基于ASD-KDE的风电出力超短期区间预测
|
摘要
为提高含风电场电网经济调度能力、降低电力系统规划决策的保守性,构建了原子稀疏分解-二维核密度估计(ASD-KDE)模型对风电出力进行区间预测。该方法在采用小波-原子稀疏分解(WD-ASD)预测模型得出点预测值及预测误差的基础上,通过摇摆窗函数将历史风电数据划分为多个波动区间,使用二维核密度估计(KDE)模型逐步滚动获取预测值置信区间。实际风电场算例验证了该模型的自适应性、快速性、有效性及可信性,得到的区间可信度高,可为调度部门提供更多不确定信息,使风电资源得到有效利用。
In order to improve the economic operation ability of wind power system and reduce the conservatism of power system planning and decision making, a ultra-short term wind power output interval forecast model based on atomic sparse decomposition and kernel density estimation(ASD-KDE)is proposed in this paper.Based on the wavelet decomposition-atomic sparse decomposition(WD-ASD)prediction model to obtain the point prediction value and prediction error, the method uses the swing window function to divide the historical wind power data into multiple fluctuation intervals, and the two dimensional kernel density estimation(KDE) model is used to get the confidence interval of the predicted value.The proposed approach is verified by the actual wind power farm example,simulation results show the adaptivity, rapidity and effectiveness of this method.In addition, the obtained interval reliability is accurate, which can provide more uncertain information for the scheduling and make the wind power resource to be utilized effectively.
In order to improve the economic operation ability of wind power system and reduce the conservatism of power system planning and decision making, a ultra-short term wind power output interval forecast model based on atomic sparse decomposition and kernel density estimation(ASD-KDE)is proposed in this paper.Based on the wavelet decomposition-atomic sparse decomposition(WD-ASD)prediction model to obtain the point prediction value and prediction error, the method uses the swing window function to divide the historical wind power data into multiple fluctuation intervals, and the two dimensional kernel density estimation(KDE) model is used to get the confidence interval of the predicted value.The proposed approach is verified by the actual wind power farm example,simulation results show the adaptivity, rapidity and effectiveness of this method.In addition, the obtained interval reliability is accurate, which can provide more uncertain information for the scheduling and make the wind power resource to be utilized effectively.
引文
[1]童光毅.关于当代能源转型方向的探讨[J].智慧电力,2018,46(10):1-3.TONG Guangyi. Probe into Modern Energy Structure Transition[J]. Smart Power,2018,46(10):1-3.
[2]靳春旭,董福贵.长期风电负荷预测方法比较[J].广东电力,2018, 31(9):70-76.JIN Chunxu, DONG Fugui. Comparison of prediction methods for long-term wind power load[J].Guangdong Electric Power, 2018,31(9):70-76.
[3] LANDBERG L, WATSON S J. Short-term prediction of local wind conditions[J]. Boundary-Layer Meteorology,1994,70(1-2):171-195.
[4]李丹,任洲洋,颜伟,等.基于因子分析和神经网络分位数回归的月度风电功率曲线概率预测[J].中国电机工程学报,2017, 37(18):5238-5247+5522.LI Dan, REN Zhouyang, YAN Wei, et al. Month-ahead wind Power curve probabilistic prediction based on factor analysis and quantile regression neural network[J].Proceedings of the CSEE, 2017, 37(18):5238-5247+5522.
[5]欧阳庭辉,查晓明,秦亮,等.含核函数切换的风电功率短期预测新方法[J].电力自动化设备,2016, 36(9):80-86.OUYANG Tinghui, ZHA Xiaoming, QIN Liang, et al.Short-term wind power prediction based on kernel function switching[J]. Electric Power Automation Equipment,2016, 36(9):80-86.
[6]陈昊,高山,王玉荣,等.基于广义自回归条件异方差偏度峰度模型的风电功率预测方法[J].中国电机工程学报,2017, 37(12):3456-3461+3673.CHEN Hao, GAO Shan, WANG Yurong, et al. Wind power forecasting method based on generalized autoregressive conditional heteroskedasticity with skewness and kurtosis model[J].Proceedings of the CSEE,2017, 37(12):3456-3461+3673.
[7]兰飞,桑川川,梁浚杰,等.基于条件Copula函数的风电功率区间预测[J].中国电机工程学报,2016, 36(S1):79-86.LAN Fei, SANG Chuanchuan, LIANG Junjie, et al.Interval prediction for wind power based on conditional copula function[J]. Proceedings of the CSEE, 2016, 36(SI):79-86.
[8]李智,韩学山,杨明,等.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, 35(3):83-87.LI Zhi, HAN Xueshan, YANG Ming, et al. Wind power fluctuation interval analysis based on quantile regression[J]. Automation of Electric Power Systems, 2011, 35(3):83-87.
[9]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, 31(25):10-16.ZHOU Songlin, MAO Meiqin, SU Jianhui. Short-term forecasting of wind power and non-parametric confidence interval estimation[J]. Proceedings of the CSEE, 2011, 31(25):10-16.
[10]吴晓刚,孙荣富,乔颖,等.基于风电场功率特性的风电预测误差分布估计[J].电网技术,2017,41(6):1801-1807.WU Xiaogang, SUN Rongfu, QIAO Ying, et al.Estimation of error distribution for wind power prediction based on power curves of wind farms[J].Power System Technology,2017,41(6):1801-1807.
[11]胡亚伟,王筱,晁勤,等.采用横纵向误差平移插值修正的风电预测精度改善方法[J].电网技术,2015, 39(10):2758-2765.HU Yawei, WANG Xiao, CHAO Qin. A forecasting accuracy improvement method for wind power based onphase and level errors translating and interpolating correction[J]. Power System Technology, 2015, 39(10):2758-2765.
[12]曲正伟,张坤,王云静,等.基于小波-原子分解的超短期风电出力预测模型[J].仪器仪表学报,2016, 37(10):2251-2258.QU Zhengwei, ZHANG Kun, WANG Yunjing, et al.Ultra short-term wind power output forecast model based on wavelet decomposition and atomic decomposition[J].Chinese Journal of Scientific Instrument, 2016, 37(10):2251-2258.
[13]黄坡,朱小帆,查晓明,等.基于波动过程聚类的风电功率预测极大误差估计方法[J].电力系统保护与控制,2016,44(13):130-136.HUANG Po, ZHU Xiaofan, ZHA Xiaoming, et al. An estimation method for wind power prediction great error based on clustering fluctuation process[J]. Power System Protection and Control,2016,44(13):130-136.
[14]甘迪,柯德平,孙元章,等.考虑爬坡特性的短期风电功率概率预测[J].电力自动化设备,2016, 36(4):145-150.GAN Di,KE Deping,SUN Yuanzhang, et al. Short-term probabilistic wind power forecast considering ramp characteristics[J]. Electric Power Automation Equipment,2016, 36(4):145-150.
[15]许丹,黄利军,李献伟,等.基于小波变换的抗噪声电压暂降检测方法研究[J].供用电,2018, 35(2):57-62.XU Dan, HUANG Lijun, LI Xianwei, et al.The study of voltage sag detection method with anti-noise feature based on wavelet transform[J]. Distribution&Utilization, 2018,35(2):57-62.
[16]蒋平,史豪,吴照.风电功率波动引发的强迫振荡扰动源定位方法[J].电力工程技术,2018,37(5):1-6.JIANG Ping, SHI Hao, WU Zhao. Localizing disturbance source of power systerm forced oscillation caused by wind power fluctuation[J]. Electric Power Engineering Technology,2018,37(5):1-6.
[17]郭森.基于BN分解和ALO优化LSSVM模型的风电出力预测[J].智慧电力,2017,45(7):92-99.GUO Sen, Wind power forecasting based on BN decomposition and LSSVM mothod optimized by ALO[J].Smart Power, 2017,45(7):92-99.
[18] SIDERATOS G, HATZIARGYRIOU N D. Probabilistic wind power forecasting using radial basis function neural networks[J]. IEEE Transactions on Power Systems, 2012,27(4):1788-1796.
[2]靳春旭,董福贵.长期风电负荷预测方法比较[J].广东电力,2018, 31(9):70-76.JIN Chunxu, DONG Fugui. Comparison of prediction methods for long-term wind power load[J].Guangdong Electric Power, 2018,31(9):70-76.
[3] LANDBERG L, WATSON S J. Short-term prediction of local wind conditions[J]. Boundary-Layer Meteorology,1994,70(1-2):171-195.
[4]李丹,任洲洋,颜伟,等.基于因子分析和神经网络分位数回归的月度风电功率曲线概率预测[J].中国电机工程学报,2017, 37(18):5238-5247+5522.LI Dan, REN Zhouyang, YAN Wei, et al. Month-ahead wind Power curve probabilistic prediction based on factor analysis and quantile regression neural network[J].Proceedings of the CSEE, 2017, 37(18):5238-5247+5522.
[5]欧阳庭辉,查晓明,秦亮,等.含核函数切换的风电功率短期预测新方法[J].电力自动化设备,2016, 36(9):80-86.OUYANG Tinghui, ZHA Xiaoming, QIN Liang, et al.Short-term wind power prediction based on kernel function switching[J]. Electric Power Automation Equipment,2016, 36(9):80-86.
[6]陈昊,高山,王玉荣,等.基于广义自回归条件异方差偏度峰度模型的风电功率预测方法[J].中国电机工程学报,2017, 37(12):3456-3461+3673.CHEN Hao, GAO Shan, WANG Yurong, et al. Wind power forecasting method based on generalized autoregressive conditional heteroskedasticity with skewness and kurtosis model[J].Proceedings of the CSEE,2017, 37(12):3456-3461+3673.
[7]兰飞,桑川川,梁浚杰,等.基于条件Copula函数的风电功率区间预测[J].中国电机工程学报,2016, 36(S1):79-86.LAN Fei, SANG Chuanchuan, LIANG Junjie, et al.Interval prediction for wind power based on conditional copula function[J]. Proceedings of the CSEE, 2016, 36(SI):79-86.
[8]李智,韩学山,杨明,等.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, 35(3):83-87.LI Zhi, HAN Xueshan, YANG Ming, et al. Wind power fluctuation interval analysis based on quantile regression[J]. Automation of Electric Power Systems, 2011, 35(3):83-87.
[9]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, 31(25):10-16.ZHOU Songlin, MAO Meiqin, SU Jianhui. Short-term forecasting of wind power and non-parametric confidence interval estimation[J]. Proceedings of the CSEE, 2011, 31(25):10-16.
[10]吴晓刚,孙荣富,乔颖,等.基于风电场功率特性的风电预测误差分布估计[J].电网技术,2017,41(6):1801-1807.WU Xiaogang, SUN Rongfu, QIAO Ying, et al.Estimation of error distribution for wind power prediction based on power curves of wind farms[J].Power System Technology,2017,41(6):1801-1807.
[11]胡亚伟,王筱,晁勤,等.采用横纵向误差平移插值修正的风电预测精度改善方法[J].电网技术,2015, 39(10):2758-2765.HU Yawei, WANG Xiao, CHAO Qin. A forecasting accuracy improvement method for wind power based onphase and level errors translating and interpolating correction[J]. Power System Technology, 2015, 39(10):2758-2765.
[12]曲正伟,张坤,王云静,等.基于小波-原子分解的超短期风电出力预测模型[J].仪器仪表学报,2016, 37(10):2251-2258.QU Zhengwei, ZHANG Kun, WANG Yunjing, et al.Ultra short-term wind power output forecast model based on wavelet decomposition and atomic decomposition[J].Chinese Journal of Scientific Instrument, 2016, 37(10):2251-2258.
[13]黄坡,朱小帆,查晓明,等.基于波动过程聚类的风电功率预测极大误差估计方法[J].电力系统保护与控制,2016,44(13):130-136.HUANG Po, ZHU Xiaofan, ZHA Xiaoming, et al. An estimation method for wind power prediction great error based on clustering fluctuation process[J]. Power System Protection and Control,2016,44(13):130-136.
[14]甘迪,柯德平,孙元章,等.考虑爬坡特性的短期风电功率概率预测[J].电力自动化设备,2016, 36(4):145-150.GAN Di,KE Deping,SUN Yuanzhang, et al. Short-term probabilistic wind power forecast considering ramp characteristics[J]. Electric Power Automation Equipment,2016, 36(4):145-150.
[15]许丹,黄利军,李献伟,等.基于小波变换的抗噪声电压暂降检测方法研究[J].供用电,2018, 35(2):57-62.XU Dan, HUANG Lijun, LI Xianwei, et al.The study of voltage sag detection method with anti-noise feature based on wavelet transform[J]. Distribution&Utilization, 2018,35(2):57-62.
[16]蒋平,史豪,吴照.风电功率波动引发的强迫振荡扰动源定位方法[J].电力工程技术,2018,37(5):1-6.JIANG Ping, SHI Hao, WU Zhao. Localizing disturbance source of power systerm forced oscillation caused by wind power fluctuation[J]. Electric Power Engineering Technology,2018,37(5):1-6.
[17]郭森.基于BN分解和ALO优化LSSVM模型的风电出力预测[J].智慧电力,2017,45(7):92-99.GUO Sen, Wind power forecasting based on BN decomposition and LSSVM mothod optimized by ALO[J].Smart Power, 2017,45(7):92-99.
[18] SIDERATOS G, HATZIARGYRIOU N D. Probabilistic wind power forecasting using radial basis function neural networks[J]. IEEE Transactions on Power Systems, 2012,27(4):1788-1796.