一种风电功率混沌时间序列概率区间简易预测模型
发布时间:2019-07-08 17:32
【摘要】:本文基于极限学习机构建了一种简易模型以直接输出风电功率概率区间.同时,为优化模型训练过程中输出区间的性能,本文基于对数据集区间带偏差信息的分析构建了一种新的优化准则,并采用量子细菌觅食优化算法以获取问题的最优解,提高模型泛化能力.对比分析两个风电场在不同置信水平和不同优化准则下的概率预测结果,仿真表明本文模型具有更高的可靠性和更窄的区间带宽,可为风电并网安全稳定运行提供决策支持.
[Abstract]:In this paper, a simple model is established based on the limit learning mechanism to directly output the probability range of wind power. At the same time, in order to optimize the performance of the output interval in the process of model training, a new optimization criterion is constructed based on the analysis of the interval deviation information of the data set, and the quantum bacteria foraging optimization algorithm is used to obtain the optimal solution of the problem and improve the generalization ability of the model. The probability prediction results of two wind farms under different confidence levels and different optimization criteria are compared and analyzed. The simulation results show that the model has higher reliability and narrower interval bandwidth, which can provide decision support for the safe and stable operation of wind power grid connection.
【作者单位】: 华中科技大学水电与数字化工程学院;西澳大利亚大学电气电子及计算机学院;
【基金】:国家自然科学基金(批准号:51379081) 湖北省自然科学基金(批准号:2011CDA032)资助的课题~~
【分类号】:TM614
[Abstract]:In this paper, a simple model is established based on the limit learning mechanism to directly output the probability range of wind power. At the same time, in order to optimize the performance of the output interval in the process of model training, a new optimization criterion is constructed based on the analysis of the interval deviation information of the data set, and the quantum bacteria foraging optimization algorithm is used to obtain the optimal solution of the problem and improve the generalization ability of the model. The probability prediction results of two wind farms under different confidence levels and different optimization criteria are compared and analyzed. The simulation results show that the model has higher reliability and narrower interval bandwidth, which can provide decision support for the safe and stable operation of wind power grid connection.
【作者单位】: 华中科技大学水电与数字化工程学院;西澳大利亚大学电气电子及计算机学院;
【基金】:国家自然科学基金(批准号:51379081) 湖北省自然科学基金(批准号:2011CDA032)资助的课题~~
【分类号】:TM614
【参考文献】
相关期刊论文 前9条
1 李智;韩学山;杨明;钟世民;;基于分位点回归的风电功率波动区间分析[J];电力系统自动化;2011年03期
2 方伟;孙俊;谢振平;须文波;;量子粒子群优化算法的收敛性分析及控制参数研究[J];物理学报;2010年06期
3 高光勇;蒋国平;;采用优化极限学习机的多变量混沌时间序列预测[J];物理学报;2012年04期
4 周松林;茆美琴;苏建徽;;风电功率短期预测及非参数区间估计[J];中国电机工程学报;2011年25期
5 张学清;梁军;;风电功率时间序列混沌特性分析及预测模型研究[J];物理学报;2012年19期
6 吴小珊;张步涵;袁小明;李高望;罗钢;周杨;;求解含风电场的电力系统机组组合问题的改进量子离散粒子群优化方法[J];中国电机工程学报;2013年04期
7 张学清;梁军;;基于EEMD-近似熵和储备池的风电功率混沌时间序列预测模型[J];物理学报;2013年05期
8 王新迎;韩敏;;基于极端学习机的多变量混沌时间序列预测[J];物理学报;2012年08期
9 刘德伟;郭剑波;黄越辉;王伟胜;;基于风电功率概率预测和运行风险约束的含风电场电力系统动态经济调度[J];中国电机工程学报;2013年16期
【共引文献】
相关期刊论文 前10条
1 张朝龙;江巨浪;李彦梅;陈世军;gだ,
本文编号:2511757
本文链接:https://www.wllwen.com/kejilunwen/dianlilw/2511757.html
教材专著