基于风速升降特性及支持向量机理论的异常数据重构算法
|
摘要
风电机组历史功率数据是进行风电研究的重要基础,而风电机组实际采集到的数据中存在大量的异常数据,这给风电功率预测研究带来许多不利影响。对历史数据的风速-功率对应关系进行研究,识别并剔除异常数据。分析风速升降变化对功率的影响,建立SVM数据重构模型。根据风速升降特性及强相关风电机组的出力特性对数据重构模型加以改进。以风电机组的实测数据为例进行仿真计算,结果表明所述方法能够对异常数据进行有效地识别和重构。
The historical power data of wind turbine is the important foundation for the study of wind power. However, amounts of data collected from wind farms usually contain abnormal data, which has adverse effects on the wind power prediction. First, the wind speed-power correspondence of historical data is studied, and the abnormal data is identified and eliminated. The influence of RISE-FALL-feature of the wind speed on the power is analyzed, and the SVM data reconstruction model is established. A data reconstruction model is improved based on the RISE-FALL-feature of the wind speed and the output characteristics of the correlation wind turbine. Taking the measured data of wind turbine as an example, the simulation results show that the method described in this paper can effectively identify and reconstruct the abnormal data.
The historical power data of wind turbine is the important foundation for the study of wind power. However, amounts of data collected from wind farms usually contain abnormal data, which has adverse effects on the wind power prediction. First, the wind speed-power correspondence of historical data is studied, and the abnormal data is identified and eliminated. The influence of RISE-FALL-feature of the wind speed on the power is analyzed, and the SVM data reconstruction model is established. A data reconstruction model is improved based on the RISE-FALL-feature of the wind speed and the output characteristics of the correlation wind turbine. Taking the measured data of wind turbine as an example, the simulation results show that the method described in this paper can effectively identify and reconstruct the abnormal data.
引文
[1]蒋程,刘文霞,张建华,等.含风电接入的发输电系统风险评估[J].电工技术学报,2014,29(2):260-270.JIANG Cheng,LIU Wenxia,ZHANG Jianhua,et al.Risk assessment of generation and transmission systems considering wind power penetration[J].Transactions of China Electrotechnical Society,2014,29(2):260-270.
[2]吴金浩,杨秀媛,孙骏.基于主成分分析法的风电功率短期组合预测[J].电气技术,2016,17(7):41-47.WU Jinhao,YANG Xiuyuan,SUN Jun.Short term combined forecasting of wind power based on principal component analysis[J].Electrical Engineering,2016,17(7):41-47.
[3]刘波,贺志佳,金昊.风力发电现状与发展趋势[J].东北电力大学学报,2016,36(2):7-13.LIU Bo,HE Zhijia,JIN Hao.Wind power status and development trends[J].Journal of Northeast Electric Power University,2016,36(2):7-13.
[4]杨德友,蔡国伟.基于因散经验模式分解与最小二乘支持向量机的风电场短期风速预测[J].东北电力大学学报,2015,35(3):44-49.YANG Deyou,CAI Guowei.The short-term wind speed forecasting for wind farm based on EEMD and LS_SVM[J].Journal of Northeast Dianli University,2015,35(3):44-49.
[5]边晓燕,王本利,陈建平,等.改进的DFIG与VSCHVDC协调控制改善风电场低电压穿越能力[J].电力系统保护与控制,2016,44(1):9-16.BIAN Xiaoyan,WANG Benli,CHEN Jianping,et al.Improvement of low voltage ride through capability of wind farm using coordinated control of the improved DFIG and VSC-HVDC[J].Power System Protection and Control,2016,44(1):9-16.
[6]杨茂,季本明.基于局域一阶加权法的风电功率超短期预测研究[J].东北电力大学学报,2015,35(5):6-10.YANG Mao,JI Benming.The ultra-short-term forecasting of wind power based on local one-order weighted method[J].Journal of Northeast Dianli University,2015,35(5):6-10.
[7]吕泉,王伟,韩水,等.基于调峰能力分析的电网弃风情况评估方法[J].电网技术,2013,37(7):1-8.LüQuan,WANG Wei,HAN Shui,et al.A new evaluation method for wind power curtailment based on analysis of system regulation capability[J].Power System Technology,2013,37(7):1-8.
[8]赵永宁,叶林,朱倩雯.风电场弃风异常数据簇的特征及处理方法[J].电力系统自动化,2014,38(21):39-46.ZHAO Yongning,YE Lin,ZHU Qianwen.Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms[J].Automation of Electric Power Systems,2014,38(21):39-46.
[9]娄建楼,胥佳,陆恒,等.基于功率曲线的风电机组数据清洗算法[J].电力系统自动化,2016,40(10):116-121.LOU Jianlou,XU Jia,LU Heng,et al.Wind turbine data-cleaning algorithm based on power curve[J].Automation of Electric Power Systems,2016,40(10):116-121.
[10]SCHLECHTINGEN M,SANTOS I F,ACHICHE S.Using data-mining approaches for wind turbine power curve monitoring:a comparative study[J].IEEE Transactions on Sustainable Energy,2013,4(3):671-679.
[11]朱倩雯,叶林,赵永宁,等.风电场输出功率异常数据识别与重构方法研究[J].电力系统保护与控制,2015,43(3):38-45.ZHU Qianwen,YE Lin,ZHAO Yongning,et al.Methods for elimination and reconstruction of abnormal power data in wind farms[J].Power System Protection and Control,2015,43(3):38-45.
[12]张东英,李伟花,刘燕华,等.风电场有功功率异常运行数据重构方法[J].电力系统自动化,2014,38(5):14-18,24.ZHANG Dongying,LI Weihua,LIU Yanhua,et al.Photovolatic generation forecast based on multidimensional time-series local support vector regression in microgrids[J].Automation of Electric Power Systems,2014,38(5):14-18,24.
[13]杨茂,孙涌,孙兆键,等.风电场大规模数据管理系统设计与研发[J].东北电力大学学报,2014,34(2):27-31.YANG Mao,SUN Yong,SUN Zhaojian,et al.Design and development of large-scale data management system of wind farm[J].Journal of Northeast Dianli University,2013,34(2):27-31.
[14]叶小岭,陈浩,郭晓杰,等.基于风速升降特性的短期风电功率预测[J].电力系统保护与控制,2016,44(19):56-62.YE Xiaoling,CHEN Hao,GUO Xiaojie,et al.Short-term wind power prediction based on the UP-DOWN-features of wind speed[J].Power System Protection and Control,2016,44(19):56-62.
[15]邱宜彬,欧阳誉波,李奇,等.考虑多风电场相关性的场景概率潮流计算及无功优化[J].电力系统保护与控制,2017,45(2):61-68.QIU Yibin,OUYANG Yubo,LI Qi,et al.Scenario probabilistic load flow calculation and reactive power optimization considering wind farms correlation[J].Power System Protection and Control,2017,45(2):61-68.
[16]徐玉琴,陈坤,李俊卿,等.Copula函数与核估计理论相结合分析风电场出力相关性的一种新方法[J].电工技术学报,2016,31(13):92-100.XU Yuqin,CHEN Kun,LI Junqing,et al.A new method analyzing output correlation of multi-wind farms based on combination of copula function and kernel estimation theory[J].Transactions of China Electrotechnical Society,2016,31(13):92-100.
[17]龚莺飞,鲁宗相,乔颖,等.基于Copula理论的光伏功率高比例异常数据机器识别算法[J].电力系统自动化,2016,40(9):16-22,55.GONG Yingfei,LU Zongxiang,QIAO Ying,et al.Copula theory based machine identification algorithm of high proportion of outliers in photovoltaic power date[J].Automation of Electric Power Systems,2016,40(9):16-22,55.
[18]叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.YE Lin,LIU Peng.Combined model based on EMD-SVM for short-term wind power prediction[J].Proceedings of the CSEE,2011,31(31):102-108.
[19]刘红柳,杨茂.基于小波变换和支持向量机的风电功率爬坡事件识别与预测[J].东北电力大学学报,2016,36(6):30-35.LIU Hongliu,YANG Mao.An approach for wind power climbing event identificationand prediction based on wavelet and SVM[J].Journal of Northeast Electric Power University,2016,36(6):30-35.
[2]吴金浩,杨秀媛,孙骏.基于主成分分析法的风电功率短期组合预测[J].电气技术,2016,17(7):41-47.WU Jinhao,YANG Xiuyuan,SUN Jun.Short term combined forecasting of wind power based on principal component analysis[J].Electrical Engineering,2016,17(7):41-47.
[3]刘波,贺志佳,金昊.风力发电现状与发展趋势[J].东北电力大学学报,2016,36(2):7-13.LIU Bo,HE Zhijia,JIN Hao.Wind power status and development trends[J].Journal of Northeast Electric Power University,2016,36(2):7-13.
[4]杨德友,蔡国伟.基于因散经验模式分解与最小二乘支持向量机的风电场短期风速预测[J].东北电力大学学报,2015,35(3):44-49.YANG Deyou,CAI Guowei.The short-term wind speed forecasting for wind farm based on EEMD and LS_SVM[J].Journal of Northeast Dianli University,2015,35(3):44-49.
[5]边晓燕,王本利,陈建平,等.改进的DFIG与VSCHVDC协调控制改善风电场低电压穿越能力[J].电力系统保护与控制,2016,44(1):9-16.BIAN Xiaoyan,WANG Benli,CHEN Jianping,et al.Improvement of low voltage ride through capability of wind farm using coordinated control of the improved DFIG and VSC-HVDC[J].Power System Protection and Control,2016,44(1):9-16.
[6]杨茂,季本明.基于局域一阶加权法的风电功率超短期预测研究[J].东北电力大学学报,2015,35(5):6-10.YANG Mao,JI Benming.The ultra-short-term forecasting of wind power based on local one-order weighted method[J].Journal of Northeast Dianli University,2015,35(5):6-10.
[7]吕泉,王伟,韩水,等.基于调峰能力分析的电网弃风情况评估方法[J].电网技术,2013,37(7):1-8.LüQuan,WANG Wei,HAN Shui,et al.A new evaluation method for wind power curtailment based on analysis of system regulation capability[J].Power System Technology,2013,37(7):1-8.
[8]赵永宁,叶林,朱倩雯.风电场弃风异常数据簇的特征及处理方法[J].电力系统自动化,2014,38(21):39-46.ZHAO Yongning,YE Lin,ZHU Qianwen.Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms[J].Automation of Electric Power Systems,2014,38(21):39-46.
[9]娄建楼,胥佳,陆恒,等.基于功率曲线的风电机组数据清洗算法[J].电力系统自动化,2016,40(10):116-121.LOU Jianlou,XU Jia,LU Heng,et al.Wind turbine data-cleaning algorithm based on power curve[J].Automation of Electric Power Systems,2016,40(10):116-121.
[10]SCHLECHTINGEN M,SANTOS I F,ACHICHE S.Using data-mining approaches for wind turbine power curve monitoring:a comparative study[J].IEEE Transactions on Sustainable Energy,2013,4(3):671-679.
[11]朱倩雯,叶林,赵永宁,等.风电场输出功率异常数据识别与重构方法研究[J].电力系统保护与控制,2015,43(3):38-45.ZHU Qianwen,YE Lin,ZHAO Yongning,et al.Methods for elimination and reconstruction of abnormal power data in wind farms[J].Power System Protection and Control,2015,43(3):38-45.
[12]张东英,李伟花,刘燕华,等.风电场有功功率异常运行数据重构方法[J].电力系统自动化,2014,38(5):14-18,24.ZHANG Dongying,LI Weihua,LIU Yanhua,et al.Photovolatic generation forecast based on multidimensional time-series local support vector regression in microgrids[J].Automation of Electric Power Systems,2014,38(5):14-18,24.
[13]杨茂,孙涌,孙兆键,等.风电场大规模数据管理系统设计与研发[J].东北电力大学学报,2014,34(2):27-31.YANG Mao,SUN Yong,SUN Zhaojian,et al.Design and development of large-scale data management system of wind farm[J].Journal of Northeast Dianli University,2013,34(2):27-31.
[14]叶小岭,陈浩,郭晓杰,等.基于风速升降特性的短期风电功率预测[J].电力系统保护与控制,2016,44(19):56-62.YE Xiaoling,CHEN Hao,GUO Xiaojie,et al.Short-term wind power prediction based on the UP-DOWN-features of wind speed[J].Power System Protection and Control,2016,44(19):56-62.
[15]邱宜彬,欧阳誉波,李奇,等.考虑多风电场相关性的场景概率潮流计算及无功优化[J].电力系统保护与控制,2017,45(2):61-68.QIU Yibin,OUYANG Yubo,LI Qi,et al.Scenario probabilistic load flow calculation and reactive power optimization considering wind farms correlation[J].Power System Protection and Control,2017,45(2):61-68.
[16]徐玉琴,陈坤,李俊卿,等.Copula函数与核估计理论相结合分析风电场出力相关性的一种新方法[J].电工技术学报,2016,31(13):92-100.XU Yuqin,CHEN Kun,LI Junqing,et al.A new method analyzing output correlation of multi-wind farms based on combination of copula function and kernel estimation theory[J].Transactions of China Electrotechnical Society,2016,31(13):92-100.
[17]龚莺飞,鲁宗相,乔颖,等.基于Copula理论的光伏功率高比例异常数据机器识别算法[J].电力系统自动化,2016,40(9):16-22,55.GONG Yingfei,LU Zongxiang,QIAO Ying,et al.Copula theory based machine identification algorithm of high proportion of outliers in photovoltaic power date[J].Automation of Electric Power Systems,2016,40(9):16-22,55.
[18]叶林,刘鹏.基于经验模态分解和支持向量机的短期风电功率组合预测模型[J].中国电机工程学报,2011,31(31):102-108.YE Lin,LIU Peng.Combined model based on EMD-SVM for short-term wind power prediction[J].Proceedings of the CSEE,2011,31(31):102-108.
[19]刘红柳,杨茂.基于小波变换和支持向量机的风电功率爬坡事件识别与预测[J].东北电力大学学报,2016,36(6):30-35.LIU Hongliu,YANG Mao.An approach for wind power climbing event identificationand prediction based on wavelet and SVM[J].Journal of Northeast Electric Power University,2016,36(6):30-35.