Comprehensive prediction of thermal comfort and energy consumption for high-speed railway stations

doi:10.11772/j.issn.1001-9081.2020060889

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (1): 249-257.DOI: 10.11772/j.issn.1001-9081.2020060889

Special Issue: 第八届中国数据挖掘会议(CCDM 2020)

• China Conference on Data Mining 2020 (CCDM 2020) • Previous Articles Next Articles

Comprehensive prediction of thermal comfort and energy consumption for high-speed railway stations

JIANG Yangsheng¹, WANG Shengnan², TU Jiaqi³, LI Sha³, WANG Hongjun⁴

1. School of Transportation and Logistics, Southwest Jiaotong University, Chengdu Sichuan 611756, China;
2. Building Engineering Design and Research Institute, China Railway Eryuan Engineering Group Company Limited, Chengdu Sichuan 610031, China;
3. School of Economics and Management, Southwest Jiaotong University, Chengdu Sichuan 610031, China;
4. School of Information Science and Technology, Southwest Jiaotong University, Chengdu Sichuan 611756, China

Received:2020-03-31 Revised:2020-07-16 Online:2021-01-10 Published:2020-09-02
Supported by:
This work is partially supported by the National Key Research and Development Program of China (2018YFC0705000).

面向高铁站的热舒适度和能耗综合预测

蒋阳升¹, 王胜男², 涂家祺³, 李莎³, 王红军⁴

1. 西南交通大学交通运输与物流学院, 成都 611756;
2. 中铁二院工程集团有限责任公司建筑工程设计研究院, 成都 610031;
3. 西南交通大学经济管理学院, 成都 610031;
4. 西南交通大学信息科学与技术学院, 成都 611756

通讯作者: 王红军
作者简介:蒋阳升(1976-),男,湖南衡阳人,教授,博士,主要研究方向:智能交通控制、机器学习;王胜男(1989-),女,辽宁沈阳人,工程师,硕士,主要研究方向:空调系统节能控制、机器学习、地道风技术;涂家祺(1996-),女,四川江油人,硕士研究生,主要研究方向:机器学习、物流配送资源优化;李莎(1997-),女,四川宜宾人,硕士研究生,主要研究方向:机器学习、物流配送资源优化;王红军(1977-),男,四川广安人,副研究员,博士,CCF高级会员,主要研究方向:机器学习、数据挖掘。
基金资助:
国家重点研发计划项目（2018YFC0705000）。

Abstract

Abstract: As many factors affect the thermal comfort of semi-enclosed buildings such as high-speed railway stations in a complex way and there exists contradiction between thermal comfort and energy consumption, a comprehensive prediction method for thermal comfort and energy consumption of high-speed railway station based on machine learning was proposed. Firstly, with sensor data capturing and Energy Plus platform, the indoor and outdoor status, the control units like multi-evaporator air conditioners and heat exchangers as well as the thermal energy transmission environment of high-speed railway station were modeled. Secondly, eight factors influencing the thermal comfort of high-speed railway station, such as the operating number of multi-evaporator air conditioners and setting temperatures of multi-evaporator air conditioners, the operating number of heat exchangers, passenger density, outdoor temperature, indoor temperature, indoor humidity, and indoor carbon dioxide concentration, were proposed, 424 model operating conditions and 3 714 240 instances were designed. Finally, in order to effectively predict indoor thermal comfort and energy consumption of high-speed railway station, six machine learning methods, which are deep neural network, support vector regression, decision tree regression, linear regression, ridge regression and Bayesian ridge regression, were designed. Experimental results show that decision tree regression has the best prediction performance in a short time with average mean squared error of 0.002 2. The obtained research results can directly provide actively predicted environmental parameters and realize real-time decision-making for the temperature control strategy in the next stage.

Key words: machine learning, urban computing, thermal comfort, prediction, regression

摘要： 针对高铁站这类半封闭建筑的热舒适度影响因素众多，影响机制复杂以及热舒适度与能耗存在背反等问题，提出了基于机器学习的高铁站热舒适度与能耗综合预测方法。首先采用传感器数据捕获及Energy Plus仿真两种方式对高铁站室内外状态、多联机及热交换机等控制单元及热能传导环境进行建模；其次提出影响高铁站热舒适度的八类因素——多联机开启台数、多联机设置温度、热交换机开启台数、客流密度、室外温度、室内温度、室内湿度和室内二氧化碳浓度，并设计424种模型运行工况以及3 714 240个实例；最后设计6种机器学习模型——深度神经网络、支持向量回归、决策树回归、线性回归、岭回归和贝叶斯岭回归，来对高铁站室内热舒适度和空调能耗进行有效预测。实验结果表明，6种机器学习模型中决策树回归预测模型能够在较短的时间内获得最优的预测性能，其平均均方误差低至0.002 2。所得研究成果可直接为下一阶段的温控策略提供主动预判的环境状态参数并实现实时决策。

关键词: 机器学习, 城市计算, 热舒适度, 预测, 回归

CLC Number:

TP181

JIANG Yangsheng, WANG Shengnan, TU Jiaqi, LI Sha, WANG Hongjun. Comprehensive prediction of thermal comfort and energy consumption for high-speed railway stations[J]. Journal of Computer Applications, 2021, 41(1): 249-257.

蒋阳升, 王胜男, 涂家祺, 李莎, 王红军. 面向高铁站的热舒适度和能耗综合预测[J]. 计算机应用, 2021, 41(1): 249-257.

References

[1] ZHENG Y,CAPRA L,WOLFSON O,et al. Urban computing:concepts,methodologies,and applications[J]. ACM Transactions on Intelligent Systems and Technology,2014,5(3):No. 38.
[2] LIU W,CUI P,NURMINEN J K,et al. Special issue on intelligent urban computing with big data[J]. Machine Vision and Applications,2017,28(7):675-677.
[3] FANGER P O. Thermal comfort:analysis and applications in environmental engineering[J]. Thermal Comfort Analysis & Applications in Environmental Engineering,1972,3(3):225-240.
[4] BU J U,KIM T Y,KIM I S,et al. Silicon-based thermal comfort sensing device[J]. Sensors and Actuators A:Physical,1996,54(1/2/3):468-471.
[5] CHOW T T,FONG K F,GIVONI B,et al. Thermal sensation of Hong Kong people with increased air speed, temperature and humidity in air-conditioned environment[J]. Building and Environment,2010,45(10):2177-2183.
[6] 刘永颉, 赵安军, 葛恒. 典型温带地区住宅热舒适度影响因素分析[J]. 工业控制计算机,2015,28(5):127-129.(LIU Y J, ZHAO A J,GE H. Analysis of factors influencing residential thermal comfort in typical temperate regions[J]. Industrial Control Computer,2015,28(5):127-129.)
[7] CHAN S Y,CHAU C K. Development of artificial neural network models for predicting thermal comfort evaluation in urban parks in summer and winter[J]. Building and Environment,2019,164:No. 106364.
[8] JOWKAR M,DE DEAR R,BRUSEY J. Influence of long-term thermal history on thermal comfort and preference[J]. Energy and Buildings,2020,210:No. 109685.
[9] 高立新. 室内热舒适度智能预测器的研究[J]. 计算机测量与控制,2002,10(8):519-520,526.(GAO L X. Research on the intelligent predictor of indoor thermal comfort[J]. Computer Measurement and Control,2002,10(8):519-520,526.)
[10] YUCE B,LI H,REZGUI Y,et al. Utilizing artificial neural network to predict energy consumption and thermal comfort level:an indoor swimming pool case study[J]. Energy and Buildings, 2014,80:45-56.
[11] 侯赞, 陈德旺, 李焱. 基于集成模糊推理的列车运行舒适度评价方法及应用[J]. 铁路计算机应用,2012,21(7):4-7.(HOU Z, CHEN D W, LI Y. Comfort evaluation method and its application for train operation based on ensemble fuzzy reasoning[J]. Railway Computer Application,2012,21(7):4-7.)
[12] MARVUGLIA A, MESSINEO A, NICOLOSI G. Coupling a neural network temperature predictor and a fuzzy logic controller to perform thermal comfort regulation in an office building[J]. Building and Environment,2014,72:287-299.
[13] 潘伟强, 李长云, 胡盛龙. 基于支持向量机的室内舒适度评价方法[J]. 计算机技术与发展,2013,23(6):214-218.(PAN W Q,LI C Y,HU S L. Indoor comfort evaluation method based on support vector machine[J]. Computer Technology and Development,2013,23(6):214-218.)
[14] 杨福迈. 寒冷地区民用建筑温度舒适度评价设计仿真[J]. 计算机仿真,2017,34(8):445-448.(YANG F M. Design and simulation of temperature comfort evaluation for civil buildings in cold regions[J]. Computer Simulation,2017,34(8):445-448.)
[15] 张玲, 王玲, 吴桐. 基于改进的粒子群算法优化反向传播神经网络的热舒适度预测模型[J]. 计算机应用,2014,34(3):775-779.(ZHANG L,WANG L,WU T. Thermal comfort prediction model based on improved particle swarm optimization-back propagation neural network[J]. Journal of Computer Applications, 2014,34(3):775-779.)
[16] 郭彤颖, 陈露. 基于鸟群算法优化BP神经网络的热舒适度预测[J]. 计算机系统应用,2018,27(4):162-166.(GUO T Y, CHEN L. Thermal comfort prediction analysis based on BP neural network optimized by bird swarm algorithm[J]. Computer Systems and Applications,2018,27(4):162-166.)
[17] SALAMONE F,BELUSSI L,CURRÒ C,et al. Integrated method for personal thermal comfort assessment and optimization through users' feedback,IoT and machine learning:a case study[J]. Sensors,2018,18(5):No. 1602.
[18] GUENTHER J,SAWODNY O. Feature selection and Gaussian process regression for personalized thermal comfort prediction[J]. Building and Environment,2019,148:448-458.
[19] JI Y, WANG Z. Thermal adaptations and logistic regression analysis of thermal comfort in severe cold area based on two case studies[J]. Energy and Buildings,2019,205:No. 109560.
[20] WANG Z,WANG J,HE Y,et al. Dimension analysis of subjective thermal comfort metrics based on ASHRAE Global Thermal Comfort Database using machine learning[J]. Journal of Building Engineering,2019,29:No. 101120.
[21] MUI K W,TSANG T W,WONG L T. Bayesian updates for indoor thermal comfort models[J]. Journal of Building Engineering, 2020,29:No. 101117.
[22] LUO M,XIE J,YAN Y,et al. Comparing machine learning algorithms in predicting thermal sensation using ASHRAE Comfort Database Ⅱ[J]. Energy and Buildings,2020,210:No. 109776.
[23] NGARAMBE J,YUN G Y,SANTAMOURIS M. The use of Artificial Intelligence(AI)methods in the prediction of thermal comfort in buildings:energy implications of AI-based thermal comfort controls[J]. Energy and Buildings, 2020, 211:No. 109807.
[24] KIKEGAWA Y,GENCHI Y,KONDO H,et al. Impacts of cityblock-scale countermeasures against urban heat-island phenomena upon a building's energy-consumption for air-conditioning[J]. Applied Energy,2006,83(6):649-668.
[25] LI C, ZHOU J, CAO Y, et al. Interaction between urban microclimate and electric air-conditioning energy consumption during high temperature season[J]. Applied Energy,2014,117:149-156.
[26] 杨世忠, 任庆昌. 基于空调大系统优化的冷却水系统能耗仿真[J]. 计算机仿真,2016,33(1):348-352.(YANG S Z,REN Q C. Energy consumption simulation of cooling water system based on large scale system optimization of air conditioning systems[J]. Computer Simulation,2016,33(1):348-352.)
[27] JIM C Y. Air-conditioning energy consumption due to green roofs with different building thermal insulation[J]. Applied Energy, 2014,128:49-59.
[28] YUAN L,KANG Y,WANG S,et al. Effects of thermal insulation characteristics on energy consumption of buildings with intermittently operated air-conditioning systems under real time varying climate conditions[J]. Energy and Buildings,2017,155:559-570.
[29] MA Z,SONG J,ZHANG J. Energy consumption prediction of airconditioning systems in buildings by selecting similar days based on combined weights[J]. Energy and Buildings,2017,151:157-166.
[30] ZHOU X,YAN D,AN J,et al. Comparative study of airconditioning energy use of four office buildings in China and USA[J]. Energy and Buildings,2018,169:344-352.
[31] ATTHAJARIYAKUL S, LEEPHAKPREEDA T. Real-time determination of optimal indoor-air condition for thermal comfort, air quality and efficient energy usage[J]. Energy and Buildings, 2004,36(7):720-733.
[32] ATTHAJARIYAKUL S, LEEPHAKPREEDA T. Neural computing thermal comfort index for HVAC systems[J]. Energy Conversion and Management,2005,46(15/16):2553-2565.
[33] WEI X,KUSIAK A,LI M,et al. Multi-objective optimization of the HVAC (heating,ventilation,and air conditioning) system performance[J]. Energy,2015,83:294-306.
[34] ZHENG Z,LI J. Optimal chiller loading by improved invasive weed optimization algorithm for reducing energy consumption[J]. Energy and Buildings,2018,161:80-88.
[35] 段冠囡, 王岳人. 超高层建筑暖通空调能耗精准预测仿真[J]. 计算机仿真,2018,35(12):317-320,379.(DUAN G N, WANG Y R. Simulation of HVAC energy consumption prediction for super high-rise building[J]. Computer Simulation,2018,35(12):317-320,379.)
[36] 钱青, 唐桂忠, 张广明, 等. 基于AR-DBN的建筑分项能耗短期预测[J]. 计算机工程,2019,45(6):290-296.(QIAN Q,TANG G Z,ZHANG G M,et al. Short term prediction of itemized building energy consumption based on AR-DBN[J]. Computer Engineering,2019,45(6):290-296.)
[37] TRAN D H, LUONG D L, CHOU J S. Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings[J]. Energy,2020,191:No. 116552.
[38] 魏峥, 王碧玲. 基于机器学习的冷水机组能耗模型辨识方法研究[J]. 建筑科学,2018,34(6):115-122(WEI Z,WANG B L. Characteristic analysis and case study of energy saving uncertainty model for heating system retrofit projects[J]. Architecture Science,2018,34(6):115-122).)
[39] ZHOU C,FANG Z,XU X,et al. Using long short-term memory networks to predict energy consumption of air-conditioning systems[J]. Sustainable Cities and Society,2020,55:No. 102000.
[40] FANGER P O. Assessment of man's thermal comfort in practice[J]. Occupational and Environmental Medicine,1973,30(4):313-324.
[41] 熊伟成, 夏光义, 黎强, 等. 某办公建筑热舒适及能耗的正交法优化[J]. 西南师范大学学报(自然科学版),2018,43(8):116-120. (XIONG W C,XIA G Y,LI Q,et al. Optimization of thermal comfort and energy consumption in an office building in orthogonal method[J]. Journal of Southwest China Normal University(Natural Science Edition),2018,43(8):116-120.)
[42] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006, 313(5786):504-507.
[43] HAYKIN S. Neural Networks:A Comprehensive Foundation[M]. 3rd ed. Upper Saddle River:Prentice-Hall,1998.
[44] SMOLA A J, SCHÖLKOPF B. A tutorial on support vector regression[J]. Statistics and Computing,2004,14(3):199-222.
[45] KIANIFARD F. Book review of Applied linear regression models:2nd by NETER J,WASSERMAN W,KUTNER M H K[J]. Technometrics,1990,32(3):352-353.
[46] HOERL A E, KENNARD R W. Ridge regression:biased estimation for nonorthogonal problems[J]. Technometrics,1970, 12(1):55-67.
[47] ABRAMSON N, BRAVERMAN D, SEBESTYEN G. Pattern recognition and machine learning[J]. IEEE Transactions on Information Theory,1963,9(4):257-261.
[48] YEH C H. Classification and regression trees[J]. Chemometrics and Intelligent Laboratory Systems,1991,12(1):95-96.
[49] 许德祥. 统计模型中均方误差的区间估计[J]. 经济数学,1999(1):52-54.(XU D X. Interval estimation of mean square error in statistical model[J]. Economic Mathematics,1999(1):52-54.)
[50] AGRESTI A. Applying R2-type measures to ordered categorical data[J]. Technometrics,1986,28(2):133-138.
[51] GARCÍA S,FERNÁNDEZ A,LUENGO J,et al. Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining:experimental analysis of power[J]. Information Sciences,2010, 180(10):2044-2064.

Comprehensive prediction of thermal comfort and energy consumption for high-speed railway stations

面向高铁站的热舒适度和能耗综合预测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	GUO Mian, ZHANG Jinyou. Computation offloading policy for machine learning in mobile edge computing environments [J]. Journal of Computer Applications, 2021, 41(9): 2639-2645.
[2]	MAO Mingze, CAO Ruihao, YAN Chungang. Semi-supervised classification algorithm based on weight diversity [J]. Journal of Computer Applications, 2021, 41(9): 2473-2480.
[3]	DAI Yurou, YANG Qing, ZHANG Fengli, ZHOU Fan. Trajectory prediction model of social network users based on self-supervised learning [J]. Journal of Computer Applications, 2021, 41(9): 2545-2551.
[4]	CAI Biao, LI Ruicen, WU Yuanyuan. Impact and enhancement of similarity features on link prediction [J]. Journal of Computer Applications, 2021, 41(9): 2569-2577.
[5]	AN Xin, YANG Haijiao, LI Jianhua, REN Fuji. Dynamic mapping method for heterogeneous multi-core system under thermal safety constraint [J]. Journal of Computer Applications, 2021, 41(9): 2631-2638.
[6]	YAN Haisheng, MA Xinqiang. Feature construction algorithm for multi-target regression via radial basis function [J]. Journal of Computer Applications, 2021, 41(8): 2219-2224.
[7]	DING Yin, SANG Nan, LI Xiaoyu, WU Feizhou. Prediction method of capacity data in telecom industry based on recurrent neural network [J]. Journal of Computer Applications, 2021, 41(8): 2373-2378.
[8]	QIN Binbin, PENG Liangkang, LU Xiangming, QIAN Jiangbo. Research progress on driver distracted driving detection [J]. Journal of Computer Applications, 2021, 41(8): 2330-2337.
[9]	MENG Fan, CHEN Guang, WANG Yong, GAO Yang, GAO Dequn, JIA Wenlong. Multi-granularity temporal structure representation based outlier detection method for prediction of oil reservoir [J]. Journal of Computer Applications, 2021, 41(8): 2453-2459.
[10]	XIAO Zhenyuan, WANG Yihan, LUO Jianqiao, XIONG Ying, LI Bailin. RefineDet based on subsection weighted loss function [J]. Journal of Computer Applications, 2021, 41(7): 1928-1932.
[11]	WU Wei, LI Zeping, YANG Huawei, LIN Chuan, WANG Zhongde. Deep attention video popularity prediction model fusing content features and temporal information [J]. Journal of Computer Applications, 2021, 41(7): 1878-1884.
[12]	ZHANG Yuanjun, ZHANG Xihuang. Dynamic network representation learning model based on graph convolutional network and long short-term memory network [J]. Journal of Computer Applications, 2021, 41(7): 1857-1864.
[13]	LI Yangying, CHEN Zhijun, ZHANG Zihao, YOU Lan. Raw sugar demand forecasting model for sugar manufacturing enterprise based on modified Elman neural network [J]. Journal of Computer Applications, 2021, 41(7): 2113-2120.
[14]	LI Xujuan, PI Jianyong, HUANG Feixiang, JIA Haipeng. Self-generated deep neural network based 4D trajectory prediction [J]. Journal of Computer Applications, 2021, 41(5): 1492-1499.
[15]	NI Shuiping, LI Huifang. Battery state-of-charge prediction method based on one-dimensional convolutional neural network combined with long short-term memory network [J]. Journal of Computer Applications, 2021, 41(5): 1514-1521.