基于Sandia方法,对北京地区的3种不同能源系统（全空调建筑和2个可再生能源系统）,采用随机森林提取特征重要性的方法替代专家判断,定量地分配权重因子,生成适用于不同能源系统的典型气象年（TMY）,并利用EnergyPlus进行模拟分析。结果显示：该方法可定量地生成适用于不同能源系统的权重因子集,用于生成相应的TMY。根据不同能源系统的特性,对时间段进行划分并提取对应的权重因子集,可进一步提高TMY的代表性。
Abstract
Based on the Sandia method, this paper uses random forest to extract the importance of features instead of expert judgment to generate typical meteorological years (TMY) for three different energy systems (one fully air-conditioned building and two renewable energy systems) in Beijing. Energy Plus is used for simulation and analysis. The results show that this method can quantitatively generate the weight factor subsets suitable for different energy systems, which can be used to generate the corresponding TMY. The representativeness of TMY can be further improved by dividing time periods according to the characteristics of different energy systems and extracting corresponding weight factor subsets.
关键词
典型气象年 /
Sandia方法 /
权重因子 /
随机森林 /
特征重要性
Key words
typical meteorological year /
Sandia method /
weighting factors /
random forest /
feature importance
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] LI H L, YANG Y,LYU K L, et al.Compare several methods of select typical meteorological year for building energy simulation in China[J]. Energy, 2020, 209: 118465.
[2] HOSSEINI M, BIGTASHI A, LEE B.Evaluating the applicability of typical meteorological year under different building designs and climate conditions[J]. Urban climate, 2021, 38: 100870.
[3] CHEN S,REN Z, TANG Z,et al.Long-term prediction of weather for analysis of residential building energy consumption in Australia[J]. Energies, 2021, 14(16): 4805.
[4] DOBOS A P, GILMAN P, KASBERG M.P50/P90 analysis for solar energy systems using the system advisor model[R]. No.NREL/CP-6A20-54488, 2012.
[5] YANG H, LU L.Study of typical meteorological years and their effect on building energy and renewable energy simulations[J]. ASHRAE transactions, 2004, 110: 424-431.
[6] MANDURINO C,VESTRUCCI P.Using meteorological data to model pollutant dispersion in the atmosphere[J]. Environmental modelling & software, 2009, 24(2):270-278.
[7] LI H L, HUANG J, HU Y, et al.A new TMY generation method based on the entropy-based TOPSIS theory for different climatic zones in China[J]. Energy, 2021, 231: 120723.
[8] CHAN A L S. Generation of typical meteorological years using genetic algorithm for different energy systems[J]. Renewable energy, 2016, 90: 1-13.
[9] SUN J,LI Z, XIAO F, et al.Generation of typical meteorological year for integrated climate based daylight modeling and building energy simulation[J]. Renewable energy, 2020, 160: 721-729.
[10] HOSSEINI M, BIGTASHI A, LEE B.A systematic approach in constructing typical meteorological year weather files using machine learning[J]. Energy and buildings, 2020, 226: 110375.
[11] WILCOX S,MARION W.Users manual for TMY3 data sets (revised)[R]. No.NREL/TP-581-43156, 2008.
[12] 夏晓圣, 陈菁菁, 王佳佳, 等. 基于随机森林模型的中国PM2.5浓度影响因素分析[J]. 环境科学, 2020, 41(5): 2057-2065.
XIA X S,CHEN J J, WANG J J, et al.PM2.5 concentration influencing factors in China based on the random rorest model[J]. Environmental science, 2020, 41(5): 2057-2065.
[13] WILLIAM M, KEN U.User’s manual for TMY2s[R]. No.NREL/TP-463-7668, 1995.
[14] 黄金. 不同地域气候特征下典型气象年权重因子的构建方法及应用[D]. 西安: 西安建筑科技大学, 2021.
HUANG J.The method and application of determining the weight factors of typical meteorological year in different regions[D]. Xi’an: Xi’an University of Architecture and Technology, 2021.
[15] 曹泽涛, 方子东, 姚瑾, 等. 基于随机森林的黄土地貌分类研究[J]. 地球信息科学学报, 2020, 22(3): 452-463.
CAO Z T,FANG Z D,YAO J,et al.Loess landform classification based on random forest[J]. Journal of geo-information science, 2020, 22(3): 452-463.
[16] 黄金, 李红莲, 吕凯琳. 一种新的典型气象年权重因子构建方法[J]. 暖通空调, 2021, 51(2): 73-78, 59.
HUANG J, LI H L, LYU K L.New method for constructing weight factors of typical meteorological years[J]. Journal of HV&AC, 2021, 51(2): 73-78,59.
基金
国家自然科学基金面上项目（52278124）; “十三五”国家重点研发计划（2018YFC0704500）
PDF(1726 KB)
