基于电力需求响应的公共建筑基线负荷预测

山东大学学报(工学版) ›› 2011, Vol. 41 ›› Issue (2): 114-118.

基于电力需求响应的公共建筑基线负荷预测

马庆,李歧强*

山东大学控制科学与工程学院, 山东济南 250061

收稿日期:2010-11-10 出版日期:2011-04-16 发布日期:2010-11-10
通讯作者: 李歧强(1964- ),男,山东临沂人，教授,博士,博士生导师,主要研究方向为复杂系统优化调度的建模和算法. Email: qqli@sdu.edu.cn E-mail:qqli@sdu.edu.cn
作者简介:马庆(1971- ),男,山东海阳人,讲师,博士研究生,主要研究方向为电力需求响应与建筑节能. Email: maqing@sdu.edu.cn
基金资助:
山东省科学技术发展计划资助项目(2007GG20007004);山东省信息产业发展专项资助项目 (2007R00065)

Public buildings baseline load forecasting based on demand
response in electric power

MA Qing, LI Qiqiang*

School of Control Science and Engineering, Shandong University, Jinan 250061, China

Received:2010-11-10 Online:2011-04-16 Published:2010-11-10

摘要/Abstract

摘要：

针对公共建筑基线负荷难以有效预测的问题,提出了一种基于模糊C均值聚类预处理的人工神经网络预测方法。采用聚类算法,将大量的复杂历史数据集划分成多个群体的混合,每个群体对应单独的预测模型进行预测。该方法减少了培训数据,克服了标准方法数据量大和处理速度慢的缺点。将预测结果与标准的人工神经网络方法相比较,得到了较高的预测精度,能有效预测公共建筑基线负荷。

关键词: 基线负荷预测, 需求响应, 模糊C均值聚类, 人工神经网络

Abstract:

According to the problem that public buildings baseline load was hard to forecast effectively, a kind of artificial neutral network forecasting method based on Fuzzy C-Means (FCM) optimization preprocesses was proposed. The complicated historical data were divided into a mixture of multiple populations, and each population was represented by a single forecasting model. This method could reduce ANN training data and overcame the disadvantage of very large data and slow processing speed. The forecasting result can have greater forecasting accuracy and effectively forecast the public buildings baseline load compared with the standard BP neutral network.

Key words: baseline load forecasting, demand response, FCM algorithm, artificial neutral network

马庆,李歧强*. 基于电力需求响应的公共建筑基线负荷预测[J]. 山东大学学报(工学版), 2011, 41(2): 114-118.

MA Qing, LI Qiqiang*. Public buildings baseline load forecasting based on demand
response in electric power[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2011, 41(2): 114-118.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed