[1]杨屹洲,方瑞明,黄文权,等.应用小波变换和支持向量机的商业电力负荷预测[J].华侨大学学报(自然科学版),2015,36(2):142-146.[doi:10.11830/ISSN.1000-5013.2015.02.0142]
　YANG Yi-zhou,FANG Rui-ming,HUANG Wen-quan,et al.Commercial Power Load Forecasting Using Wavelet Transform and SVM[J].Journal of Huaqiao University(Natural Science),2015,36(2):142-146.[doi:10.11830/ISSN.1000-5013.2015.02.0142]
点击复制

应用小波变换和支持向量机的商业电力负荷预测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第2期
页码:
142-146
栏目:
出版日期:
2015-03-20

文章信息/Info

Title:
Commercial Power Load Forecasting Using Wavelet Transform and SVM
文章编号:
1000-5013(2015)02-0142-05
作者:
杨屹洲1;  方瑞明1;  黄文权1;  梁颖1;  汪亮2
1. 华侨大学 信息科学与工程学院, 福建 厦门 361021;2. 厦门埃锐圣电力科技有限公司, 福建 厦门 361002
Author(s):
YANG Yi-zhou1;  FANG Rui-ming1;  HUANG Wen-quan1;  LIANG Ying1;  WANG Liang2
1. College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China; 2. Akson Power Technology Limited, Xiamen 361002, China
关键词:
商业电力;  负荷预测;  支持向量机;  小波分解;  节能;  数据采集系统;  粒子群算法
Keywords:
commercial power;  load forecasting;  support vector machine;  wavelet transform;  saving energy;  data acquisition system;  particle swarm optimization
分类号:
TM715
DOI:
10.11830/ISSN.1000-5013.2015.02.0142
文献标志码:
A
摘要:
提出一种基于小波分解和支持向量机相结合的模型,将其应用于预测商业建筑电力负荷.首先,基于商业建筑配电系统的数据采集系统实时监测数据,分析商业负荷用电特性,指出商业负荷的随机特性造成单一预测模型精度难以满足要求.其次,提出了一种基于小波分解和粒子群支持向量机的商业电力负荷预测算法.通过小波变换把负荷序列分解为不同频段的子序列,再对这些子序列分别采用不同的粒子群支持向量机模型进行预测,引入粒子群算法对支持向量机模型参数进行寻优.最后,将各分量预测值重构得到最终预测值.实验结果证明:小波分解后和粒子群支持向量机相结合的模型精度明显优于单一支持向量机模型.
Abstract:
A model based on wavelet transform and support vector machine(SVM)was proposed, and which is applied to power load forecasting of commercial buildings. Firstly, this paper is based on real time monitoring data of the data acquisition system of the electrical distribution system for commercial buildings which analyzes the characteristics of commercial model load, and states the fact that the precision of single forecasting model is difficult to meet the requirement because of the random characteristic of commercial load. Secondly, a predictive algorithm for commercial power load based on wavelet transform and particle swarm optimization(PSO)-SVM is proposed through the wavelet transform decomposition of load sequence into the components of different frequencies, then a PSO-SVM model is built for each component to forecast and the PSO algorithm is used to output the optimal parameters. Finally, reconstruct the forecasting result of each component to obtain the final forecast. Experimental result shows that the wavelet PSO-SVM model is a more accurate model to predict electricity consumption than that of the model only based on SVM.

参考文献/References:

[1] DONG Bing,CAO Cheng,LEE S E.Applying support vector machines to predict building energy consumption in tropical region[J].Energy and Buildings,2005,37(5):545-553.
[2] KISSOCK J K.A methodology to measure retrofit energy savings in commercial buildings[D].Texas:Texas A and M University,1993:32-57.
[3] DHAR A,REDDY T A,CLARIDGE D E.A fourier series model to predict hourly heating and cooling energy use in commercial buildings with outdoor temperature as the only weather variable[J].Journal of Solar Energy Engineering,1999,121(1):47-53.
[4] DONG B,LEE S E,SAPAR M H.A holistic utility bill analysis method for baselining whole commercial building energy consumption in Singapore[J].Energy and Building,2005,37(2):167-174.
[5] GUILLERMO E.New artificial neural network prediction method for electrical consumption forecasting based on building end-uses[J].Energy and Building,2011,43(11):3112-3119.
[6] 方瑞明.支持向量机理论及其应用分析[M].北京:中国电力出版社,2007:15-19.
[7] 曾勍炜,徐知海,吴键.基于粒子群优化和支持向量机的电力负荷预测[J].微电子与计算机,2001,28(1):147-153.
[8] 王红瑞,刘晓红,唐奇,等.基于小波变换的支持向量机水文过程预测[J].清华大学学报:自然科学版,2010,50(9):1378-1381.
[9] 张华,郁永静,冯志军.基于小波分解与支持向量机的风速预测模型[J].水利发电学报,2012,31(1):208-212.
[10] 韩勇,李红梅.基于小波分解的支持向量机母线负荷预测[J].电力自动化设备,2012,32(4):88-91.
[11] 李元诚,方廷健,郑国祥.短期电力负荷预测的小波支持向量机方法研究[J].中国科学技术大学学报,2003,33(6):726-732.
[12] 梁颖,方瑞明.基于SCADA和支持向量回归的风电机组状态在线评估方法[J].电力系统自动化,2013,37(14):8-12.
[13] 付宝英,王启志.自适应粒子群优化BP神经网络的变压器故障诊断[J].华侨大学学报:自然科学版,2013,34(3):262-266.
[14] 路志英,李艳英,陆洁,等.粒子群算法优化RBF-SVM沙尘暴预报模型参数[J].天津大学学报:学报自然科学版,2008,41(4):413-418.

相似文献/References:

[1]杨屹洲,方瑞明,黄文权,等.应用小波变换和支持向量机的商业电力负荷预测[J].华侨大学学报(自然科学版),2015,36(预先出版):0.
　YANG Yi-zhou,FANG Rui-ming,HUANG Wen-quan,et al.Commercial Power Load Forecasting Based on Wavelet Transform and SVM[J].Journal of Huaqiao University(Natural Science),2015,36(2):0.

备注/Memo

备注/Memo:
收稿日期: 2013-11-26
通信作者: 方瑞明(1972-),男,教授,博士,主要从事电气装置智能诊断、特种电机分析与设计的研究.E-mail:fangrm@hqu.edu.cn.
基金项目: 福建省自然科学基金资助项目(2012J01223)
更新日期/Last Update: 2015-03-20