|
| 引用本文: | 杨茂,翟冠强,李大勇,等.基于风速升降特性及支持向量机理论的异常数据重构算法[J].电力系统保护与控制,2018,46(16):31-37.[点击复制] |
| YANG Mao,ZHAI Guanqiang,LI Dayong,et al.An algorithm of abnormal data reconstruction based on RISE-FALL-feature of the wind speed and support vector machine[J].Power System Protection and Control,2018,46(16):31-37[点击复制] |
|
| |
|
|
| 本文已被：浏览 4468次 下载 1816次 |
码上扫一扫！ |
| 基于风速升降特性及支持向量机理论的异常数据重构算法 |
| 杨茂,翟冠强,李大勇,苏欣,翟玉成 |
|
|
| (现代电力系统仿真控制与绿色电能新技术吉林省重点实验室东北电力大学，吉林 吉林 132012;国网吉林省电力有限公司通化供电公司，吉林 通化 130022;东北电力大学理学院，吉林 吉林 132012;国网吉林省长春市双阳区供电公司，吉林 长春 130600) |
|
| 摘要: |
| 风电机组历史功率数据是进行风电研究的重要基础，而风电机组实际采集到的数据中存在大量的异常数据，这给风电功率预测研究带来许多不利影响。对历史数据的风速-功率对应关系进行研究，识别并剔除异常数据。分析风速升降变化对功率的影响，建立SVM数据重构模型。根据风速升降特性及强相关风电机组的出力特性对数据重构模型加以改进。以风电机组的实测数据为例进行仿真计算，结果表明所述方法能够对异常数据进行有效地识别和重构。 |
| 关键词: 风电功率 异常数据 重构 SVM 风速升降特性 |
| DOI：10.7667/PSPC171181 |
| 投稿时间：2017-08-07修订日期：2017-10-02 |
| 基金项目:国家重点研发计划项目课题资助(2018YFB0904200) |
|
| An algorithm of abnormal data reconstruction based on RISE-FALL-feature of the wind speed and support vector machine |
| YANG Mao,ZHAI Guanqiang,LI Dayong,SU Xin,ZHAI Yucheng |
| (Modern Power System Simulation Control & Renewable Energy Technology, Jilin Province Key Laboratory Northeast Electric Power University, Jilin 132012, China;State Grid Jilin Electric Power Co., Ltd., Tonghua Power Supply Company, Tonghua 130022, China;College of Science, Northeast Electric Power University, Jilin 132012, China;Changchun Power Supply Company, State Grid Jilin Electric Power Co., Ltd., Changchun 130600, China) |
| Abstract: |
| The historical power data of wind turbine is the important foundation for the study of wind power. However, amounts of data collected from wind farms usually contain abnormal data, which has adverse effects on the wind power prediction. First, the wind speed-power correspondence of historical data is studied, and the abnormal data is identified and eliminated. The influence of RISE-FALL-feature of the wind speed on the power is analyzed, and the SVM data reconstruction model is established. A data reconstruction model is improved based on the RISE-FALL-feature of the wind speed and the output characteristics of the correlation wind turbine. Taking the measured data of wind turbine as an example, the simulation results show that the method described in this paper can effectively identify and reconstruct the abnormal data. This work is supported by National Key Research and Development project of China (No. 2018YFB0904200). |
| Key words: wind power abnormal data reconstruction SVM RISE-FALL-feature of the wind speed |
|
|
|
|
|
