面向功能分区的大型商场建筑冷负荷预测方法
作者:
作者单位:

1.西安建筑科技大学,建筑设备与工程学院,西安 710055;2.西安建筑科技大学,信息与控制工程学院,西安 710055;3.中国建筑西北设计研究院有限公司,西安 710018

作者简介:

赵安军(1975—),男,西安建筑科技大学副教授,硕士生导师,主要研究方向为建筑物联网、建筑节能与能效分析、建筑设备控制与优化。

通讯作者:

荆竟 (1982—),男,高级工程师,(E-mail) xby5s@163.com。

中图分类号:

TP391.9

基金项目:

国家重点研发计划资助项目(2017YFC0704100)。


A cold load prediction method of shopping malls oriented to functional zoning
Author:
Affiliation:

1. School of Building Services Science and Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, P. R. China; ,;2.School of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, P. R. China; ,;3.China Northwest Architecture Design and Research Institute, Xi’an 710018, P. R. China

Fund Project:

Supported by National Key Research and Development Program(2017YFC0704100).

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [16]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对大型商场面向建筑整体冷负荷预测不能为商场各区域按需供冷提供合理控制策略的问题,通过研究商场不同区域冷负荷特点,采用灰色关联度分析法筛选影响商场不同区域冷负荷的关键影响因素,针对实际情况中各输入特征对冷负荷影响程度的不稳定性,提出了基于双重注意力机制和LSTM的短期分区冷负荷预测模型。LSTM网络充分考虑空调冷负荷与相关特征变量之间的非线性关系,特征注意力自主分析历史信息和输入变量之间的关系,提取重要特征,时序注意力选取LSTM网络关键时刻的历史信息,提升较长时间段预测效果的稳定性。以西安某大型商场建筑的冷负荷数据集为实验数据,实验结果表明所提模型相比于LSTM模型、CNN-LSTM模型和Attention-LSTM模型,误差指标MAPE和RMSE均有显著降低,R2明显增加且稳定0.99以上,具有较好的泛化能力和较强的稳定性。

    Abstract:

    Current cooling load prediction method of overall buildings for large-scale shopping malls cannot provide a reasonable control strategy for demands of various areas of the shopping mall. By studying the characteristics of cooling load in different areas of shopping malls, the key influencing factors of cooling load in different areas of shopping malls were screened by using grey relational degree analysis method. To solve the instability of the influence degree of each input variable on cooling load in actual situation, a short-term zoned cooling load prediction model based on double attention mechanism and LSTM was proposed. LSTM network fully considers the nonlinear relationship between air-conditioning cooling load and related characteristic variables. Feature attention analyzes the relationship between historical information and input variables autonomously to extract important features. Sequential attention selects historical information at critical moments of LSTM network to improve the stability of long-term prediction effects. The experimental results show that compared with LSTM model, CNN-LSTM model and attention-LSTM model, the error indexes MAPE and RMSE of the proposed model decrease significantly, and its R2 increases significantly and remains stable above 0.99, indicating good generalization ability and strong stability.

    参考文献
    [1] Fan C, Xiao F, Zhao Y. A short-term building cooling load prediction method using deep learning algorithms[J]. Applied Energy, 2017, 195: 222-233.
    [2] 杨福, 王衍金, 王伟宵. 基于eQUEST的某商业建筑空调系统节能分析[J]. 建筑节能, 2020, 48(5): 76-79.Yang F, Wang Y J, Wang W X. Energy simulation analysis of a commercial building based on eQUEST[J]. Building Energy Efficiency, 2020, 48(5): 76-79.(in Chinese)
    [3] Ahmad T, Chen H X, Guo Y B, et al. A comprehensive overview on the data driven and large scale based approaches for forecasting of building energy demand: a review[J]. Energy and Buildings, 2018, 165: 301-320.
    [4] American Society of Heating, Refrigerating and Air-Conditioning Engineers, Inc., Atlanta, (States)GA United. Building on the shoulders of giants. Annual report, July 1, 1994-June 30, 1995[R]. Office of Scientific and Technical Information (OSTI), 1996.
    [5] Campana J P, Morini G L. BESTEST and EN ISO 52016 benchmarking of ALMABuild, a new open-source simulink tool for dynamic energy modelling of buildings[J]. Energies, 2019, 12(15): 2938.
    [6] Abasnezhad S, Soltani N, Markarian E, et al. Impact of building design parameters precision on heating and cooling load calculations[J]. Environmental Progress & Sustainable Energy, 2019, 38(2): 741-749.
    [7] Zhou X, Fan Z B, Liang L Q, et al. Comparison of four algorithms based on machine learning for cooling load forecasting of large-scale shopping mall[J]. Energy Procedia, 2017, 142: 1799-1804.
    [8] Fan C L, Ding Y F. Cooling load prediction and optimal operation of HVAC systems using a multiple nonlinear regression model[J]. Energy and Buildings, 2019, 197: 7-17.
    [9] Fan C L, Liao Y D, Zhou G, et al. Improving cooling load prediction reliability for HVAC system using Monte-Carlo simulation to deal with uncertainties in input variables[J]. Energy and Buildings, 2020, 226: 110372.
    [10] 杨熊, 于军琪, 郭晨露, 等. 基于改进PSO-BP神经网络的冰蓄冷空调冷负荷动态预测模型[J]. 土木与环境工程学报(中英文), 2019, 41(1): 168-174.Yang X, Yu J Q, Guo C L, et al. Dynamic load forecasting model of ice storage air conditioning based on improved PSO-BP neural network[J]. Journal of Civil and Environmental Engineering, 2019, 41(1): 168-174. (in Chinese)
    [11] 周璇, 凡祖兵, 刘国强, 等. 基于多元非线性回归法的商场空调负荷预测[J]. 暖通空调, 2018, 48(3): 120-125, 95.Zhou X, Fan Z B, Liu G Q, et al. Cooling load prediction of shopping mall air conditioning based on multivariate nonlinear regression method[J]. Heating Ventilating & Air Conditioning, 2018, 48(3): 120-125, 95. (in Chinese)
    [12] 邵必林, 史洋博, 赵煜. 融合注意力机制与LSTM的建筑能耗预测模型研究[J]. 软件导刊, 2021, 20(10): 61-67.Shao B L, Shi Y B, Zhao Y. Research on building energy consumption prediction model by integrating attention mechanism and LSTM[J]. Software Guide, 2021, 20(10): 61-67.(in Chinese)
    [13] 李慧, 段培永, 刘凤英. 大型商场建筑夏季冷负荷动态预测模型[J]. 土木建筑与环境工程, 2016, 38(2): 104-110.Li H, Duan P Y, Liu F Y. Prediction model of dynamic cooling load for shopping mall building in summer[J]. Journal of Civil,Architectural & Environmental Engineering, 2016, 38(2): 104-110. (in Chinese)
    [14] 解海翔, 陈芳芳, 刘易, 等. 基于改进灰色关联分析和CMPSO-LSSVM算法的短期电力负荷预测[J]. 现代电子技术, 2021, 44(8): 177-181.Xie H X, Chen F F, Liu Y, et al. Short-term power load prediction based on improved grey relational analysis and CMPSO-LSSVM algorithm[J]. Modern Electronics Technique, 2021, 44(8): 177-181. (in Chinese)
    [15] 田浩含, 撖奥洋, 于立涛, 等. 基于GRA-LSTM神经网络的区域综合能源系统多元负荷短期预测模型[J]. 广东电力, 2020, 33(5): 44-51.Tian H H, Han A Y, Yu L T, et al. Research on multi-load short-term forecasting model of regional integrated energy system based on GRA-LSTM neural network[J]. Guangdong Electric Power, 2020, 33(5): 44-51. (in Chinese)
    [16] 周雨佳, 窦志成, 葛松玮, 等. 基于递归神经网络与注意力机制的动态个性化搜索算法[J]. 计算机学报, 2020, 43(5): 812-826.Zhou Y J, Dou Z C, Ge S W, et al. Dynamic personalized search based on RNN with attention mechanism[J]. Chinese Journal of Computers, 2020, 43(5): 812-826. (in Chinese)
    相似文献
    引证文献
引用本文

赵安军,杨航杰,荆竞,张萌芝,焦阳.面向功能分区的大型商场建筑冷负荷预测方法[J].重庆大学学报,2023,46(6):61-75.

复制
相关视频

分享
文章指标
  • 点击次数:371
  • 下载次数: 818
  • HTML阅读次数: 150
  • 引用次数: 0
历史
  • 收稿日期:2021-10-30
  • 在线发布日期: 2023-06-27
文章二维码