文档介绍：基于粗糙集理论的中长期风速预测
32
第 32 卷第 1 期 2012 年 1 月 5 日
中
国电机工程学 Proceedings of the CSEE 中图分类号:TM 71
报
, 2012 ©2012 . 学科分类号:470×40
文章编号:0258-8013 (2012) 01-0032-06
文献标志码:A
基于粗糙集理论的中长期风速预测
高爽 1,冬雷 1,高阳 2,廖晓钟 1
(,北京市海淀区 100081; ,辽宁省沈阳市 110136)
Mid-long Term Wind Speed Prediction Based on Rough Set Theory
GAO Shuang1, DONG Lei1, GAO Yang2, LIAO Xiaozhong1
(1. School of Automation, Beijing Institute of Technology, Haidian District, Beijing 100081, China; 2. Department of Electrical Engineering, Shenyang Institute of Engineering, Shenyang 110136, Liaoning Province, China) ABSTRACT: In mid-long term wind speed prediction, dealing with the relevant factors correctly is the key point to improve the prediction accuracy. A new prediction scheme that uses rough set method was presented. The key factors that affect the wind speed prediction were identified by rough set theory. Then the rough set work prediction model was built by adding the key factors as the additional inputs to the pure chaos work model. To test the approach, the data from a wind farm of Heilongjiang province were used. The prediction results were presented pared to the chaos work model and persistence model. The results show that the prediction accuracy of rough set method is the best, and rough set method is a useful tool in mid-long term wind speed prediction. KEY WORDS: wind speed prediction; rough set; chaos work; persistence model
摘要: 在中长期风速预测中, 正确处理相关因素的影响是提高风速预测精度的关键。该文提出一种粗糙集理论预测方法。利用粗糙集理论分析出风速预测的主要影响因素, 将其作为中长期风速预测模型的附加输入, 建立粗糙集神经网络预测模型。利用黑龙江某风电场的数据进行训练和预测, 并将预测结果与单纯的混沌神经网络预测方法和持续模型方法进行对比, 结果表明, 粗糙集神经网络模型的预测精度最高。粗糙集方法在中长期风速预测中将是一个有用的工具。关键词:风速预测;粗糙集;混沌神经网络;持续模型
量约为 ´10 9 MW,其中可利用的风能为 2´ 107 MW。中国风能储量很大、分布面广,开发利用潜力巨大。装机 2010 年中国新增安装风电机组 12 904 台, 容量 18 MW,年同比增长 %;累计安装风电机组 34 485 台,装机容量 44 MW,年同比增长 %,继续位居全球之首。由于风力发电是一种间歇性能源,风电场的功其输出功率的波动范率输出具有很强的随机性[1-2], 围通常较大,速度较快,导致电网调峰、无功及电压控制十分困难,给电网的安全稳定及正常调度带来新的问题。当风