彭显刚;潘可达;张丹;刘艺;林志坚;

• 1:广东工业大学自动化学院
• 2:广东电网有限责任公司汕头供电局

摘要(Abstract)：

针对季节性电力负荷划分不准确及温度、湿度对电力负荷的动态性影响,提出一种基于季节性负荷自适应划分及重要点分割的多分段短期负荷预测模型。采用聚类与CART树相结合的方法,根据地区历史负荷数据自适应的确定当地季节性负荷划分规则;使用非参数核密度估计方法提取季节典型日负荷曲线,并基于划分结果对各季负荷曲线进行重要点分割;同时根据分割结果,采用基于皮尔逊相关系数加权的相似系数,对各时段负荷进行参考日的筛选,以确定预测模型的输入量,最后提出一种结合纵横交叉算法参数优化的鲁棒极限学习机进行多分段预测模型的建立。通过实例仿真分析,验证了所提方法提高预测精度的有效性。

关键词(KeyWords)： 聚类分析;CART决策树;重要点分割;改进鲁棒极限学习机;短期负荷预测

Abstract:

Keywords:

基金项目(Foundation): 中央财政支持地方高校发展专项资金项目(粤财教[2016] 202号)~~

作者(Author): 彭显刚;潘可达;张丹;刘艺;林志坚;

Email:

DOI: 10.13335/j.1000-3673.pst.2018.1705

参考文献(References)：

• [1]康重庆，夏清，刘梅．电力系统负荷预测[M]．中国电力出版社，2017.
• [2] Overbye T J,Weber J.Smart grid wide-area transmission system visualization[J].Engineering,2015,1(4):466-474.
• [3] Kuster C,Rezgui Y,Mourshed M.Electrical load forecasting models:a critical systematic review[J].Sustainable Cities&Society,2017,35.
• [4]彭显刚，郑伟钦，林利祥，等．考虑负荷自适应检测和修复的鲁棒极限学习机短期负荷预测方法[J]．中国电机工程学报，2016,36(23):6409-6417.Peng Xiangang,Zheng Weiqin,Lin Lixiang,et al.Short-term load forecasting method based on outlier robust extreme learning machine considering adaptive load detection and repair[J].Proceedings of the CSEE,2016,36(23):6409-6417(in Chinese).
• [5] Bessec M,Fouquau J.Short-run electricity load forecasting with combinations of stationary wavelet transforms[J].European Journal of Operational Research,2017,264:149-164.
• [6] H?verstad B A,Tidemann A,Langseth H,et al.Short-term load forecasting with seasonal decomposition using evolution for parameter tuning[J].IEEE Transactions on Smart Grid,2015,6(4):1904-1913.
• [7]李江，王宝财，陈继开．考虑气象因素的改进虚拟交互回归负荷预测方法[J]．南方电网技术，2017,11(8):72-79.Li Jiang,Wang Baocai,Chen Jikai.Improved dummy interactive regression method for load forecasting considering meteorological factors[J].Southern Power System Technology,2017,11(8):72-79(in Chinese).
• [8]卜凡鹏，陈俊艺，张琪祁，等．一种基于双层迭代聚类分析的负荷模式可控精细化识别方法[J]．电网技术，2018,42(3):903-913.Bu Fanpeng,Chen Junyi,Zhang Qiqi,et al.A controllable and refine recognition method of electrical load pattern based on bilayer iterative clustering analysis[J].Power System Technology,2018,42(3):903-913(in Chinese).
• [9]王星华，陈卓优，彭显刚．一种基于双层聚类分析的负荷形态组合识别方法[J]．电网技术，2016,40(5):1495-1501.Wang Xinghua,Chen Zhuoyou,Peng Xiangan.A new combinational electrical load analysis method based on bilayer clustering analysis[J].Power System Technology,2016,40(5):1495-1501(in Chinese).
• [10]陈华丰，张葛祥．基于决策树和支持向量机的电能质量扰动识别[J]．电网技术，2013,37(5):1272-1278.Chen Huafeng, Zhang Gexiang. Power quality disturbance identification using decision tree and support vector machine[J].Power System Technology,2013,37(5):1272-1278(in Chinese).
• [11] Hong T,Wang P,White L.Weather station selection for electric load forecasting[J].International Journal of Forecasting,2015,31(2):286-295.
• [12]刘荣，方鸽飞．改进Elman神经网络的综合气象短期负荷预测[J]．电力系统保护与控制，2012,40(22):113-117.Liu Rong, Fang Gefei. Short-term load forecasting with comprehensive weather factors based on improved Elman neural network[J].Power System Protection&Control,2012,40(22):113-117(in Chinese).
• [13]马瑞，周谢，彭舟，等．考虑气温因素的负荷特性统计指标关联特征数据挖掘[J]．中国电机工程学报，2015,35(1):43-51.Ma Rui,Zhou Xie,Peng Zhou,et al.Data mining on correlation feature of load characteristics statistical indexes considering temperature[J].Proceedings of the CSEE,2015,35(1):43-51(in Chinese).
• [14]孙宏斌，陈佳，江曦源，等．最小信息损失综合短期负荷预测(二)：算法和算例[J]．中国电机工程学报，2016,36(18):4801-4807.Sun Hongbin,Chen Jia,Jiang Xiyuan,et al.Minimization of information loss based hybrid short-term load forecasting part2-algorithm and case study[J].Proceedings of the CSEE,2016,36(18):4801-4807(in Chinese).
• [15]陈超，黄国勇，邵宗凯，等．基于日特征量相似日的PSO-SVM短期负荷预测[J]．中国电力，2013,46(7):91-94.Chen Chao,Huang Guoyong,Shao Zongkai,et al.Short-term load forecasting for similar days based on PSO-SVM and daily feature vector[J].Electric Power,2013.46(7):91-94(in Chinese).
• [16] Fuad M M M,Marteau P F.Speeding-up the similarity search in time series databases by coupling dimensionality reduction techniques with a fast-and-dirty filter[C]//IEEE Fourth International Conference on Semantic Computing.IEEE Computer Society,Pittsburgh,2010:101-104.
• [17]程敏，翁宁泉，刘庆，等．基于时间序列分段的气象数据压缩算法[J]．计算机系统应用，2014,23(8):125-129.Cheng Min,Weng Ningquan,Liu Qing,et al.Meteorological data compression algorithm based on time-series segmentation[J].Computer Systems&Applications,2014,23(8):125-129(in Chinese).
• [18] Li Y,Wang S,Deng C.Redundant ridgelet transform and its application to image processing[C]//Fifth International Conference on Information Assurance and Security.IEEE Computer Society,Xian,2009:225-228.
• [19]高亚静，孙永健，杨文海，等．基于非参数核密度估计和改进谱多流形聚类的负荷曲线分类研究[J]．电网技术，2018,42(5):1605-1612.Gao Yajing,Sun Yongjian,Yang Wenhai,et al.Study on load curve’s classification based on nonparametric kernel density estimation and improved spectral multi-manifold clustering[J]. Power System Technology,2018,42(5):1605-1612(in Chinese).
• [20] Zhang K,Luo M.Outlier-robust extreme learning machine for regression problems[J].Neurocomputing,2015,151(3):1519-1527.
• [21] Meng A B,Chen Y C,Yin H,et al.Crisscross optimization algorithm and its application[J].Knowledge-Based Systems,2014,67(4):218-229.
• [22] File Exchange-MATLAB Central[EB/OL].http：//cn.Mathworks.com/matlabcentral/fileexchange/31877-electricity-load-forecasting-for-theaustralian-market-case-study.
• [23]李鹏，何帅，韩鹏飞，等．基于长短期记忆的实时电价条件下智能电网短期负荷预测[J]．电网技术，2018,DOI:10.13335/j.1000-3673.Pst.2018.0433.Li Peng,He Shuai,Han Pengfei,et al.Short term load forecasting of smart grid based on long short term memory recurrent neural networks in condition of real-time electricity price[J].Power System Technology, 2018, DOI:10.13335/j.1000-3673.Pst.2018.0433(in Chinese).