基于数据挖掘的楼宇短期负荷预测方法研究

林顺富; 郝朝; 汤晓栋; 李东东; 符杨

引用本文:	林顺富,郝朝,汤晓栋,等.基于数据挖掘的楼宇短期负荷预测方法研究[J].电力系统保护与控制,2016,44(7):83-89.
	LIN Shunfu,HAO Chao,TANG Xiaodong,et al.Study of short-term load forecasting method based on data mining for buildings[J].Power System Protection and Control,2016,44(7):83-89

【打印本页】【下载PDF全文】【查看/发表评论】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 5427次下载 2951次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
基于数据挖掘的楼宇短期负荷预测方法研究
林顺富^1,2, 郝朝¹, 汤晓栋³, 李东东^1,2, 符杨¹
1.上海电力学院电气工程学院，上海 200090;2.上海高校高效电能应用工程研究中心，上海 200090;3.上海电器科学研究所，上海 200063

摘要:

楼宇短期负荷预测是楼宇能效管理系统中对用能子系统进行评估诊断、优化控制以及调度规划的重要基础。针对智能楼宇参与需求响应所需高精度、实时负荷信息的要求，提出一种基于数据挖掘支持向量机的楼宇短期负荷预测方法。选择与待预测时点相似相近的样本数据集，采用K-means算法对样本数据集中的温度、湿度、气压等气象数据进行聚类，根据聚类结果提取训练样本，最后采用支持向量机(SVM)算法建立负荷预测模型。实际应用结果表明，该方法预测结果平均相对误差为1.34%，相对误差在1%以内的概率达到67.5%，优于现有的时间序列法、同结构SVM法、不考虑气象因素的DMSVM法等方法。

关键词: 楼宇能效管理负荷预测数据挖掘支持向量机聚类分析

DOI：10.7667/PSPC151318

分类号:

基金项目:上海市科委科创项目(14DZ1201602)；国家自然科学基金项目(51207088)；上海绿色能源并网工程技术研究中心(13DZ2251900)；国网公司科技项目(SGRI-DL-71-14-004)

Study of short-term load forecasting method based on data mining for buildings

LIN Shunfu^1,2, HAO Chao¹, TANG Xiaodong³, LI Dongdong^1,2, FU Yang¹

1.College of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China;2. ShanghaiHigher Institution Engineering Research Center of High Efficiency Electricity Application, Shanghai 200090,China;3.Shanghai Electrical Apparatus Research Institute, Shanghai 200063, China

Abstract:

The load forecasting is the important basis of the energy management systems for the evaluation and diagnosis, optimized control, and scheduling of the energy subsystems in buildings. In order to obtain real-time and high accuracy load information, this paper proposes a short-term load forecasting method based on data mining for buildings. It firstly finds the sample datasets that are similar to the forecasted time points from the historical data, and then performs the K-means cluster analysis on the meteorological data, such as temperature, humidity, barometric pressure, etc., and finally adopts the support vector machine (SVM) for short term forecasting. The practical application results prove that the eMAPE of the proposed method is 1.34%, and the probability of the relative error less than 1% is 67.5%, which are obviously better than that of the ARIMA, SVM and DMSVM without meteorological data.

Key words: energy management of buildings load forecasting data mining support vector machine cluster analysis

X关闭