摘要
风电场短期风速区间预测对风电场与电力系统的协调运行具有重要意义,基于模糊信息粒化和最小二乘支持向量机提出了一种短期风速区间预测算法。首先对风速时间序列进行Witold Pedrycz模糊信息粒化,得到3个模糊粒子Low、R和Up,分别代表风速区间的最小值、变化趋势和最大值,然后利用最小二乘支持向量机回归预测模型对粒化数据进行回归预测。实例分析结果表明,该算法提高了预测精度和效率,可以有效地预测风电场短期风速的变化区间和变化趋势。
Interval prediction of short-term wind speed in wind farm is significant for wind farm and the power system stable operation. A short-term wind speed interval prediction algorithm is proposed by using the fuzzy information granulation and LS-SVM. This paper conducted the time series of daily wind speed with Witold Pedrycz fuzzy information granulation which provided three parameters Low, R and Up respectively represented the minimum value,the change trend and the maximum value, and did the regression forecasting of the data after granulation with the least squares support vector machine （KS-SVM）prediction model The results of the case analysis show that the granulation improves the precision and efficiency, and can effectively predict the change interval and change trend of shortterm wind speed in wind farm.
出处
《电力系统及其自动化学报》
CSCD
北大核心
2015年第9期47-52,共6页
Proceedings of the CSU-EPSA
基金
国家自然科学基金资助项目(51267012)
甘肃省电网公司科技项目(2010406029)
甘肃省高等学校基本科研业务费专项资金项目(1103ZTC141)
关键词
风力发电
风速区间预测
模糊信息粒化
最小二乘支持向量机
wind power generation
wind speed interval prediction
fuzzy information granulation
least squares support vector machine
