基于PCA-GA-LSSVM的输电线路覆冰负荷在线预测模型
|
摘要
针对目前输电线路覆冰负荷预测模型存在的预测精度不足、模型参数选择随意性强、预测效率低等问题,提出了一种基于现场监测数据的输电线路覆冰负荷在线预测模型。首先基于主成分分析法(PrincipalComponent Analysis, PCA)提取微气象数据中的有效信息,并采用遗传优化算法(Genetic Algorithm, GA)对惩罚系数等模型参数进行优化确定,建立离线最小二乘支持向量机(LeastSquaresSupportVectorMachines, LS-SVM)模型。然后基于KKT条件(Karush-Kuhn-Tucker conditions)和增量在线学习算法,实现了回归函数和预测模型的在线更新。最后通过云南电网相关输电线路覆冰灾害的实例进行仿真分析。实验结果表明所提模型可有效地对现场输电线路覆冰负荷进行在线预测,单步长及多步长的预测效果均优于传统的覆冰预测模型,应用该预测模型可更好地为输变电系统的除冰和维护决策服务。
Traditional icing load prediction models exist many shortcomings, such as forecasting inaccuracy, casualness in choosing model parameters, and low prediction efficiency. Thus, an online prediction model based on the field micrometeorological data is proposed to predict the icing load of power transmission line. Firstly, this paper extracts effective information from micrometeorological data based on Principal Component Analysis(PCA), and optimizes the regression parameters by Genetic Algorithm(GA), and builds and trains offline LS-SVM training model. Secondly, online updating of regression function and prediction model is realized based on Karush-Kuhn-Tucker conditions and incremental online learning algorithm. Finally, the validity of the model is evaluated by related transmission lines of Yunnan Power Grid. Experimental results indicate that this method could predict the real-time icing load on overhead power lines, obtaining better performance in single-step and multi-step forecast than traditional icing load prediction models, which could serve for deicing and maintenance decision for power transmission and distribution system.
Traditional icing load prediction models exist many shortcomings, such as forecasting inaccuracy, casualness in choosing model parameters, and low prediction efficiency. Thus, an online prediction model based on the field micrometeorological data is proposed to predict the icing load of power transmission line. Firstly, this paper extracts effective information from micrometeorological data based on Principal Component Analysis(PCA), and optimizes the regression parameters by Genetic Algorithm(GA), and builds and trains offline LS-SVM training model. Secondly, online updating of regression function and prediction model is realized based on Karush-Kuhn-Tucker conditions and incremental online learning algorithm. Finally, the validity of the model is evaluated by related transmission lines of Yunnan Power Grid. Experimental results indicate that this method could predict the real-time icing load on overhead power lines, obtaining better performance in single-step and multi-step forecast than traditional icing load prediction models, which could serve for deicing and maintenance decision for power transmission and distribution system.
引文
[1]罗剑波,郁琛,谢云云,等.关于自然灾害下电力系统安全稳定防御方法的评述[J].电力系统保护与控制,2018,46(6):158-170.LUO Jianbo,YU Chen,XIE Yunyun,et al.A review on risk assessment of power grid security and stability under natural disasters[J].Power System Protection and Control,2018,46(6):158-170.
[2]蒋兴良,张志劲,胡琴,等.再次面临电网冰雪灾害的反思与思考[J].高电压技术,2018,44(2):463-469.JIANG Xingliang,ZHANG Zhijin,HU Qin,et al.Thinkings on the restrike of ice and snow disaster to the power grid[J].High Voltage Engineering,2018,44(2):463-469.
[3]王燕,杜志叶,阮江军.高压架空输电线路覆冰情况下风险评估研究[J].电力系统保护与控制,2016,44(10):84-90.WANG Yan,DU Zhiye,RUAN Jiangjun.Reliability risk evaluation for the high voltage overhead transmission line under icing condition[J].Power System Protection and Control,2016,44(10):84-90.
[4]蒋兴良,姜方义,汪泉霖,等.基于最优时间步长模型的输电导线雾凇覆冰预测[J].电工技术学报,2018,33(18):4408-4418.JIANG Xingliang,JIANG Fangyi,WANG Quanlin,et al.Prediction of rime accretion on transmission line based on optimal time step model[J].Transactions of China Electrotechnical Society,2018,33(18):4408-4418.
[5]BO Zhiqian,LIN Xiangning,WANG Qingping,et al.Developments of power system protection and control[J].Protection and Control of Modern Power Systems,2016,1(1):1-8.DOI:10.1186/s41601-016-0012-2.
[6]陈金熠,范春菊,胡天强,等.考虑架空输电线路状态的线路覆冰监测系统的研究[J].电力系统保护与控制,2012,40(15):93-98.CHEN Jinyi,FAN Chunju,HU Tianqian,et al.Study on monitoring system of transmission line icing considering the state of overhead transmission lines[J].Power System Protection and Control,2012,40(15):93-98.
[7]黄文焘,邰能灵,范春菊.基于杆塔结构力学测量的线路覆冰在线监测系统研究[J].电力系统保护与控制,2012,40(24):71-75.HUANG Wentao,TAI Nengling,FAN Chunju.Study on icing monitoring system of different tower overhead transmission lines based on mechanics measurements[J].Power System Protection and Control,2012,40(24):71-75.
[8]张志劲,张翼,蒋兴良,等.基于标准旋转导体等效碰撞系数的绝缘子覆冰表征[J].电工技术学报,2018,33(21):5119-5127.ZHANG Zhijin,ZHANG Yi,JIANG Xingliang,et al.Icing characterization of insulator based on the equivalent collision coefficient of standard rotating conductors[J].Transactions of China Electrotechnical Society,2018,33(21):5119-5127.
[9]张松海,施心陵,李鹏,等.基于动态拉力与倾角的输电线路覆冰过程辨识与建模[J].电力系统保护与控制,2016,44(9):57-61.ZHANG Songhai,SHI Xinling,LI Peng,et al.Identification and modeling of the power transmission line icing based on dynamic data of tension and angle[J].Power System Protection and Control,2016,44(9):57-61.
[10]王敩青,戴栋,郝艳捧,等.基于在线监测系统的输电线路覆冰数据统计与分析[J].高电压技术,2012,38(11):3000-3007.WANG Xiaoqing,DAI Dong,HAO Yanpeng,et al.Statistics and analysis of transmission lines icing data based on online monitoring system[J].High Voltage Engineering,2012,38(11):3000-3007.
[11]陆佳政,张红先,彭继文,等.基于极值I型概率分布模型的湖南地区电网覆冰重现期计算[J].高电压技术,2012,38(2):464-468.LU Jiazheng,ZHANG Hongxian,PENG Jiwen,et al.Calculation of Hunan Power Grid icing recurrence interval based on extreme-value type I probability distribution model[J].High Voltage Engineering,2012,38(2):464-468.
[12]王建城,苏盛,盛小勇,等.输电线路多年一遇极值覆冰估计方法适用性分析[J].电网技术,2015,39(9):2614-2620.WANG Jiancheng,SU Sheng,SHENG Xiaoyong,et al.Comparative study of applicability of methods for estimating transmission line icing return period based on various extreme value distributions[J].Power System Technology,2015,39(9):2614-2620.
[13]黄宵宁,许瑞,许家浩.南方山区线路覆冰在线监测数据特征分析与预测模型研究[J].电力系统保护与控制,2015,43(23):111-116.HUANG Xiaoning,XU Rui,XU Jiahao.Analysis of the characteristics for on-line monitoring data and research of the forecast model of the line icing in southern mountain area[J].Power System Protection and Control,2015,43(23):111-116.
[14]黄新波,李弘博,朱永灿,等.基于时间序列分析与卡尔曼滤波的输电线路覆冰短期预测[J].高电压技术,2017,43(6):1943-1949.HUANG Xinbo,LI Hongbo,ZHU Yongcan,et al.Short-term forecast for transmission line icing by time series analysis and Kalman filtering[J].High Voltage Engineering,2017,43(6):1943-1949.
[15]戴栋,黄筱婷,代洲,等.基于支持向量机的输电线路覆冰回归模型[J].高电压技术,2013,39(11):2822-2828.DAI Dong,HUANG Xiaoting,DAI Zhou,et al.Regression model for transmission lines icing based on support vector machine[J].High Voltage Engineering,2013,39(11):2822-2828.
[16]LI P,LI Q M,REN W P,et al.SVM-based prediction method for icing process of overhead power lines[J].International Journal of Modelling Identification&Control,2015,23(4):362-371.
[17]赵明霞,李庆富.小数据量情境下的滑坡位移非线性变化预测模型[J].信阳师范学院学报(自然科学版),2017,30(4):521-525.ZHAO Mingxia,LI Qingfu.Prediction model to the slope displacement nonlinear changing under the small-data situation[J].Journal of Xinyang Normal University(Natural Science Edition),2017,30(4):521-525.
[18]胡霁芳,郑强,宋学力.基于主成分分析的EWMA图对单只股票短期交易的监控[J].信阳师范学院学报(自然科学版),2018,31(1):11-16.HU Jifang,ZHENG Qiang,SONG Xueli.Principal component analysis-based ewma control chart formonitoring in short-term trading of single stock[J].Journal of Xinyang Normal University(Natural Science Edition),2018,31(1):11-16.
[19]刘春城,刘佼.输电线路导线覆冰机理及雨凇覆冰模型[J].高电压技术,2011,37(1):241-248.LIU Chuncheng,LIU Jiao.Ice accretion mechanism and glaze loads model on wires of power transmission lines[J].High Voltage Engineering,2011,37(1):241-248.
[20]LI Zhi,YE Lin,ZHAO Yongning,et al.Short-term wind power prediction based on extreme learning machine with error correction[J].Protection and Control of Modern Power Systems,2016,1(1):9-16.DOI 10.1186/s41601-016-0016-y.
[21]LI J,LI P,MIAO A,et al.Online prediction method of icing of overhead power lines based on support vector regression[J].International Transactions on Electrical Energy Systems,2018,28:2500.
[22]WONG P K,WONG H C,VONG C M.Online timesequence incremental and decremental least squares support vector machines for engine air-ratio prediction[J].International Journal of Engine Research,2012,13(1):28-40.
[23]游朗.输电线路覆冰厚度短期预测模型研究[D].北京:华北电力大学,2017.YOU Lang.Research on short-term prediction models of ice thickness of transmission line[D].Beijing:North China Electric Power University,2017.
[24]李小娟.基于数据挖掘的输电线路覆冰预测模型研究[D].太原:太原理工大学,2016.LI Xiaojuan.Research on the icing prediction models of transmission line based on data mining[D].Taiyuan:Taiyuan University of Technology,2016.
[2]蒋兴良,张志劲,胡琴,等.再次面临电网冰雪灾害的反思与思考[J].高电压技术,2018,44(2):463-469.JIANG Xingliang,ZHANG Zhijin,HU Qin,et al.Thinkings on the restrike of ice and snow disaster to the power grid[J].High Voltage Engineering,2018,44(2):463-469.
[3]王燕,杜志叶,阮江军.高压架空输电线路覆冰情况下风险评估研究[J].电力系统保护与控制,2016,44(10):84-90.WANG Yan,DU Zhiye,RUAN Jiangjun.Reliability risk evaluation for the high voltage overhead transmission line under icing condition[J].Power System Protection and Control,2016,44(10):84-90.
[4]蒋兴良,姜方义,汪泉霖,等.基于最优时间步长模型的输电导线雾凇覆冰预测[J].电工技术学报,2018,33(18):4408-4418.JIANG Xingliang,JIANG Fangyi,WANG Quanlin,et al.Prediction of rime accretion on transmission line based on optimal time step model[J].Transactions of China Electrotechnical Society,2018,33(18):4408-4418.
[5]BO Zhiqian,LIN Xiangning,WANG Qingping,et al.Developments of power system protection and control[J].Protection and Control of Modern Power Systems,2016,1(1):1-8.DOI:10.1186/s41601-016-0012-2.
[6]陈金熠,范春菊,胡天强,等.考虑架空输电线路状态的线路覆冰监测系统的研究[J].电力系统保护与控制,2012,40(15):93-98.CHEN Jinyi,FAN Chunju,HU Tianqian,et al.Study on monitoring system of transmission line icing considering the state of overhead transmission lines[J].Power System Protection and Control,2012,40(15):93-98.
[7]黄文焘,邰能灵,范春菊.基于杆塔结构力学测量的线路覆冰在线监测系统研究[J].电力系统保护与控制,2012,40(24):71-75.HUANG Wentao,TAI Nengling,FAN Chunju.Study on icing monitoring system of different tower overhead transmission lines based on mechanics measurements[J].Power System Protection and Control,2012,40(24):71-75.
[8]张志劲,张翼,蒋兴良,等.基于标准旋转导体等效碰撞系数的绝缘子覆冰表征[J].电工技术学报,2018,33(21):5119-5127.ZHANG Zhijin,ZHANG Yi,JIANG Xingliang,et al.Icing characterization of insulator based on the equivalent collision coefficient of standard rotating conductors[J].Transactions of China Electrotechnical Society,2018,33(21):5119-5127.
[9]张松海,施心陵,李鹏,等.基于动态拉力与倾角的输电线路覆冰过程辨识与建模[J].电力系统保护与控制,2016,44(9):57-61.ZHANG Songhai,SHI Xinling,LI Peng,et al.Identification and modeling of the power transmission line icing based on dynamic data of tension and angle[J].Power System Protection and Control,2016,44(9):57-61.
[10]王敩青,戴栋,郝艳捧,等.基于在线监测系统的输电线路覆冰数据统计与分析[J].高电压技术,2012,38(11):3000-3007.WANG Xiaoqing,DAI Dong,HAO Yanpeng,et al.Statistics and analysis of transmission lines icing data based on online monitoring system[J].High Voltage Engineering,2012,38(11):3000-3007.
[11]陆佳政,张红先,彭继文,等.基于极值I型概率分布模型的湖南地区电网覆冰重现期计算[J].高电压技术,2012,38(2):464-468.LU Jiazheng,ZHANG Hongxian,PENG Jiwen,et al.Calculation of Hunan Power Grid icing recurrence interval based on extreme-value type I probability distribution model[J].High Voltage Engineering,2012,38(2):464-468.
[12]王建城,苏盛,盛小勇,等.输电线路多年一遇极值覆冰估计方法适用性分析[J].电网技术,2015,39(9):2614-2620.WANG Jiancheng,SU Sheng,SHENG Xiaoyong,et al.Comparative study of applicability of methods for estimating transmission line icing return period based on various extreme value distributions[J].Power System Technology,2015,39(9):2614-2620.
[13]黄宵宁,许瑞,许家浩.南方山区线路覆冰在线监测数据特征分析与预测模型研究[J].电力系统保护与控制,2015,43(23):111-116.HUANG Xiaoning,XU Rui,XU Jiahao.Analysis of the characteristics for on-line monitoring data and research of the forecast model of the line icing in southern mountain area[J].Power System Protection and Control,2015,43(23):111-116.
[14]黄新波,李弘博,朱永灿,等.基于时间序列分析与卡尔曼滤波的输电线路覆冰短期预测[J].高电压技术,2017,43(6):1943-1949.HUANG Xinbo,LI Hongbo,ZHU Yongcan,et al.Short-term forecast for transmission line icing by time series analysis and Kalman filtering[J].High Voltage Engineering,2017,43(6):1943-1949.
[15]戴栋,黄筱婷,代洲,等.基于支持向量机的输电线路覆冰回归模型[J].高电压技术,2013,39(11):2822-2828.DAI Dong,HUANG Xiaoting,DAI Zhou,et al.Regression model for transmission lines icing based on support vector machine[J].High Voltage Engineering,2013,39(11):2822-2828.
[16]LI P,LI Q M,REN W P,et al.SVM-based prediction method for icing process of overhead power lines[J].International Journal of Modelling Identification&Control,2015,23(4):362-371.
[17]赵明霞,李庆富.小数据量情境下的滑坡位移非线性变化预测模型[J].信阳师范学院学报(自然科学版),2017,30(4):521-525.ZHAO Mingxia,LI Qingfu.Prediction model to the slope displacement nonlinear changing under the small-data situation[J].Journal of Xinyang Normal University(Natural Science Edition),2017,30(4):521-525.
[18]胡霁芳,郑强,宋学力.基于主成分分析的EWMA图对单只股票短期交易的监控[J].信阳师范学院学报(自然科学版),2018,31(1):11-16.HU Jifang,ZHENG Qiang,SONG Xueli.Principal component analysis-based ewma control chart formonitoring in short-term trading of single stock[J].Journal of Xinyang Normal University(Natural Science Edition),2018,31(1):11-16.
[19]刘春城,刘佼.输电线路导线覆冰机理及雨凇覆冰模型[J].高电压技术,2011,37(1):241-248.LIU Chuncheng,LIU Jiao.Ice accretion mechanism and glaze loads model on wires of power transmission lines[J].High Voltage Engineering,2011,37(1):241-248.
[20]LI Zhi,YE Lin,ZHAO Yongning,et al.Short-term wind power prediction based on extreme learning machine with error correction[J].Protection and Control of Modern Power Systems,2016,1(1):9-16.DOI 10.1186/s41601-016-0016-y.
[21]LI J,LI P,MIAO A,et al.Online prediction method of icing of overhead power lines based on support vector regression[J].International Transactions on Electrical Energy Systems,2018,28:2500.
[22]WONG P K,WONG H C,VONG C M.Online timesequence incremental and decremental least squares support vector machines for engine air-ratio prediction[J].International Journal of Engine Research,2012,13(1):28-40.
[23]游朗.输电线路覆冰厚度短期预测模型研究[D].北京:华北电力大学,2017.YOU Lang.Research on short-term prediction models of ice thickness of transmission line[D].Beijing:North China Electric Power University,2017.
[24]李小娟.基于数据挖掘的输电线路覆冰预测模型研究[D].太原:太原理工大学,2016.LI Xiaojuan.Research on the icing prediction models of transmission line based on data mining[D].Taiyuan:Taiyuan University of Technology,2016.