融合历史数据和实时影响因素的精细化负荷预测
|
摘要
随着智能电网技术的飞速发展,对负荷预测的精度提出了越来越高的要求。融合负荷、天气等多源数据,提出了一种基于数据融合的支持向量机精细化负荷预测方法。首先对负荷历史数据进行聚类分析,将运行日分成六类。然后将负荷数据和温度、湿度等天气数据进行融合,针对六类聚类结果分别建立基于数据融合的支持向量机精细化负荷预测模型,并对模型参数进行全局优化。采用不同的预测模型对浙江省某地级市2013年的负荷进行预测,结果表明所提出的负荷预测方法的预测精度明显高于传统的负荷预测方法的预测精度。
With the rapid development of smart grid technology, increasingly demand on the accuracy of load forecasting is put forward. Integrating load, weather and other multi-sourced data, a refined load forecasting method of Support Vector Machine(SVM) based on data fusion is proposed. Firstly, the historical load data is clustered and the operation days are divided into six categories. Then the weather data such as temperature and humidity are combined with the load data, and the refined load forecasting models of SVM based on data fusion are established respectively for the six clustering results. And the parameters of the model are optimized globally. Different forecasting models are used to predict the load of a prefecture-level city in Zhejiang Province in 2013, the prediction results show that the prediction accuracy of the load forecasting method proposed in this paper is obviously higher than that of the traditional load forecasting method.
With the rapid development of smart grid technology, increasingly demand on the accuracy of load forecasting is put forward. Integrating load, weather and other multi-sourced data, a refined load forecasting method of Support Vector Machine(SVM) based on data fusion is proposed. Firstly, the historical load data is clustered and the operation days are divided into six categories. Then the weather data such as temperature and humidity are combined with the load data, and the refined load forecasting models of SVM based on data fusion are established respectively for the six clustering results. And the parameters of the model are optimized globally. Different forecasting models are used to predict the load of a prefecture-level city in Zhejiang Province in 2013, the prediction results show that the prediction accuracy of the load forecasting method proposed in this paper is obviously higher than that of the traditional load forecasting method.
引文
[1]雷正新,韩蓓,聂萌,等.配电网大数据环境下的多点负荷预测算法与应用研究[J].电力系统保护与控制,2016,44(23):1-11.LEI Zhengxin,HAN Bei,NIE Meng,et al.Multipoint load forecasting algorithm and its application in distribution network big data environment[J].Power System Protection and Control,2016,44(23):1-11.
[2]王新,孟玲玲.基于EEMD-LSSVM的超短期负荷预测[J].电力系统保护与控制,2015,43(1):61-66.WANG Xin,MENG Lingling.Ultra-short term load forecasting based on EEMD-LSSVM[J].Power System Protection and Control,2015,43(1):61-66.
[3]苏学能,刘天琪,曹鸿谦,等.基于Hadoop架构的多重分布式BP神经网络的短期负荷预测方法[J].中国电机工程学报,2017,37(17):4966-4973,5216.SU Xueneng,LIU Tianqi,CAO Hongqian,et al.Short-term load forecasting method for multi-distributed BP neural network based on Hadoop architecture[J].Proceedings of the CSEE,2017,37(17):4966-4973,5216.
[4]罗楠,朱业玉,杜彩月,等.支持向量机方法在电力负荷预测中的应用[J].电网技术,2007,31(增刊2):215-218.LUO Nan,ZHU Yeyu,DU Caiyue,et al.Application of support vector machine method in electric load forecasting[J].Power System Technology,2007,31(S2):215-218.
[5]耿艳,韩学山,韩力.基于最小二乘支持向量机的短期负荷预测[J].电网技术,2008,32(18):72-76.GENG Yan,HAN Xueshan,HAN Li.Short-term load forecasting based on least squares support vector machine[J].Power System Technology,2008,32(18):72-76.
[6]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):121-125,141.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):121-125,141.
[7]祖向荣,田敏,白焰.基于模糊聚类与函数小波核回归的短期负荷预测方法[J].电力自动化设备,2016,36(10):134-140,165.ZU Xiangrong,TIAN Min,BAI Yan.Short term load forecasting method based on fuzzy clustering and function wavelet kernel regression[J].Electric Power Automation Equipment,2016,36(10):134-140,165.
[8]吴倩红,高军,侯广松,等.实现影响因素多源异构融合的短期负荷预测支持向量机算法[J].电力系统自动化,2016,40(15):67-72,92.WU Qianhong,GAO Jun,HOU Guangsong,et al.Short-term load forecasting support vector machine algorithm based on multi-source heterogeneous fusion of load factors[J].Automation of Electric Power Systems,2016,40(15):67-72,92.
[9]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.A short-term load forecasting method based on fractal feature correction of meteorological similar days[J].Power System Technology,2017,41(6):1949-1955.
[10]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,2009,33(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,2009,33(3):63-68.
[11]王海云,田莎莎,张再驰,等.基于负荷预测与关联规则修正的不良数据辨识方法[J].电力系统保护与控制,2017,45(23):24-33.WANG Haiyun,TIAN Shasha,ZHANG Zaichi,et al.Amethod of identifying bad data based on load forecasting and association rules[J].Power System Protection and Control,2017,45(23):24-33.
[12]杨慧霞,邓迎君,刘志斌,等.含有历史不良数据的电力负荷预测研究[J].电力系统保护与控制,2017,45(15):62-68.YANG Huixia,DENG Yingjun,LIU Zhibin,et al.Research on power load forecasting with historical bad data[J].Power System Protection and Control,2017,45(15):62-68.
[13]高亚静,孙永健,杨文海,等.基于新型人体舒适度的气象敏感负荷短期预测研究[J].中国电机工程学报,2017,37(7):1946-1955.GAO Yajing,SUN Yongjian,YANG Wenhai,et al.Study on short-term forecast of meteorological sensitive load based on new human comfort[J].Proceedings of the CSEE,2017,37(7):1946-1955.
[14]HUO J,SHI T,CHANG J.Comparison of random forest and SVM for electrical short-term load forecast with different data sources[C]//2016 7th IEEE International Conference on Software Engineering and Service Science(ICSESS),August 26-28,2016,Beijing,China:1077-1080.
[15]YE N,LIU Y,WANG Y.Short-term power load forecasting based on SVM[C]//World Automation Congress 2012,June 24-28,2012,Puerto Vallarta,Mexico:47-51.
[16]ZHANG M G,LI L R.Short-term load combined forecasting method based on BPNN and LS-SVM[C]//2011 IEEE Power Engineering and Automation Conference,September 8-9,2011,Wuhan,China:319-322.
[17]SELAKOV A,ILIC S,VUKMIROVIC S,et al.Acomparative analysis of SVM and ANN based hybrid model for short term load forecasting[C]//PES T&D2012,May 7-10,2012,Orlando,FL,USA:1-5.
[18]LIU B,XU G.Short-term power load forecasting based on LS-SVM[C]//2010 International Conference of Information Science and Management Engineering,August 7-8,2010,Xi'an,China:311-314.
[19]ZHANG Q,LIU T.Application of SVM and wavelet neural network method for short-term power load forecasting[C]//The 2nd International Conference on Computer and Automation Engineering(ICCAE),February26-28,2010,Singapore,Singapore:412-416.
[20]牛东晓,刘达,陈广娟,等.基于遗传优化的支持向量机小时负荷滚动预测[J].电工技术学报,2007,22(6):148-153.NIU Dongxiao,LIU Da,CHEN Guangjuan,et al.Support vector machine models optimized by genetic algorithm for hourly load rolling forecasting[J].Transactions of China Electrotechnical Society,2007,22(6):148-153.
[21]谢宏,魏江平,刘鹤立.短期负荷预测中支持向量机模型的参数选取和优化方法[J].中国电机工程学报,2006,26(22):17-22.XIE Hong,WEI Jiangping,LIU Heli.Parameter selection and optimization method of SVM model for short-term load forecasting[J].Proceedings of the CSEE,2006,26(22):17-22.
[22]张玉,莫寒,张烈平.基于模糊支持向量机的光伏发电量预测[J].热力发电,2017,46(1):116-120.ZHANG Yu,MO Han,ZHANG Lieping.Photovoltaic power generation prediction based on fuzzy support vector machine[J].Thermal Power Generation,2017,46(1):116-120.
[23]张然然,刘鑫屏.火电机组超短期负荷预测[J].热力发电,2018,47(7):52-57.ZHANG Ranran,LIU Xinping.Ultra short term load forecast for thermal power units[J].Thermal Power Generation,2018,47(7):52-57.
[24]李若晨,朱帆,朱永利,等.结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测[J].电力系统保护与控制,2018,46(17):83-88.LI Ruochen,ZHU Fan,ZHU Yongli,et al.Short-term load forecasting of power system based on recurrent neural network combined with restricted Boltzmann machine[J].Power System Protection and Control,2018,46(17):83-88.
[25]方八零,李龙,赵家铸,等.动态相似与静态相似相结合的短期负荷预测方法[J].电力系统保护与控制,2018,46(15):29-35.FANG Baling,LI Long,ZHAO Jiazhu,et al.Short-term load forecasting method combining dynamic similarity with static similarity[J].Power System Protection and Control,2018,46(15):29-35.
[2]王新,孟玲玲.基于EEMD-LSSVM的超短期负荷预测[J].电力系统保护与控制,2015,43(1):61-66.WANG Xin,MENG Lingling.Ultra-short term load forecasting based on EEMD-LSSVM[J].Power System Protection and Control,2015,43(1):61-66.
[3]苏学能,刘天琪,曹鸿谦,等.基于Hadoop架构的多重分布式BP神经网络的短期负荷预测方法[J].中国电机工程学报,2017,37(17):4966-4973,5216.SU Xueneng,LIU Tianqi,CAO Hongqian,et al.Short-term load forecasting method for multi-distributed BP neural network based on Hadoop architecture[J].Proceedings of the CSEE,2017,37(17):4966-4973,5216.
[4]罗楠,朱业玉,杜彩月,等.支持向量机方法在电力负荷预测中的应用[J].电网技术,2007,31(增刊2):215-218.LUO Nan,ZHU Yeyu,DU Caiyue,et al.Application of support vector machine method in electric load forecasting[J].Power System Technology,2007,31(S2):215-218.
[5]耿艳,韩学山,韩力.基于最小二乘支持向量机的短期负荷预测[J].电网技术,2008,32(18):72-76.GENG Yan,HAN Xueshan,HAN Li.Short-term load forecasting based on least squares support vector machine[J].Power System Technology,2008,32(18):72-76.
[6]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):121-125,141.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):121-125,141.
[7]祖向荣,田敏,白焰.基于模糊聚类与函数小波核回归的短期负荷预测方法[J].电力自动化设备,2016,36(10):134-140,165.ZU Xiangrong,TIAN Min,BAI Yan.Short term load forecasting method based on fuzzy clustering and function wavelet kernel regression[J].Electric Power Automation Equipment,2016,36(10):134-140,165.
[8]吴倩红,高军,侯广松,等.实现影响因素多源异构融合的短期负荷预测支持向量机算法[J].电力系统自动化,2016,40(15):67-72,92.WU Qianhong,GAO Jun,HOU Guangsong,et al.Short-term load forecasting support vector machine algorithm based on multi-source heterogeneous fusion of load factors[J].Automation of Electric Power Systems,2016,40(15):67-72,92.
[9]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.A short-term load forecasting method based on fractal feature correction of meteorological similar days[J].Power System Technology,2017,41(6):1949-1955.
[10]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,2009,33(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,2009,33(3):63-68.
[11]王海云,田莎莎,张再驰,等.基于负荷预测与关联规则修正的不良数据辨识方法[J].电力系统保护与控制,2017,45(23):24-33.WANG Haiyun,TIAN Shasha,ZHANG Zaichi,et al.Amethod of identifying bad data based on load forecasting and association rules[J].Power System Protection and Control,2017,45(23):24-33.
[12]杨慧霞,邓迎君,刘志斌,等.含有历史不良数据的电力负荷预测研究[J].电力系统保护与控制,2017,45(15):62-68.YANG Huixia,DENG Yingjun,LIU Zhibin,et al.Research on power load forecasting with historical bad data[J].Power System Protection and Control,2017,45(15):62-68.
[13]高亚静,孙永健,杨文海,等.基于新型人体舒适度的气象敏感负荷短期预测研究[J].中国电机工程学报,2017,37(7):1946-1955.GAO Yajing,SUN Yongjian,YANG Wenhai,et al.Study on short-term forecast of meteorological sensitive load based on new human comfort[J].Proceedings of the CSEE,2017,37(7):1946-1955.
[14]HUO J,SHI T,CHANG J.Comparison of random forest and SVM for electrical short-term load forecast with different data sources[C]//2016 7th IEEE International Conference on Software Engineering and Service Science(ICSESS),August 26-28,2016,Beijing,China:1077-1080.
[15]YE N,LIU Y,WANG Y.Short-term power load forecasting based on SVM[C]//World Automation Congress 2012,June 24-28,2012,Puerto Vallarta,Mexico:47-51.
[16]ZHANG M G,LI L R.Short-term load combined forecasting method based on BPNN and LS-SVM[C]//2011 IEEE Power Engineering and Automation Conference,September 8-9,2011,Wuhan,China:319-322.
[17]SELAKOV A,ILIC S,VUKMIROVIC S,et al.Acomparative analysis of SVM and ANN based hybrid model for short term load forecasting[C]//PES T&D2012,May 7-10,2012,Orlando,FL,USA:1-5.
[18]LIU B,XU G.Short-term power load forecasting based on LS-SVM[C]//2010 International Conference of Information Science and Management Engineering,August 7-8,2010,Xi'an,China:311-314.
[19]ZHANG Q,LIU T.Application of SVM and wavelet neural network method for short-term power load forecasting[C]//The 2nd International Conference on Computer and Automation Engineering(ICCAE),February26-28,2010,Singapore,Singapore:412-416.
[20]牛东晓,刘达,陈广娟,等.基于遗传优化的支持向量机小时负荷滚动预测[J].电工技术学报,2007,22(6):148-153.NIU Dongxiao,LIU Da,CHEN Guangjuan,et al.Support vector machine models optimized by genetic algorithm for hourly load rolling forecasting[J].Transactions of China Electrotechnical Society,2007,22(6):148-153.
[21]谢宏,魏江平,刘鹤立.短期负荷预测中支持向量机模型的参数选取和优化方法[J].中国电机工程学报,2006,26(22):17-22.XIE Hong,WEI Jiangping,LIU Heli.Parameter selection and optimization method of SVM model for short-term load forecasting[J].Proceedings of the CSEE,2006,26(22):17-22.
[22]张玉,莫寒,张烈平.基于模糊支持向量机的光伏发电量预测[J].热力发电,2017,46(1):116-120.ZHANG Yu,MO Han,ZHANG Lieping.Photovoltaic power generation prediction based on fuzzy support vector machine[J].Thermal Power Generation,2017,46(1):116-120.
[23]张然然,刘鑫屏.火电机组超短期负荷预测[J].热力发电,2018,47(7):52-57.ZHANG Ranran,LIU Xinping.Ultra short term load forecast for thermal power units[J].Thermal Power Generation,2018,47(7):52-57.
[24]李若晨,朱帆,朱永利,等.结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测[J].电力系统保护与控制,2018,46(17):83-88.LI Ruochen,ZHU Fan,ZHU Yongli,et al.Short-term load forecasting of power system based on recurrent neural network combined with restricted Boltzmann machine[J].Power System Protection and Control,2018,46(17):83-88.
[25]方八零,李龙,赵家铸,等.动态相似与静态相似相结合的短期负荷预测方法[J].电力系统保护与控制,2018,46(15):29-35.FANG Baling,LI Long,ZHAO Jiazhu,et al.Short-term load forecasting method combining dynamic similarity with static similarity[J].Power System Protection and Control,2018,46(15):29-35.