摘要
提出了一种数据驱动空间负荷预测方法。将网格化体系下的功能地块作为空间负荷预测的基本单元,并且通过多维指标体系进行属性描述。基于大量调研数据,通过数据挖掘方法对不同类型地块的空间负荷密度分布规律和负荷曲线典型形态进行提取。建立Softmax多元概率分类模型对未知地块的负荷水平类型进行匹配。自下而上对相邻地块负荷预测结果进行时域叠加,得到更大区域的预测信息,包括其负荷量和预测负荷曲线。算例仿真结果表明提出的空间负荷预测方法在预测精度上有一定提升。
A data-driven spatial load forecasting(SLF) method based on Softmax probabilistic classifier is proposed. The functional land plots in the grid system are used as SLF units of spatial load forecasting and the attribute is described through the multi-dimensional indicator system. Based on a large amount of research data, the law of spatial load density distribution and typical shape of load curve of different land plot types are extracted by data mining method. The Softmax probabilistic classifier is introduced to forecast load levels of unknown land plots. Bottom-up superposition for load forecasting results of adjacent land plots in time domain is conducted, which obtains forecasting information of larger area including load levels and forecasted load curve. The simulation results of the example show that the proposed spatial load forecasting method has a certain improvement in forecasting accuracy.
引文
[1] 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.
[2] 刘思,傅旭华,叶承晋,等.考虑地域差异的配电网空间负荷聚类及一体化预测方法[J].电力系统自动化,2017,41(3):70-75.DOI:10.7500/AEPS20160507003.LIU Si,FU Xuhua,YE Chengjin,et al.Spatial load clustering and integrated forecasting method of distribution network considering regional difference[J].Automation of Electric Power Systems,2017,41(3):70-75.DOI:10.7500/AEPS20160507003.
[3] 孙旭,任震.空间负荷预测在城市电网规划中的应用[J].电力系统保护与控制,2005,33(14):79-81.SUN Xu,REN Zhen.Application of spatial load forecasting in urban power network planning[J].Power System Protection and Control,2005,33(14):79-81.
[4] LEONARDO M O,JOHN F.Assessing the overall performance of Brazilian electric distribution companies[R/OL].[2018-05-20].http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.453.3503.
[5] HONG T,SHAHIDEHPOUR M.Load forecasting case study[R/OL].[2018-05-20].https://coefs.uncc.edu/hong/files/2015/03/WTP-2015-NARUC-HONG-Shahidehpour.pdf.
[6] WILLIS H L.Spatial electric load forecasting [M].2rd ed.New York:Marcel Dekker,2002.
[7] CHOW M Y,TRAM H.Methodology of urban re-development considerations in spatial load forecasting[J].IEEE Transactions on Power Systems,1997,12(2):996-1001.
[8] JOEL D M,EDGAR M C,ANTONIO P F.A cellular automaton approach to spatial electric load forecasting[J].IEEE Transactions on Power Systems,2011,26(2):532-540.
[9] JOEL D M,EDGAR M C,ANTONIO P F.Multi-agent simulation of urban social dynamics for spatial load forecasting[J].IEEE Transactions on Power Systems,2012,27(4):1870-1878.
[10] 赵强,景罗,赵光俊,等.顾及空间异质性的多尺度空间负荷预测[J].电力自动化设备,2014,34(2):91-96.ZHAO Qiang,JING Luo,ZHAO Guangjun,et al.Multi-scale spatial load forecasting considering spatial heterogeneity[J].Electric Power Automation Equipment,2014,34(2):91-96.
[11] 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):61-67.DOI:10.7500/AEPS20170328001.XIAO Bai,YANG Xintong,TIAN Li,et al.Spatial load forecasting method based on development degree of cell[J].Automation of Electric Power Systems,2018,42(1):61-67.DOI:10.7500/AEPS20170328001.
[12] 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):56-61.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):56-61.
[13] 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.
[14] YE Chengjin,DING Yi,SONG Yonghua,et al.A data driven multi-state model for distribution system flexible planning utilizing hierarchical parallel computing[J].Applied Energy,2018,232:9-25.
[15] QUILUMBA F L,LEE W J,HUANG Heng,et al.Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities[J].IEEE Transactions on Smart Grid,2015,6(2):911-918.
[16] NUTKIEWICZ A,YANG Zheng,JAIN R K.Data-driven urban energy simulation (DUE-S):a framework for integrating engineering simulation and machine learning methods in a multi-scale urban energy modeling workflow[J].Applied Energy,2018,225:1176-1189.
[17] 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.
[18] 方斯顿,程浩忠,徐国栋,等.基于非参数核密度估计的扩展准蒙特卡洛随机潮流方法[J].电力系统自动化,2015,39(7):21-27.FANG Sidun,CHENG Haozhong,XU Guodong,et al.An extended quasi Monte Carlo probabilistic load flow method based on non-parametric kernel density estimation[J].Automation of Electric Power Systems,2015,39(7):21-27.
[19] XIAO Junwei,LU Jianfeng,LI Xiangyu.Davies Bouldin index based hierarchical initialization k-means[J].Intelligent Data Analysis,2017,21(6):1327-1338.
[20] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521:436-444.
[21] LI Yiyan,HAN Dong,YAN Zheng.Long-term system load forecasting based on data-driven linear clustering method[J].Journal of Modern Power Systems and Clean Energy,2018,6(2):306-316.
[22] 城市电力规划规范:GB/T 50293—1999[S].北京:中国建筑工业出版社,1999.Specification for urban power planning:GB/T 50293—1999[S].Beijing:China Architecture & Building Press,1999.
[23] SCHOPFER S,TIEFENBECK V,STAAKE T.Economic assessment of photovoltaic battery systems based on household load profiles[J].Applied Energy,2018,223:229-248.