摘要
风电的波动性和不确定性给大规模风电并网带来了挑战,估计风电场上报风电的预测功率误差范围,能够为含风电电力系统的运行调度提供重要信息。因此,提出基于隐马尔可夫模型的日内风电功率预测误差区间滚动估计方法。通过建立隐马尔可夫模型实现一定置信水平下对风电功率误差波动区间的快速估计,并利用局部加权回归散点平滑法对误差区间进行处理。以实际数据为例分析,结果表明所提方法能够给出风电功率预测误差的波动范围,为电力系统的调度与控制、备用容量的配置、风险评估等方面提供更全面的信息。
The randomness and fluctuation of wind power bring challenges to the integration of wind power to the power grid.The error range estimation of predicted power for wind farms can provide important information for the operation and the scheduling of power system with wind power.So,an interval rolling estimation method for daily wind power forecast errors is proposed,which is based on hidden Markov model.The hidden Markov model can be built to achieve fast estimation of wind power error fluctuation range under the certain confidence level,and the local weighted regression smoothing method is used to deal with the error interval.Based on the actual data,the simulation results show that this method can give the fluctuation range of the wind power prediction error and provide more comprehensive information for the power system scheduling and control,the allocation of backup capacity,the risk assessment and so on.
引文
[1]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.
[2]刘兴杰,谢春雨.基于贝塔分布的风电功率波动区间估计[J].电力自动化设备,2014,34(12):26-30.LIU Xingjie,XIE Chunyu.Wind power fluctuation interval estimation based on beta distribution[J].Electric Power Automation Equipment,2014,34(12):26-30.
[3]刘燕华,李伟花,刘冲,等.短期风电功率预测误差的混合偏态分布模型[J].中国电机工程学报,2015,35(10):2375-2382.LIU Yanhua,LI Weihua,LIU Chong,et al.Mixed skew distribution model of short-term wind power prediction error[J].Proceedings of the CSEE,2015,35(10):2375-2382.
[4]ZHANG Z,SUN Y,GAO D,et al.A versatile probability distribution model for wind power forecast errors and its application in economic dispatch[J].IEEE Transactions on Power Systems,2013,28(3):3114-3125.
[5]KHOSRAVI A,NAHAVANDI S.Combined nonparametric prediction intervals for wind power generation[J].IEEETransactions on Sustainable Energy,2013,4(4):849-856.
[6]张凯锋,杨国强,陈汉一,等.基于数据特征提取的风电功率预测误差估计方法[J].电力系统自动化,2014,38(16):22-27.DOI:10.7500/AEPS20140113008.ZHANG Kaifeng,YANG Guoqiang,CHEN Hanyi,et al.An estimation method for wind power forecast errors based on numerical feature extraction[J].Automation of Electric Power Systems,2014,38(16):22-27.DOI:10.7500/AEPS20140113008.
[7]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.
[8]章国勇,伍永刚,张洋,等.一种风电功率混沌时间序列概率区间简易预测模型[J].物理学报,2014,63(13):422-430.ZHANG Guoyong,WU Yonggang,ZHANG Yang,et al.Asimple model for probabilistic interval forecasts of wind power chaotic time series[J].Chinese Physical Society,2014,63(13):422-430.
[9]梅生伟,薛安成,张雪敏.电力系统自组织临界特性与大电网安全[M].北京:清华大学出版社,2009.MEI Shengwei,XUE Ancheng,ZHANG Xuemin.Selforganized criticality of power system and safety for large power grid[M].Beijing:Tsinghua University Press,2009.
[10]ALFONSO P,MARCELO M.Indirect acquisition of violin instrumental controls from audio signal with hidden Markov models[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2015,23(5):932-940.
[11]CAO Y,LI Y,COLEMAN S,et al.Adaptive hidden Markov model with anomaly states for price manipulation detection[J].IEEE Transactions on Neural Networks and Learning Systems,2015,26(2):318-330.
[12]LU Q,QIAO Y,ANANSARI N,et al.Big data driven hidden Markov model based individual mobility prediction at points of interest[J].IEEE Transactions on Vehicular Technology,2017,66(6):5204-5216.
[13]BO W,KENJI K,JIRO K.History-based throughput prediction with hidden Markov model in mobile networks[C]//2016IEEE International Conference on Multimedia&Expo Workshops(ICMEW),July 11-15,2016,Seattle,USA:1-6.
[14]岳夏.基于HMM的复杂条件故障诊断技术研究[D].广州:华南理工大学,2012.YUE Xia.HMM-based fault diagnosis technology under complex conditions[D].Guangzhou:South China University of Technology,2012.
[15]李思岑.基于高阶隐马尔可夫模型的人体行为识别研究[D].成都:西华大学,2016.LI Sicen.Research on human behavior recognition based on high-order hidden Markov model[D].Chengdu:Xihua University,2016.
[16]OCAK H,LOPARO A.New bearing fault detection and diagnosis scheme based on hidden Markov modeling of vibration signals proceeding[C]//2001IEEE International Conference,May 7-11,2001,Salt Lake City,USA:3141-3144.
[17]LEEJ M,KIM S,HWANG Y,et al.Diagnosis of mechanical fault signals using continuous hidden Markov model[J].Journal of Sound and Vibration,2004,27(6):1065-1080.
[18]PARK S,CHOI J,SEOL J,et al.Expectation-maximizationbased channel estimation for multiuser MIMO systems[J].IEEE Transactions on Communications,2017,65(6):2397-2410.
[19]CHENG C,TAY W,HUANG G.Extreme learning machines for intrusion detection[C]//Proceedings of the 2012International Joint Conference on Neural Networks(IJCNN),Brisbane,Australia:1-8.
[20]WAN C,XU Z,PINSON P,et al.Optimal prediction intervals of wind power generation[J].IEEE Transactions on Power Systems,2014,29(3):1166-1174.
[21]杨锡运,关文渊,刘玉奇,等.基于粒子群优化的核极限学习机模型的风电功率区间预测方法[J].中国电机工程学报,2015,35(增刊):146-152.YANG Xiyun,GUAN Wenyuan,LIU Yuqi,et al.Prediction intervals forecasts of wind power based on PSO-KELM[J].Proceedings of the CSEE,2015,35(Supplement):146-152.