利用模糊信息粒化与支持向量机的空间负荷预测方法Spatial Load Forecasting Method Using Fuzzy Information Granulation and Support Vector Machine
肖白;赵晓宁;姜卓;施永刚;焦明曦;王徭;
摘要(Abstract):
若直接使用实测负荷数据最大值进行空间负荷预测,则元胞负荷中的异常数据会导致预测结果精度降低,考虑到通过确定并利用元胞负荷合理最大值可以明显改善预测精度,提出一种基于模糊信息粒化与支持向量机的空间负荷预测方法。首先构建电力地理信息系统,并在其中生成2类元胞。其次按照时间尺度的长短区分Ⅰ类元胞负荷颗粒度的粗细,通过划分模糊粒化窗口,建立合理的模糊集对Ⅰ类元胞细颗粒度下的历史负荷数据进行模糊信息粒化,进而确定出Ⅰ类元胞粗颗粒度下的历史负荷的合理最大值。然后采用支持向量机模型,对粗颗粒度下的Ⅰ类元胞负荷进行预测。最后确定Ⅰ类元胞负荷密度均衡系数,求取分类负荷密度指标,结合用地信息求得各Ⅱ类元胞负荷预测值,从而实现对空间电力负荷预测结果的网格化。工程实例表明了该方法的实用性和有效性。
关键词(KeyWords): 空间负荷预测;地理信息系统;模糊信息粒化;支持向量机;网格化
基金项目(Foundation): 国家自然科学基金项目(51177009);; 吉林省产业创新专项基金项目(2019C058-7);; 吉林省教育厅科技项目(JJKH20180442KJ)~~
作者(Author): 肖白;赵晓宁;姜卓;施永刚;焦明曦;王徭;
Email:
DOI: 10.13335/j.1000-3673.pst.2019.1463
参考文献(References):
- [1]Willis H L.Spatial electric load forecasting[M].New York,USA:Marcel Dekker,2002:217-243.
- [2]肖白,周潮,穆钢.空间电力负荷预测方法综述与展望[J].中国电机工程学报,2013,33(25):78-92.Xiao Bai,Zhou Chao,Mu Gang.Review and prospect of the spatial load forecasting methods[J].Proceedings of the CSEE,2013,33(25):78-92(in Chinese).
- [3]Xie Jingrui,Hong Tao.Load forecasting using 24 solar terms[J].Journal of Modern Power Systems and Clean Energy,2018,6(2):208-214.
- [4]Hong Tao,Pierre Pinson,Fan Shu.Global energy forecasting competition 2012[J].International Journal of Forecasting,2014,30(2):357-363.
- [5]Luo Jian,Hong Tao,Yue Meng.Real-time anomaly detection for very short-term load forecasting[J].Journal of Modern Power Systems and Clean Energy,2018,6(2):235-243.
- [6]杨丽徙,王金凤,陈根永,等.基于元胞自动机理论的电力负荷空间分布预测[J].中国电机工程学报,2007,27(4):15-20.Yang Lixi,Wang Jinfeng,Chen Genyong,et al.Load spatial distribution forecasting model on cellular automata theory[J].Proceedings of the CSEE,2007,27(4):15-20(in Chinese).
- [7]肖白,黎平.城网空间电力负荷预测中的规律性分析[J].电网技术,2009,33(20):113-118.Xiao Bai,Li Ping.A load regularity analysis on spatial load forecasting of urban power system[J].Power System Technology,2009,33(20):113-118(in Chinese).
- [8]肖白,刘庆永,牛强,等.基于元胞负荷特性分析的RBF神经网络空间负荷预测方法[J].电网技术,2018,42(1):301-306.Xiao Bai,Liu Qingyong,Niu Qiang,et al.Cellular load characteristics analysis RBF neural network spatial load forecasting method[J].Power System Technology,2018,42(1):301-306(in Chinese).
- [9]乐欢,王主丁,肖栋柱,等.基于空区推论的空间负荷预测分类分区实用法[J].电力系统自动化,2009,33(7):81-85.Le Huan,Wang Zhuding,Xiao Dongzhu,et al.Vacant area inference based classification and subarea practical method for spatial load forecasting[J].Automation of Electric Power Systems,2009,33(7):81-85(in Chinese).
- [10]朱凤娟,王主丁,陆俭,等.考虑小区发展不均衡的空间负荷预测分类分区法[J].电力系统自动化,2012,36(12):41-48.Zhu Fengjuan,Wang Zhuding,Lu Jian,et al.Disequilibrium development areas based classification and subarea method for spatial load forecasting[J].Automation of Electric Power Systems,2012,36(12):41-48(in Chinese).
- [11]刘思,傅旭华,叶承晋,等.应用聚类分析与非参数核密度估计的空间负荷分布规律[J].电网技术,2017,41(2):604-610.Liu Si,Fu Xuhua,Ye Chengjin,et al.Spatial load distribution based on clustering analysis and non-parametric kernel density estimation[J].Power System Technology,2017,41(2):604-610(in Chinese).
- [12]肖白,杨修宇,穆钢.基于元胞历史负荷数据的负荷密度指标法[J].电网技术,2014,38(4):1014-1019.Xiao Bai,Yang Xiuyu,Mu Gang.A load density index method based on historical data of cell load[J].Power System Technology,2014,38(4):1014-1019(in Chinese).
- [13]肖白,刘庆永,房龙江,等.基于模糊粗糙集理论和时空信息的空间负荷预测[J].电力建设,2017,38(1):58-67.Xiao Bai,Liu Qingyong,Fang Longjiang,et al.Spatial load forecasting based on fuzzy rough set theory with spatial and temporal information[J].Electric Power Construction,2017,38(1):58-67(in Chinese).
- [14]肖白,杨欣桐,田莉,等.计及元胞发展程度的空间负荷预测方法[J].电力系统自动化,2018,42(1):61-66.Xiao Bai,Yang Xintong,Tian Li,et al.Spatial load forecasting method considering the development degree of the cells[J].Automation of Electric Power Systems,2018,42(1):61-66(in Chinese).
- [15]Witold Pedrycz.Knowledge-based clustering-from data to information granules[M].New York:John Wiley&Sons,Inc,2003.
- [16]Bargicla A,Pedrycz W.Granular computing:an introduction[M].Dodrecht:Kluwer Academic Publishers,2003.
- [17]许宗礼.人民币兑美元汇率短期预测研究-基于模糊信息粒化的SVM模型[D].广州:暨南大学,2016.
- [18]候聪,何大四,靳晓东.基于模糊信息粒化和支持向量机的空调负荷预测[J].建筑热能通风空调,2017,36(2):28-32.Hou Cong,He Dasi,Jin Xiaodong.Air conditioning load forecasting based on fuzzy information granulation and support vector machine[J].Building Energy&Environment,2017,36(2):28-32(in Chinese).
- [19]王恺,关少卿,汪令祥,等.基于模糊信息粒化和最小二乘支持向量机的风电功率联合预测建模[J].电力系统保护与控制,2015,43(2):27-31.Wang Kai,Guan Shaoqing,Wang Lingxiang,et al.Fuzzy information granulation and least squares support vector machine joint forecasting modeling of wind power[J].Power System Protection and Control,2015,43(2):27-31(in Chinese).
- [20]丁志勇,杨苹,杨曦,等.基于连续时间段聚类的支持向量机风电功率预测方法[J].电力系统自动化,2012,36(14):132-135.Ding Zhiyong,Yang Ping,Yang Xi,et al.Wind power prediction method based on sequential time clustering support vector machine[J].Automation of Electric Power Systems,2012,36(14):132-135(in Chinese).
- [21]肖白,聂鹏,穆钢,等.基于多级聚类分析和支持向量机的空间负荷预测方法[J].电力系统自动化,2015,39(12):56-60.Xiao Bai,Nie Peng,Mu Gang,et al.A spatial load forecasting method based on multilevel clustering analysis and support vector machine[J].Automation of Electric Power Systems,2015,39(12):56-60(in Chinese).
- [22]杨茂,陈新鑫,张强,等.基于支持向量机的短期风速预测研究综述[J].东北电力大学学报,2017,37(4):1-7.Yang Mao,Chen Xinxin,Zhang Qiang,et al.A review of short-term wind speed prediction based on support vector machine[J].Journal of Northeast Electric Power University,2017,37(4):1-7(in Chinese).
- [23]李国庆,张钰,张明江,等.基于MRMR的集合经验模态分解和支持向量机的风电功率实时预测[J].东北电力大学学报,2017,37(2):39-44.Li Guoqing,Zhang Yu,Zhang Mingjiang,et al.The wind power real-time prediction based on the EEMD and SVM of the MRMR[J]Journal of Northeast Electric Power University,2017,37(2):39-44(in Chinese).
- [24]肖白,蒲睿,穆钢.基于多尺度空间分辨率的空间负荷预测误差评价方法[J].中国电机工程学报,2015,35(22):5731-5739.Xiao Bai,Pu Rui,Mu Gang.Method of spatial load forecasting error evaluation based on the multi-scale spatial resolution[J].Proceedings of the CSEE,2015,35(22):5731-5739(in Chinese).
- [25]Prada J,Dorronsoro J R.General noise support vector regression with non-constant uncertainty intervals for solar radiation prediction[J].Journal of Modern Power Systems and Clean Energy,2018,6(2):268-280.
- [26]Ma Ziming,Zhong Haiwang,Le Xie,et al.Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model:an ERCOT case study[J].Journal of Modern Power Systems and Clean Energy,2018,6(2):281-291.
- [27]吴倩红,高军,候广松,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):67-71.Wu Qianhong,Gao Jun,Hou Guangsong,et al.Impact of renewable power plant collector system on stability of grid-connected multi-converters[J].Automation of Electric Power Systems,2016,40(15):67-71(in Chinese).
- [28]崔天晓,周小龙,刘文浩,等.基于Hilbert包络谱和SVM的齿轮故障诊断[J].东北电力大学学报,2017,37(6):56-61.Cui Tianxiao,Zhou Xiaolong,Liu Wenhao,et al.Gear fault diagnosis based on Hilbert envelope spectrum and SVM[J].Journal of Northeast Electric Power University,2017,37(6):56-61(in Chinese).
- [29]杨茂,黄宾阳,江博,等.基于卡尔曼滤波和支持向量机的风电功率实时预测研究[J].东北电力大学学报,2017,37(2):45-51.Yang Mao,Huang Binyang,Jiang Bo,et al.Real-time prediction for wind power based on Kalman filter and support vector machines[J].Journal of Northeast Electric Power University,2017,37(2):45-51(in Chinese).
- [30]康重庆,夏清,刘梅.电力系统负荷预测[M].北京:中国电力出版社,2007:94-97.