经济新常态下基于Verhulst-SVM的中长期负荷预测模型
|
摘要
经济新常态背景下,电力系统中长期负荷预测面临着很多新问题,例如:GDP、人口等电力负荷影响因素呈"S"型曲线增长、电力负荷影响因素与电力负荷之间的不确定性增加、历史样本数量少等。为此,提出一种基于Verhulst-SVM的中长期负荷预测模型。首先,从经济新常态特征中提取影响电力负荷的主要因素,并分析各影响因素的发展趋势;然后,利用Verhulst模型对"S"型曲线增长的电力负荷影响因素进行预测,并采用支持向量机(Support Vector Machine,SVM)替代线性回归预测模型,实现小样本、高不确定性条件下中长期负荷高精度预测。最后,通过天津市2015年和2016年的负荷预测算例,验证了所提模型的精度和可靠性,可为经济新常态背景下中长期负荷预测提供借鉴。
Under the background of the new normal economy of China,the medium-and long-term load forecasting of power systems faces many new problems. For example,the factors affecting the power load such as GDP and population are Sshaped curve growth,the uncertainty between power load and power load influencing factors increases,and the number of historical samples is small. To this end,a medium and long-term load forecasting model based on Verhulst-SVM is proposed in this paper. Firstly,the main factors affecting the electric load are extracted from the new normal of economy characteristics of China,and the development trend of each influencing factor is analyzed. Then,the Verhulst model is used to predict the load influencing factors which are S-shaped curve growth. And the support vector machine( SVM) is used to replace the linear regression prediction model to achieve high-precision prediction of medium and long-term load under small samples and high uncertainty. Finally,it is proved that the proposed model has high precision and reliability by predicting the power load of Tianjin in 2015 and 2016,which can provide reference for medium and long-term power load forecasting under the background of the new normal economy of China.
Under the background of the new normal economy of China,the medium-and long-term load forecasting of power systems faces many new problems. For example,the factors affecting the power load such as GDP and population are Sshaped curve growth,the uncertainty between power load and power load influencing factors increases,and the number of historical samples is small. To this end,a medium and long-term load forecasting model based on Verhulst-SVM is proposed in this paper. Firstly,the main factors affecting the electric load are extracted from the new normal of economy characteristics of China,and the development trend of each influencing factor is analyzed. Then,the Verhulst model is used to predict the load influencing factors which are S-shaped curve growth. And the support vector machine( SVM) is used to replace the linear regression prediction model to achieve high-precision prediction of medium and long-term load under small samples and high uncertainty. Finally,it is proved that the proposed model has high precision and reliability by predicting the power load of Tianjin in 2015 and 2016,which can provide reference for medium and long-term power load forecasting under the background of the new normal economy of China.
引文
[1]关于进一步深化电力体制改革的若干意见[R].北京:中共中央国务院,2015.
[2]李建民.中国的人口新常态与经济新常态[J].人口研究,2015,39(1):3-13.
[3]金鑫,罗滇生,孙广强,等.中长期电力负荷预测模型筛选与组合方法[J].电力系统及其自动化学报,2012,24(4):150-156.Jin Xin,Luo Diansheng,Sun Guangqiang,et al.Sifting and Combination Method of Medium-and Long-Term Load Forecasting Model[J].Proceedings of the CSU-EPSA,2012,24(4):150-156.
[4]肖先勇,葛嘉,何德胜.基于支持向量机的中长期电力负荷组合预测[J].电力系统及其自动化学报,2008,20(1):84-88.Xiao Xianyong,Ge Jia,He Desheng.Combination Method of Mid-Long Term Load Forecasting Based on Support Vector Machine[J].Proceedings of the CSU-EPSA,2008,20(1):84-88.
[5]邹品晶,姚建刚,孔维辉,等.基于多变量时间序列反演自记忆模型的中长期电力负荷预测[J].电力系统及其自动化学报,2017,29(10):98-105.Zhou Pinjing,Yao Jiangang,Kong Weihui,et al.Mid-long Term Power Load Forecasting Based on Multivariable Time Series Inversion Selfmemory Model[J].Proceedings of the CSU-EPSA,2017,29(10):98-105.
[6]李亦言,严正,冯冬涵.考虑城市化因素的中长期负荷预测模型[J].电力自动化设备,2016,36(4):54-61.Li Yiyan,Yan Zheng,Feng Donghan.Mid/long-term load forecasting model considering urbanization characteristics[J].Electric Power Automation Equipment,2016,36(4):54-61.
[7]王森,薛永端,仉志华,等.基于黄金分割法优选的中长期负荷变权组合预测[J].电测与仪表,2016,53(3):85-92.Wang Sen,Xue Yongrui,Zhang Zhihua,et al.Variable weight combination method for mid-long term load forecasting based on golden section algorithm)[J].Electrical Measurement&Instrumentation,2016,53(3):85-92.
[8]余建明,燕飞,杨文宇,等.中长期电力负荷的变权灰色组合预测模型[J].电网技术,2005,29(17):26-29.Yu Jianming,Yan Fei,Yang Wenyu,et al.Gray variable weight combination model for middle and long term load forecasting[J].Power System Technology,2005,29(17):26-29.
[9]李如琦,苏浩益,王宗耀,等.应用启发式最小二乘支持向量机的中长期电力负荷预测[J].电网技术,2011,35(11):195-199.Li Ruqi,Su Haoyi,Wang Zongyao,et al.Medium and long term load forecasting based on heuristic least square support vector machine[J].Power System Technology,2011,35(11):195-199.
[10]王义军,李殿文,高超,等.基于改进的PSO-SVM的短期电力负荷预测[J].电测与仪表,2015,52(3):22-25.Wang Yijun,Li Dianwen,Gao Chao,et al.Short-term power load forecasting based on improved PSO-SVM)[J].Electrical Measurement&Instrumentation,2015,52(3):22-25.
[11]罗治强,姚建刚,金永顺,等.中长期电力组合预测模型的理论研究[J].中国电机工程学报,2010,30(16):53-59.
[12]Niu Dongxiao,Wang Yongli.Optimization of support vector machine power load forecasting model based on data mining and Lyapunov exponents[J].Journal of Central South University of Technology,2010,17:406-412.
[13]胥威汀,李婷,刘友波,等.考虑电力市场交易影响的中长期负荷预测方法[J].电测与仪表,2017,54(2):100-108.
[14]Yang Shuxia,Cao Yuan,Liu Da,et al.RS-SVM forecasting model and power supply-demand forecast[J].Journal of Central South University of Technology,2011,18:2074-2079.
[15]王小君,毕圣,徐云鹍,等.基于数据挖掘技术和支持向量机的短期负荷预测[J].电测与仪表,2016,53(10):62-67.Wang Xiaojun,Bi Sheng,Xu Yunkun,et al.Short-term load forecasting based on support vector machines and data mining technology[J].Electrical Measurement&Instrumentation,2016,53(10):62-67.
[16]唐杰明,刘俊勇,杨可,等.基于灰色模型和最小二乘支持向量机的电力短期负荷组合预测[J].电网技术,2006,33(3):63-68.Tang Jieming,Liu Junyong,Yang Ke,et al.Short-term load combination forecasting by grey model and least square support vector machine[J].Power System Technology,2006,33(3):63-68.
[2]李建民.中国的人口新常态与经济新常态[J].人口研究,2015,39(1):3-13.
[3]金鑫,罗滇生,孙广强,等.中长期电力负荷预测模型筛选与组合方法[J].电力系统及其自动化学报,2012,24(4):150-156.Jin Xin,Luo Diansheng,Sun Guangqiang,et al.Sifting and Combination Method of Medium-and Long-Term Load Forecasting Model[J].Proceedings of the CSU-EPSA,2012,24(4):150-156.
[4]肖先勇,葛嘉,何德胜.基于支持向量机的中长期电力负荷组合预测[J].电力系统及其自动化学报,2008,20(1):84-88.Xiao Xianyong,Ge Jia,He Desheng.Combination Method of Mid-Long Term Load Forecasting Based on Support Vector Machine[J].Proceedings of the CSU-EPSA,2008,20(1):84-88.
[5]邹品晶,姚建刚,孔维辉,等.基于多变量时间序列反演自记忆模型的中长期电力负荷预测[J].电力系统及其自动化学报,2017,29(10):98-105.Zhou Pinjing,Yao Jiangang,Kong Weihui,et al.Mid-long Term Power Load Forecasting Based on Multivariable Time Series Inversion Selfmemory Model[J].Proceedings of the CSU-EPSA,2017,29(10):98-105.
[6]李亦言,严正,冯冬涵.考虑城市化因素的中长期负荷预测模型[J].电力自动化设备,2016,36(4):54-61.Li Yiyan,Yan Zheng,Feng Donghan.Mid/long-term load forecasting model considering urbanization characteristics[J].Electric Power Automation Equipment,2016,36(4):54-61.
[7]王森,薛永端,仉志华,等.基于黄金分割法优选的中长期负荷变权组合预测[J].电测与仪表,2016,53(3):85-92.Wang Sen,Xue Yongrui,Zhang Zhihua,et al.Variable weight combination method for mid-long term load forecasting based on golden section algorithm)[J].Electrical Measurement&Instrumentation,2016,53(3):85-92.
[8]余建明,燕飞,杨文宇,等.中长期电力负荷的变权灰色组合预测模型[J].电网技术,2005,29(17):26-29.Yu Jianming,Yan Fei,Yang Wenyu,et al.Gray variable weight combination model for middle and long term load forecasting[J].Power System Technology,2005,29(17):26-29.
[9]李如琦,苏浩益,王宗耀,等.应用启发式最小二乘支持向量机的中长期电力负荷预测[J].电网技术,2011,35(11):195-199.Li Ruqi,Su Haoyi,Wang Zongyao,et al.Medium and long term load forecasting based on heuristic least square support vector machine[J].Power System Technology,2011,35(11):195-199.
[10]王义军,李殿文,高超,等.基于改进的PSO-SVM的短期电力负荷预测[J].电测与仪表,2015,52(3):22-25.Wang Yijun,Li Dianwen,Gao Chao,et al.Short-term power load forecasting based on improved PSO-SVM)[J].Electrical Measurement&Instrumentation,2015,52(3):22-25.
[11]罗治强,姚建刚,金永顺,等.中长期电力组合预测模型的理论研究[J].中国电机工程学报,2010,30(16):53-59.
[12]Niu Dongxiao,Wang Yongli.Optimization of support vector machine power load forecasting model based on data mining and Lyapunov exponents[J].Journal of Central South University of Technology,2010,17:406-412.
[13]胥威汀,李婷,刘友波,等.考虑电力市场交易影响的中长期负荷预测方法[J].电测与仪表,2017,54(2):100-108.
[14]Yang Shuxia,Cao Yuan,Liu Da,et al.RS-SVM forecasting model and power supply-demand forecast[J].Journal of Central South University of Technology,2011,18:2074-2079.
[15]王小君,毕圣,徐云鹍,等.基于数据挖掘技术和支持向量机的短期负荷预测[J].电测与仪表,2016,53(10):62-67.Wang Xiaojun,Bi Sheng,Xu Yunkun,et al.Short-term load forecasting based on support vector machines and data mining technology[J].Electrical Measurement&Instrumentation,2016,53(10):62-67.
[16]唐杰明,刘俊勇,杨可,等.基于灰色模型和最小二乘支持向量机的电力短期负荷组合预测[J].电网技术,2006,33(3):63-68.Tang Jieming,Liu Junyong,Yang Ke,et al.Short-term load combination forecasting by grey model and least square support vector machine[J].Power System Technology,2006,33(3):63-68.