基于短期风功率预测的数据预处理算法研究
|
摘要
针对实测风速和功率数据中包含奇异点以及同一风速下风功率存在较大范围波动的问题,文章提出一种数据预处理算法。首先,采用拉依达准则剔除风速和功率奇异点;再使用优化的一次指数平滑法及最大皮尔逊相关系数对风速进行平滑处理;最后,利用新疆阿勒泰地区某风电场单台风机的实测数据进行验证分析。以文章提出的预处理方法得到的风速作为BP神经网络预测模型的输入,风功率的预测准确度显著高于已有预处理方法得到的结果。
Aiming at the problem that the measured wind speed and power data contain singular points and there exists fluctuations in wind power at the same wind speed, a data preprocessing algorithm is proposed. Firstly, the Pauta criterion is adopted to eliminate wind speed and power singularities. Then, the improved single exponential smoothing and maximum Pearson correlation coefficient are used to smooth wind speeds. Finally, the measured data of a single wind turbine of a wind farm in the Altay region of Xinjiang were used for verification and analysis. The wind speed obtained by the pretreatment method proposed in this paper is taken as the input of BP neural network prediction model, and the prediction accuracy of wind power is significantly higher than that obtained by the existing pretreatment method.
Aiming at the problem that the measured wind speed and power data contain singular points and there exists fluctuations in wind power at the same wind speed, a data preprocessing algorithm is proposed. Firstly, the Pauta criterion is adopted to eliminate wind speed and power singularities. Then, the improved single exponential smoothing and maximum Pearson correlation coefficient are used to smooth wind speeds. Finally, the measured data of a single wind turbine of a wind farm in the Altay region of Xinjiang were used for verification and analysis. The wind speed obtained by the pretreatment method proposed in this paper is taken as the input of BP neural network prediction model, and the prediction accuracy of wind power is significantly higher than that obtained by the existing pretreatment method.
引文
[1]张丽英,叶廷路,辛耀中,等.大规模风电接入电网的相关问题及措施[J].中国电机工程学报,2010,30(25):1-9.
[2]张文秀,武新芳,陆豪乾.风电功率预测技术综述与改进建议[J].电力与能源,2014,35(4):436-441.
[3]戚双斌,王维庆,张新燕.基于支持向量机的风速与风功率预测方法研究[J].华东电力,2009,37(9):1600-1603.
[4]罗毅,刘峰,刘向杰.基于主成分—遗传神经网络的短期风电功率预测[J].电力系统保护与控制,2012(23):47-53.
[5] Guo Zhenhai, Zhao Weigang, Lu Haiyan, et al.Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model[J].Renewable Energy,2012,37(1):241-249.
[6]张国强,张伯明.基于组合预测的风电场风速及风电机功率预测[J].电力系统自动化,2009,33(18):92-95.
[7]卢芸,刘金强,滕予非,等.基于最优平滑阶数的风电功率曲线建模策略研究[J].现代电力,2018(1):14-18.
[8] Bai Feifei,Liu Yong,Liu Yilu,et al.Measurement based correlation approach for power system dynamic response estimation[J].Generation Transmission&Distribution Iet,2015,9(12):1474-1484.
[9] Y R Ding,Y J Cai,P D Sun,et al.The use of combined neural networks and genetic algorithms for prediction of river water quality[J].Journal of Applied Research&Technology,2014,12(3):493-499.
[10]王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版),2012(5):837-841.
[2]张文秀,武新芳,陆豪乾.风电功率预测技术综述与改进建议[J].电力与能源,2014,35(4):436-441.
[3]戚双斌,王维庆,张新燕.基于支持向量机的风速与风功率预测方法研究[J].华东电力,2009,37(9):1600-1603.
[4]罗毅,刘峰,刘向杰.基于主成分—遗传神经网络的短期风电功率预测[J].电力系统保护与控制,2012(23):47-53.
[5] Guo Zhenhai, Zhao Weigang, Lu Haiyan, et al.Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model[J].Renewable Energy,2012,37(1):241-249.
[6]张国强,张伯明.基于组合预测的风电场风速及风电机功率预测[J].电力系统自动化,2009,33(18):92-95.
[7]卢芸,刘金强,滕予非,等.基于最优平滑阶数的风电功率曲线建模策略研究[J].现代电力,2018(1):14-18.
[8] Bai Feifei,Liu Yong,Liu Yilu,et al.Measurement based correlation approach for power system dynamic response estimation[J].Generation Transmission&Distribution Iet,2015,9(12):1474-1484.
[9] Y R Ding,Y J Cai,P D Sun,et al.The use of combined neural networks and genetic algorithms for prediction of river water quality[J].Journal of Applied Research&Technology,2014,12(3):493-499.
[10]王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版),2012(5):837-841.