基于特征影响因子和改进BP算法的直驱风机风电场建模方法
|
摘要
风电场/场群规模化接入电网背景下,电网的故障暂态特性发生了根本性改变。然而,现有单机等值型无法精确表征风电场/场群的故障暂态特性。该文提出一种基于特征影响因子和改进人工神经网络反向传播(backpropagation neuronnetworks,BP)算法的直驱风机风电场建模方法。首先,建立直驱风机暂态模型,通过理论分析构建风机与公共连接点(point of common coupling,PCC)距离、直流侧限流措施投入情况、风速、出口处无功功率等故障特征影响因子。然后,对特征影响因子集计算欧式距离,基于改进最大最小距离法提取风机的分类初始中心。通过改进BP算法,以特征影响因子和分类初始中心为训练集,实现神经网络的快速收敛。最后,通过仿真算例,对所提方法进行验证。仿真结果表明,所述方法在收敛速度、建模精度方面,与传统BP算法和单机等值建模方法相比均有较大提升。
As the large-scale wind farms/fields accessed to the grid, the fault transient characteristics of the grid had undergone fundamental changes. However, the existing single-machine equivalent model cannot accurately characterize the fault transient characteristics of wind farms/field groups. This paper proposed a modeling method of direct-driven wind generators wind farm based on feature influence factors and improved back-propagation neural networks(BP) algorithm. Firstly, the transient model of the single direct-drive wind power generators was established.Through the theoretical analysis, the influence factors of the fault characteristics such as the distance between the generator and the point of common coupling(PCC), the situation of the DC-side current limiting measure, the wind speed and the reactive power of wind generator were constructed. Secondly,the Euclidean distance was calculated for the factor set, and the classification initial center of the wind generators were extracted based on the improved maximum and minimum distance method. By improving the BP algorithm, the feature influence factors and the initial center of the classification were used as training sets to achieve fast convergence of the neural network. Finally, the proposed method was verified by simulation examples. The simulation results show that the proposed method had a greatly improvement in convergence speed and modeling accuracy compared with traditional BP algorithm and single-machine equivalent modeling method.
As the large-scale wind farms/fields accessed to the grid, the fault transient characteristics of the grid had undergone fundamental changes. However, the existing single-machine equivalent model cannot accurately characterize the fault transient characteristics of wind farms/field groups. This paper proposed a modeling method of direct-driven wind generators wind farm based on feature influence factors and improved back-propagation neural networks(BP) algorithm. Firstly, the transient model of the single direct-drive wind power generators was established.Through the theoretical analysis, the influence factors of the fault characteristics such as the distance between the generator and the point of common coupling(PCC), the situation of the DC-side current limiting measure, the wind speed and the reactive power of wind generator were constructed. Secondly,the Euclidean distance was calculated for the factor set, and the classification initial center of the wind generators were extracted based on the improved maximum and minimum distance method. By improving the BP algorithm, the feature influence factors and the initial center of the classification were used as training sets to achieve fast convergence of the neural network. Finally, the proposed method was verified by simulation examples. The simulation results show that the proposed method had a greatly improvement in convergence speed and modeling accuracy compared with traditional BP algorithm and single-machine equivalent modeling method.
引文
[1]苏勋文,米增强,王毅.风电场常用等值方法的适用性及其改进研究[J].电网技术,2010,34(6):175-180.Su Xunwen,Mi Zengqiang,Wang Yi.Applicability and improvement of common-used equivalent methods for wind farms[J].Power System Technology,2010,34(6):175-180(in Chinese).
[2]娄素华,李志恒,高苏杰,等.风电场模型及其对电力系统的影响[J].电网技术,2007,31(S2):330-334.Lou Suhua,Li Zhiheng,Gao Sujie,et al.Wind farms models and its impacts on wind farms integration into power system[J].Power System Technology,2007,31(S2):330-334(in Chinese).
[3]欧阳金鑫,刁艳波,郑迪,等.基于电流轨迹相似度的双馈风电机群电磁暂态同调分群方法[J].中国电机工程学报,2017,37(10):2896-2904.Ouyang Jinxin,Diao Yanbo,Zheng Di,et al.A clustering method of coherent generators during electromagnetic transient process based on similar degrees of current trajectories for doubly fed wind farms[J].Proceedings of the CSEE,2017,37(10):2896-2904(in Chinese).
[4]周海强,鞠平,宋忠鹏,等.基于附加虚拟阻抗和蚁群优化算法的动态等效模型在线修正方法[J].中国电机工程学报,2011,31(19):75-81.Zhou Haiqiang,Ju Ping,Song Zhongpeng,et al.An online adjustment method of dynamic equivalent model based on additional fictitious impedances and ant colony optimization algorithm[J].Proceedings of the CSEE,2011,31(19):75-81(in Chinese).
[5]朱乾龙,韩平平,丁明,等.基于聚类-判别分析的风电场概率等值建模研究[J].中国电机工程学报,2014,34(28):4770-4780.Zhu Qianlong,Han Pingping,Ding Ming,et al.Probabilistic equivalent model for wind farms based on clustering-discriminant analysis[J].Proceedings of the CSEE,2014,34(28):4770-4780(in Chinese).
[6]Liu Hongzhi,Chen Zhe.Aggregated modelling for wind farms for power system transient stability studies[C]//Proceedings of 2012 Asia-Pacific Power and Energy Engineering Conference.Shanghai,China:IEEE,2012:1-6.
[7]Conroy J,Watson R.Aggregate modelling of wind farms containing full-converter wind turbine generators with permanent magnet synchronous machines:transient stability studies[J].IET Renewable Power Generation,2009,3(1):39-52.
[8]高峰,赵东来,周孝信,等.直驱式风电机组风电场动态等值[J].电网技术,2012,36(12):222-227.Gao Feng,Zhao Donglai,Zhou Xiaoxin,et al.Dynamic equivalent algorithm for wind farm composed of direct-drive wind turbines[J].Power System Technology,2012,36(12):222-227(in Chinese).
[9]洪树斌,范春菊,陈实,等.PQ控制策略下多逆变型电源的故障等值方法[J].电网技术,2018,42(4):1101-1109.Hong Shubin,Fan Chunju,Chen Shi,et al.Research on fault equivalence method for multiple inverter-interfaced distributed generation based on pq control strategy[J].Power System Technology,2018,42(4):1101-1109(in Chinese).
[10]陆飞,刘其辉,赵亚男,等.基于低电压穿越去磁控制的风电场内部故障等值建模方法[J].电力系统自动化,2016,40(10):24-30.Lu Fei,Liu Qihui,Zhao Yannan,et al.Equivalent modeling method for wind farm inner fault based on demagnetizing control of low voltage ride through[J].Automation of Electric Power Systems,2016,40(10):24-30(in Chinese).
[11]张星,李龙源,胡晓波,等.基于风电机组输出时间序列数据分群的风电场动态等值[J].电网技术,2015,39(10):2787-2793.Zhang Xing,Li Longyuan,Hu Xiaobo,et al.Wind farm dynamic equivalence based on clustering by output time series data of wind turbine generators[J].Power System Technology,2015,39(10):2787-2793(in Chinese).
[12]宋国兵,李端祯,常仲学,等.风速及风机地理位置分布特性对直驱风电场故障特征的影响分析[J].电网技术,2016,40(6):1690-1696.Song Guobing,Li Duanzhen,Chang Zhongxue,et al.Analysis of impact of wind speed and wind turbine location distribution characteristics on PMSG wind farm fault characteristics[J].Power System Technology,2016,40(6):1690-1696(in Chinese).
[13]中华人民共和国国家质量监督检验检疫总局,中国国家标准化管理委员会.GB/T 14285-2006继电保护和安全自动装置技术规程[S].北京:中国标准出版社,2007.General Administration of Quality Supervision,Inspection and Quarantine of the People's Republic of China,National Standardization Management Committee of China.GB/T 14285-2006 Technical code for relaying protection and security automatic equipment[S].Beijing:China Standard Press,2007(in Chinese).
[14]毕天姝,刘素梅,薛安成,等.逆变型新能源电源故障暂态特性分析[J].中国电机工程学报,2013,33(13):165-171.Bi Tianshu,Liu Sumei,Xue Ancheng,et al.Fault characteristics of inverter-interfaced renewable energy sources[J].Proceedings of the CSEE,2013,33(13):165-171(in Chinese).
[15]杨国生,毕天姝.短路电流受限电源系统接入电网的继电保护整定计算技术研究系列报告(1)-短路电流受限电源系统的故障特性研究技术报告[R].北京:中国电力科学研究院,2018.Yang Guosheng,Bi Tianshu.Research of fault characteristics for power system with short-circuit current limited power source[R].Beijing:China Electric Power Research Institute,2018(in Chinese).
[16]李金宗.模式识别导论[M].北京:高等教育出版社,1994.Li Jinzong.Pattern recognition introduction[M].Beijing:Higher Education Press,1994(in Chinese).
[17]王俊.含风电的电力系统可用输电能力研究[D].哈尔滨:哈尔滨工业大学,2013.Wang Jun.Research on available transfer capability of power system with wind power[D].Harbin:Harbin Institute of Technology,2013(in Chinese).
[18]米增强,苏勋文,杨奇逊,等.风电场动态等值模型的多机表征方法[J].电工技术学报,2010,25(5):162-169.Mi Zengqiang,Su Xunwen,Yang Qixun,et al.Multi-machine representation method for dynamic equivalent model of wind farms[J].Transactions of China Electrotechnical Society,2010,25(5):162-169(in Chinese).
[19]郑睿敏,李建华,李作红,等.考虑尾流效应的风电场建模以及随机潮流计算[J].西安交通大学学报,2008,42(12):1515-1520.Zheng Ruimin,Li Jianhua,Li Zuohong,et al.Modeling of large-scale wind farms in the probabilistic power flow analysis considering wake effects[J].Journal of Xi’an Jiaotong University,2008,42(12):1515-1520(in Chinese).
[20]祁文军,姜超,方建疆,等.达坂城风电场风能资源分析[J].太阳能学报,2013,34(5):909-914.Qi Wenjun,Jiang Chao,Fang Jianjiang,et al.Analysis of wind energy resource for DABANCHENG wind farm[J].Acta Energiae Solaris Sinica,2013,34(5):909-914(in Chinese).
[2]娄素华,李志恒,高苏杰,等.风电场模型及其对电力系统的影响[J].电网技术,2007,31(S2):330-334.Lou Suhua,Li Zhiheng,Gao Sujie,et al.Wind farms models and its impacts on wind farms integration into power system[J].Power System Technology,2007,31(S2):330-334(in Chinese).
[3]欧阳金鑫,刁艳波,郑迪,等.基于电流轨迹相似度的双馈风电机群电磁暂态同调分群方法[J].中国电机工程学报,2017,37(10):2896-2904.Ouyang Jinxin,Diao Yanbo,Zheng Di,et al.A clustering method of coherent generators during electromagnetic transient process based on similar degrees of current trajectories for doubly fed wind farms[J].Proceedings of the CSEE,2017,37(10):2896-2904(in Chinese).
[4]周海强,鞠平,宋忠鹏,等.基于附加虚拟阻抗和蚁群优化算法的动态等效模型在线修正方法[J].中国电机工程学报,2011,31(19):75-81.Zhou Haiqiang,Ju Ping,Song Zhongpeng,et al.An online adjustment method of dynamic equivalent model based on additional fictitious impedances and ant colony optimization algorithm[J].Proceedings of the CSEE,2011,31(19):75-81(in Chinese).
[5]朱乾龙,韩平平,丁明,等.基于聚类-判别分析的风电场概率等值建模研究[J].中国电机工程学报,2014,34(28):4770-4780.Zhu Qianlong,Han Pingping,Ding Ming,et al.Probabilistic equivalent model for wind farms based on clustering-discriminant analysis[J].Proceedings of the CSEE,2014,34(28):4770-4780(in Chinese).
[6]Liu Hongzhi,Chen Zhe.Aggregated modelling for wind farms for power system transient stability studies[C]//Proceedings of 2012 Asia-Pacific Power and Energy Engineering Conference.Shanghai,China:IEEE,2012:1-6.
[7]Conroy J,Watson R.Aggregate modelling of wind farms containing full-converter wind turbine generators with permanent magnet synchronous machines:transient stability studies[J].IET Renewable Power Generation,2009,3(1):39-52.
[8]高峰,赵东来,周孝信,等.直驱式风电机组风电场动态等值[J].电网技术,2012,36(12):222-227.Gao Feng,Zhao Donglai,Zhou Xiaoxin,et al.Dynamic equivalent algorithm for wind farm composed of direct-drive wind turbines[J].Power System Technology,2012,36(12):222-227(in Chinese).
[9]洪树斌,范春菊,陈实,等.PQ控制策略下多逆变型电源的故障等值方法[J].电网技术,2018,42(4):1101-1109.Hong Shubin,Fan Chunju,Chen Shi,et al.Research on fault equivalence method for multiple inverter-interfaced distributed generation based on pq control strategy[J].Power System Technology,2018,42(4):1101-1109(in Chinese).
[10]陆飞,刘其辉,赵亚男,等.基于低电压穿越去磁控制的风电场内部故障等值建模方法[J].电力系统自动化,2016,40(10):24-30.Lu Fei,Liu Qihui,Zhao Yannan,et al.Equivalent modeling method for wind farm inner fault based on demagnetizing control of low voltage ride through[J].Automation of Electric Power Systems,2016,40(10):24-30(in Chinese).
[11]张星,李龙源,胡晓波,等.基于风电机组输出时间序列数据分群的风电场动态等值[J].电网技术,2015,39(10):2787-2793.Zhang Xing,Li Longyuan,Hu Xiaobo,et al.Wind farm dynamic equivalence based on clustering by output time series data of wind turbine generators[J].Power System Technology,2015,39(10):2787-2793(in Chinese).
[12]宋国兵,李端祯,常仲学,等.风速及风机地理位置分布特性对直驱风电场故障特征的影响分析[J].电网技术,2016,40(6):1690-1696.Song Guobing,Li Duanzhen,Chang Zhongxue,et al.Analysis of impact of wind speed and wind turbine location distribution characteristics on PMSG wind farm fault characteristics[J].Power System Technology,2016,40(6):1690-1696(in Chinese).
[13]中华人民共和国国家质量监督检验检疫总局,中国国家标准化管理委员会.GB/T 14285-2006继电保护和安全自动装置技术规程[S].北京:中国标准出版社,2007.General Administration of Quality Supervision,Inspection and Quarantine of the People's Republic of China,National Standardization Management Committee of China.GB/T 14285-2006 Technical code for relaying protection and security automatic equipment[S].Beijing:China Standard Press,2007(in Chinese).
[14]毕天姝,刘素梅,薛安成,等.逆变型新能源电源故障暂态特性分析[J].中国电机工程学报,2013,33(13):165-171.Bi Tianshu,Liu Sumei,Xue Ancheng,et al.Fault characteristics of inverter-interfaced renewable energy sources[J].Proceedings of the CSEE,2013,33(13):165-171(in Chinese).
[15]杨国生,毕天姝.短路电流受限电源系统接入电网的继电保护整定计算技术研究系列报告(1)-短路电流受限电源系统的故障特性研究技术报告[R].北京:中国电力科学研究院,2018.Yang Guosheng,Bi Tianshu.Research of fault characteristics for power system with short-circuit current limited power source[R].Beijing:China Electric Power Research Institute,2018(in Chinese).
[16]李金宗.模式识别导论[M].北京:高等教育出版社,1994.Li Jinzong.Pattern recognition introduction[M].Beijing:Higher Education Press,1994(in Chinese).
[17]王俊.含风电的电力系统可用输电能力研究[D].哈尔滨:哈尔滨工业大学,2013.Wang Jun.Research on available transfer capability of power system with wind power[D].Harbin:Harbin Institute of Technology,2013(in Chinese).
[18]米增强,苏勋文,杨奇逊,等.风电场动态等值模型的多机表征方法[J].电工技术学报,2010,25(5):162-169.Mi Zengqiang,Su Xunwen,Yang Qixun,et al.Multi-machine representation method for dynamic equivalent model of wind farms[J].Transactions of China Electrotechnical Society,2010,25(5):162-169(in Chinese).
[19]郑睿敏,李建华,李作红,等.考虑尾流效应的风电场建模以及随机潮流计算[J].西安交通大学学报,2008,42(12):1515-1520.Zheng Ruimin,Li Jianhua,Li Zuohong,et al.Modeling of large-scale wind farms in the probabilistic power flow analysis considering wake effects[J].Journal of Xi’an Jiaotong University,2008,42(12):1515-1520(in Chinese).
[20]祁文军,姜超,方建疆,等.达坂城风电场风能资源分析[J].太阳能学报,2013,34(5):909-914.Qi Wenjun,Jiang Chao,Fang Jianjiang,et al.Analysis of wind energy resource for DABANCHENG wind farm[J].Acta Energiae Solaris Sinica,2013,34(5):909-914(in Chinese).
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |