基于样本扩展和特征标记的节假日短期负荷预测
|
摘要
针对目前节假日负荷预测中有效样本缺乏的问题,基于休息日与节假日负荷特性的相似性分析,提出一种扩展样本策略,以丰富基础样本数据量;探讨了对负荷样本节假日特征属性的标记方式,并构建了一种有效的相关因素矢量;最后结合支持向量机(support vector machine,SVM)算法,对节假日负荷进行预测,以提高其预测结果的精度。算例结果表明,与传统方法相比,所提方法能够有效提高负荷预测精度,可推广应用于实践中。
Aiming at the problem of lacking of effective samples in current holiday load forecasting, a strategy for sample expansion is proposed based on similarity analysis on load characteristics in weekends and holidays to enrich data size of basic samples. Feature extraction ways of load characteristic attributes in holidays is discussed and effective vectors of relevant factors are constructed. The support vector machine(SVM) algorithm is combined for load forecasting in holidays so as to improve accuracy of forecasting result. The example result indicates that compared with conventional methods, the proposed method can effectively improve load forecasting accuracy and be applied in practice.
Aiming at the problem of lacking of effective samples in current holiday load forecasting, a strategy for sample expansion is proposed based on similarity analysis on load characteristics in weekends and holidays to enrich data size of basic samples. Feature extraction ways of load characteristic attributes in holidays is discussed and effective vectors of relevant factors are constructed. The support vector machine(SVM) algorithm is combined for load forecasting in holidays so as to improve accuracy of forecasting result. The example result indicates that compared with conventional methods, the proposed method can effectively improve load forecasting accuracy and be applied in practice.
引文
[1] 谢真桢,杨秀,张鹏,等.基于信息论与混合聚类分析的短期负荷预测方法研究[J].电测与仪表,2017,54(19):67-72.XIE Zhenzhen,YANG Xiu,ZHANG Peng,et al.Study on short-term load forecasting method based on information theory and mixed cluster analysis[J].Electrical Measurement & Instrumentation,2017,54(19):67-72.
[2] 吕跃春,廖晔,刘欣宇,等.基于规律性分析和误差修正的负荷预测方法[J].广东电力,2015,28(1):48-52.Lü Yuechun,LIAO Ye,LIU Xinyu,et al.Load forecast method based on regularity analysis and error correction [J].Guangdong Electric Power,2015,28(1):48-52.
[3] 李滨,黄佳,吴茵,等.基于分形特性修正气象相似日的节假日短期负荷预测方法[J].电网技术,2017,41(6):1949-1955.LI Bin,HUANG Jia,WU Yin,et al.Holiday short-term load forecasting based on fractal characteristic modified meteorological similar day[J].Power System Technology,2017,41(6):1949-1955.
[4] 郭建鹏,佘颖铃,温步瀛.基于EEMD-ARIMA模型的地区月负荷量预测[J].电力工程技术,2018,37(6):28-32,74.GUO Jianpeng,SHE Yingling,WEN Buying.Regional monthly load forecast based on EEMD-ARIMA model [J].Electric Power Engineering Technology,2018,37(6):28-32,74.
[5] 张冰玉.基于数据挖掘技术的短期电力负荷预测[J].电力大数据,2017,20(10):18-21.ZHANG Bingyu .Prediction of short-term power load based on data mining technology [J].Power Systems and Big Data,2017 ,20(10):18-21.
[6] 桑福敏,胡润滋.国家法定节假日重庆地区电网日负荷预测分析与研究[J].重庆电力高等专科学校学报,2015,20(6):42-45,57.SANG Fumin,HU Runzi.Analysis and research on the daily load forecast of the power grid in Chongqing during the national statutory holidays[J].Journal of Chongqing Electric Power College,2015,20(6):42-45,57.
[7] 侯亮,李焱.山西电网节假日短期负荷预测研究与分析[J].山西广播电视大学学报,2006(5):90-91.HOU Liang,LI Yan.Research and analysis on the holiday short-term load forecasting research of shanxi power network[J].Journal of Shanxi Radion & TV University,2006(5):90-91.
[8] 高靖,张明理,邓鑫阳,等.基于特征聚类的多能源系统负荷预测方法研究[J].可再生能源,2019,37(2):232-236.GAO Jing,ZHANG Mingli,DENG Xinyang,et al.Research on multi energy system load forecasting method based on feature clustering[J].Renewable Energy Resources,2019,37(2):232-236.
[9] 黄晗,孙堃,刘达.基于随机森林的电力系统小时负荷预测研究[J].智慧电力,2018,46(5):8-14.HUANG Han,SUN Kun,LIU Da.Hourly load forecasting of power system based on random forest[J].Smart Power,2018,46(5):8-14.
[10] 谢毓广,刘童,陈凡,等.基于置信度理论和多元线性回归方程的电网负荷预测[J].电工技术,2018(13):42-45.XIE Yuguang,LIU Tong,CHEN Fan,et al.Network load forecasting based on confidence theory and multiple linear regression equation[J].Electric Engineering,2018(13):42-45.
[11] 林辉,刘晶,郝志峰,等.基于相似日负荷修正的节假日短期负荷预测[J].电力系统保护与控制,2010,38(7):47-51.LIN Hui,LIU Jing,HAO Zhifeng,et al.Short-term load forecasting for holidays based on the similar days load modification[J].Power System Protection and Control,2010,38(7):47-51.
[12] 李军,於阳.基于稀疏编码的短期风电功率时间序列预测[J].电力系统保护与控制,2018,46(12):16-23.LI Jun,YU Yang.Short-term wind power time series prediction based on sparse coding method[J].Power System Protection and Control,2018,46(12):16-23.
[13] 李啸骢,李春涛,从兰美,等.基于动态权值相似日选取算法的短期负荷预测[J].电力系统保护与控制,2017,45(6):1-8.LI Xiaocong,LI Chuntao,CONG Lanmei,et al.Short-term load forecasting based on dynamic weight similar day selection algorithm[J].Power System Protection and Control,2017,45(6):1-8.
[14] 吴云,雷建文,鲍丽山,等.基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J].电力系统自动化,2018,42(20):67-74.WU Yun,LEI Jianwen,BAO Lishan,et al.Short-term load forecasting based on improved grey relational analysis and neural network optimized by bat algorithm[J].Automation of Electric Power System,2018,42(20):67-74.
[15] 刘鑫,滕欢,宫毓斌,等.基于改进卡尔曼滤波算法的短期负荷预测[J].电测与仪表,2018,12(1):1-5.LIU Xin,TENG Huan,GONG Yubin,et al.Short-term load forecasting based on the improved Kalman filter algorithm[J].Electrical Measurement & Instrumentation ,2018,12(1):1-5.
[16] 许高明,覃正波.基于维纳滤波的节假日短期负荷预测[J].科技创新与应用,2015(2):15-16.XU Gaoming,QIN Zhengbo.Short-term load forecasting based on wiener filtering [J].Technology Innovation and Application,2015(2):15-16.
[17] 陆继翔,张琪培,杨志宏,等.基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J].电力系统自动化,2019(1):1-7.LU Jixiang,ZHANG Qipei,YANG Zhihong,et al.Short-term load forecasting method based on hybrid CNN-LSTM neural network model[J].Automation of Electric Power System,2019(1):1-7.
[18] 张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012,32(11):121-125.ZHANG Ping,PAN Xueping,XUE Wenchao.Short-term load forecasting based on wavelet decomposition,fuzzy gray correlation clustering and BP neural network[J].Electric Power Automation Equipment,2012,32(11):121-125.
[19] 黄元生,邓佳佳,苑珍珍.基于ARMA误差修正和自适应粒子群优化的SVM短期负荷预测[J].电力系统保护与控制,2011,39(14):26-32.HUANG Yuansheng,DENG Jiajia,YUAN Zhenzhen.SVM short-term load forecasting based on ARMA error calibration and the adaptive particle swarm optimization[J].Power System Protection and Control,2011,39(14):26-32.
[20] 祝志慧,孙云莲,季宇.基于EMD和SVM的短期负荷预测[J].高电压技术,2007,33(5):118-122.ZHU Zhihui,SUN Yunlian,JI Yu.Short-term load forecasting based on EMD and SVM[J].High Voltage Engineering,2007,33(5):118-122.
[21] 万强,王清亮,王睿豪,等.基于支持向量机的某地区电网短期电力负荷预测[J].电网与清洁能源,2016,32(12):14-20.WAN Qiang,WANG Qingliang,WANG Ruihao,et al.Short-term load forecasting of a regional power grid based on support vector machine[J].Power System and Clean Energy,2016,32(12):14-20.
[2] 吕跃春,廖晔,刘欣宇,等.基于规律性分析和误差修正的负荷预测方法[J].广东电力,2015,28(1):48-52.Lü Yuechun,LIAO Ye,LIU Xinyu,et al.Load forecast method based on regularity analysis and error correction [J].Guangdong Electric Power,2015,28(1):48-52.
[3] 李滨,黄佳,吴茵,等.基于分形特性修正气象相似日的节假日短期负荷预测方法[J].电网技术,2017,41(6):1949-1955.LI Bin,HUANG Jia,WU Yin,et al.Holiday short-term load forecasting based on fractal characteristic modified meteorological similar day[J].Power System Technology,2017,41(6):1949-1955.
[4] 郭建鹏,佘颖铃,温步瀛.基于EEMD-ARIMA模型的地区月负荷量预测[J].电力工程技术,2018,37(6):28-32,74.GUO Jianpeng,SHE Yingling,WEN Buying.Regional monthly load forecast based on EEMD-ARIMA model [J].Electric Power Engineering Technology,2018,37(6):28-32,74.
[5] 张冰玉.基于数据挖掘技术的短期电力负荷预测[J].电力大数据,2017,20(10):18-21.ZHANG Bingyu .Prediction of short-term power load based on data mining technology [J].Power Systems and Big Data,2017 ,20(10):18-21.
[6] 桑福敏,胡润滋.国家法定节假日重庆地区电网日负荷预测分析与研究[J].重庆电力高等专科学校学报,2015,20(6):42-45,57.SANG Fumin,HU Runzi.Analysis and research on the daily load forecast of the power grid in Chongqing during the national statutory holidays[J].Journal of Chongqing Electric Power College,2015,20(6):42-45,57.
[7] 侯亮,李焱.山西电网节假日短期负荷预测研究与分析[J].山西广播电视大学学报,2006(5):90-91.HOU Liang,LI Yan.Research and analysis on the holiday short-term load forecasting research of shanxi power network[J].Journal of Shanxi Radion & TV University,2006(5):90-91.
[8] 高靖,张明理,邓鑫阳,等.基于特征聚类的多能源系统负荷预测方法研究[J].可再生能源,2019,37(2):232-236.GAO Jing,ZHANG Mingli,DENG Xinyang,et al.Research on multi energy system load forecasting method based on feature clustering[J].Renewable Energy Resources,2019,37(2):232-236.
[9] 黄晗,孙堃,刘达.基于随机森林的电力系统小时负荷预测研究[J].智慧电力,2018,46(5):8-14.HUANG Han,SUN Kun,LIU Da.Hourly load forecasting of power system based on random forest[J].Smart Power,2018,46(5):8-14.
[10] 谢毓广,刘童,陈凡,等.基于置信度理论和多元线性回归方程的电网负荷预测[J].电工技术,2018(13):42-45.XIE Yuguang,LIU Tong,CHEN Fan,et al.Network load forecasting based on confidence theory and multiple linear regression equation[J].Electric Engineering,2018(13):42-45.
[11] 林辉,刘晶,郝志峰,等.基于相似日负荷修正的节假日短期负荷预测[J].电力系统保护与控制,2010,38(7):47-51.LIN Hui,LIU Jing,HAO Zhifeng,et al.Short-term load forecasting for holidays based on the similar days load modification[J].Power System Protection and Control,2010,38(7):47-51.
[12] 李军,於阳.基于稀疏编码的短期风电功率时间序列预测[J].电力系统保护与控制,2018,46(12):16-23.LI Jun,YU Yang.Short-term wind power time series prediction based on sparse coding method[J].Power System Protection and Control,2018,46(12):16-23.
[13] 李啸骢,李春涛,从兰美,等.基于动态权值相似日选取算法的短期负荷预测[J].电力系统保护与控制,2017,45(6):1-8.LI Xiaocong,LI Chuntao,CONG Lanmei,et al.Short-term load forecasting based on dynamic weight similar day selection algorithm[J].Power System Protection and Control,2017,45(6):1-8.
[14] 吴云,雷建文,鲍丽山,等.基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J].电力系统自动化,2018,42(20):67-74.WU Yun,LEI Jianwen,BAO Lishan,et al.Short-term load forecasting based on improved grey relational analysis and neural network optimized by bat algorithm[J].Automation of Electric Power System,2018,42(20):67-74.
[15] 刘鑫,滕欢,宫毓斌,等.基于改进卡尔曼滤波算法的短期负荷预测[J].电测与仪表,2018,12(1):1-5.LIU Xin,TENG Huan,GONG Yubin,et al.Short-term load forecasting based on the improved Kalman filter algorithm[J].Electrical Measurement & Instrumentation ,2018,12(1):1-5.
[16] 许高明,覃正波.基于维纳滤波的节假日短期负荷预测[J].科技创新与应用,2015(2):15-16.XU Gaoming,QIN Zhengbo.Short-term load forecasting based on wiener filtering [J].Technology Innovation and Application,2015(2):15-16.
[17] 陆继翔,张琪培,杨志宏,等.基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J].电力系统自动化,2019(1):1-7.LU Jixiang,ZHANG Qipei,YANG Zhihong,et al.Short-term load forecasting method based on hybrid CNN-LSTM neural network model[J].Automation of Electric Power System,2019(1):1-7.
[18] 张平,潘学萍,薛文超.基于小波分解模糊灰色聚类和BP神经网络的短期负荷预测[J].电力自动化设备,2012,32(11):121-125.ZHANG Ping,PAN Xueping,XUE Wenchao.Short-term load forecasting based on wavelet decomposition,fuzzy gray correlation clustering and BP neural network[J].Electric Power Automation Equipment,2012,32(11):121-125.
[19] 黄元生,邓佳佳,苑珍珍.基于ARMA误差修正和自适应粒子群优化的SVM短期负荷预测[J].电力系统保护与控制,2011,39(14):26-32.HUANG Yuansheng,DENG Jiajia,YUAN Zhenzhen.SVM short-term load forecasting based on ARMA error calibration and the adaptive particle swarm optimization[J].Power System Protection and Control,2011,39(14):26-32.
[20] 祝志慧,孙云莲,季宇.基于EMD和SVM的短期负荷预测[J].高电压技术,2007,33(5):118-122.ZHU Zhihui,SUN Yunlian,JI Yu.Short-term load forecasting based on EMD and SVM[J].High Voltage Engineering,2007,33(5):118-122.
[21] 万强,王清亮,王睿豪,等.基于支持向量机的某地区电网短期电力负荷预测[J].电网与清洁能源,2016,32(12):14-20.WAN Qiang,WANG Qingliang,WANG Ruihao,et al.Short-term load forecasting of a regional power grid based on support vector machine[J].Power System and Clean Energy,2016,32(12):14-20.