大小:
- 2.98 MB
- 下载次数:
- 60
-
高速下载
|
|
