超高层建筑用电最大负荷预测研究  

Predictive Research on Maximum Electric Load of Super High-rise Buildings

作　　者：宋辰 岳云涛 王成 岳世光 潘鑫 李佳旭 SONG Chen;YUE Yuntao;WANG Cheng;YUE Shiguang;PAN Xin;LI Jiaxu(China Architecture Design & Research Group, Beijing 100044,China;Beijing University of Civil Engineering and Architecture, College of Electrical and Information Engineering, Beijing 102616, China)

机构地区：[1]中国建筑设计研究院有限公司,北京市100044 [2]北京建筑大学电气与信息工程学院,北京市102616

出　　处：《建筑电气》2019年第5期34-38,共5页Building Electricity

摘　　要：针对100m以上250m以下的超高层建筑研究用电最大负荷,对已有实测超高层建筑用电数据进行分析与处理,分别采用BP神经网络算法和支持向量机算法进行建模和预测,最后对两种预测结果进行比较,从而确定出更适合超高层建筑用电最大负荷预测的方法。The maximum electric load of super high-rise buildings with height of 100 ~ 250 m is researched, the existing measured electricity consumption data of super high-rise buildings are analyzed and processed, the BP neural network algorithm and the support vector machine( SVM)algorithm are used for modeling and prediction.Finally, the two prediction results are compared to determine a more suitable method for predicting the maximum electric load of super high-rise buildings.

关 键 词：超高层建筑 最大负荷预测 BP神经网络算法 支持向量机算法 数据分析 数据处理 仿真计算 误差分析 

分 类 号：TU852[建筑科学]