上海交通大学学报 ›› 2021, Vol. 55 ›› Issue (3): 331-336.doi: 10.16183/j.cnki.jsjtu.2019.310

所属专题: 《上海交通大学学报》2021年“土木建筑工程”专题 《上海交通大学学报》2021年12期专题汇总专辑

• • 上一篇    下一篇

基于支持向量机的办公建筑逐时能耗预测

肖冉, 魏子清, 翟晓强()   

  1. 上海交通大学 制冷与低温工程研究所,上海  200240
  • 收稿日期:2019-10-25 出版日期:2021-03-01 发布日期:2021-04-02
  • 通讯作者: 翟晓强 E-mail:xqzhai@sjtu.edu.cn
  • 作者简介:肖冉(1996-), 男,四川省广安市人,硕士生,主要研究方向为智慧建筑与建筑节能.
  • 基金资助:
    国家重点研发计划(2017YFC0704200)

Hourly Energy Consumption Forecasting for Office Buildings Based on Support Vector Machine

XIAO Ran, WEI Ziqing, ZHAI Xiaoqiang()   

  1. Institute of Refrigeration and Cryogenics, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2019-10-25 Online:2021-03-01 Published:2021-04-02
  • Contact: ZHAI Xiaoqiang E-mail:xqzhai@sjtu.edu.cn

摘要:

针对建筑运行能耗非线性和不确定性强的特点,提出一种基于支持向量机的办公建筑逐时能耗预测方法. 采用单变量模型检验法确定模型输入变量,引入网格搜索方法优化模型超参数. 使用模型拟合误差的置信区间来描述建筑运行能耗的不确定性. 采用实际办公楼案例对所提出的预测方法进行验证. 结果表明:网格搜索优化后的模型平均绝对百分比误差(MAPE)降低31.3%, 取得更高的模型精度; 加入置信区间后不同季节中MAPE均低于1.5%, 体现了建筑的运行波动. 该方法可为建筑运行诊断及优化提供参考.

关键词: 能耗, 预测方法, 支持向量机, 网格搜索, 置信区间

Abstract:

Aimed at the nonlinearity and uncertainty of building energy consumption, a forecasting approach based on the support vector machine is proposed in this paper for the prediction of hourly energy consumption of an office building. The univariate model test is used to determine the input parameters. Superior model hyper-parameters are found by grid search optimization. The confidence interval of the model fitting error is applied to describe the uncertainty of building energy consumption. A case study is conducted using the data collected from an actual office building to verify the proposed approach. The results show that the overall mean absolute percentage error (MAPE) of the model after grid search optimization is reduced by 31.3%, and a higher model precision is achieved. After combining the prediction with the confidence interval, MAPE is found to be lower than 1.5% in different seasons and the building operation fluctuations are embodied. This approach can be used in the diagnosis and optimization of building operation.

Key words: energy consumption, forecasting approach, support vector machine, grid search, confidence interval

中图分类号: