Study on difference analysis and sampling inference methods of room temperature spatial characteristics

doi:10.3969/j.issn.2097-0706.2022.09.007

Abstract

Abstract:

To pursue the "dual carbon" target, technical transformations in heating industry is overwhelming. In recent years, networked room temperature acquisition devices have been widely used in this industry. Since the collected data of thermal energy users are affected by equipment installation ratio, installation location, systematic error, random error, etc., the room temperature data needs to be analysed and processed before being used to evaluate the heating quality. Based on data cleaning and sampling statistics, difference analysis and sampling inference methods for classical room temperature spatial characteristics are proposed, which provides theoretical guidance for the application of room temperature data from massive heat users in heating quality assessment and heat supply optimization control.

Key words: IoT, room temperature data, data cleaning, big data analysis, sampling method, carbon neutrality, smart heating

CLC Number:

TK01

ZHANG Xu, ZHANG Haohao, GU Jihao. Study on difference analysis and sampling inference methods of room temperature spatial characteristics[J]. Integrated Intelligent Energy, 2022, 44(9): 51-58.

Figures/Tables 11

Table 1

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Table 2

Statistical results based on stratified systematic sampling method

项目		抽样比例
项目		3%	5%	7%	9%	10%	15%	20%
样本量n		57	95	131	170	188	284	382
样本均值μ/℃		21.009	21.569	21.452	21.367	21.522	21.643	21.374
样本标准差σ/℃		2.003	1.832	2.150	1.755	2.421	2.353	2.087
样本的平均误差 $σ x ¯$ /℃		0.269	0.188	0.188	0.135	0.177	0.140	0.107
总体均值的Z值		1.707	0.532	0.092	0.754	0.302	1.249	0.888
<18 ℃	比重区间	(0.149,0.377)	(0.076,0.219)	(0.091,0.214)	(0.104,0.214)	(0.145,0.260)	(0.113,0.197)	(0.156,0.236)
	总体成数Z值	2.120	0.931	0.937	0.861	0.626	1.281	0.569
	样本与总体比重差异	是	否	否	否	否	否	否
	样本比重	0.263	0.147	0.153	0.159	0.202	0.155	0.196
18~20 ℃	比重区间	(0.147,0.157)	(0.182,0.188)	(0.217,0.221)	(0.215,0.218)	(0.158,0.161)	(0.172,0.173)	(0.194,0.195)
	总体成数Z值	0.750	0.036	1.950	1.931	0.835	0.376	0.659
	样本与总体比重差异	否	否	是	否	否	否	否
	样本比重	0.140	0.179	0.214	0.212	0.154	0.169	0.190
20~22 ℃	比重区间	(0.554,0.554)	(0.62,0.62)	(0.605,0.605)	(0.585,0.585)	(0.585,0.586)	(0.611,0.611)	(0.561,0.561)
	总体成数Z值	0.597	0.545	0.290	0.171	0.088	0.776	1.080
	样本与总体比重差异	否	否	否	否	否	否	否
	样本比重	0.544	0.611	0.595	0.576	0.580	0.606	0.556
22~21 ℃	比重区间	(0.069,0.069)	(0.079,0.079)	(0.022,0.022)	(0.063,0.063)	(0.051,0.051)	(0.065,0.065)	(0.045,0.045)
	总体成数Z值	0.501	2.350	2.390	0.840	0.159	1.377	0.059
	样本与总体比重差异	否	是	是	否	否	否	否
	样本比重	0.053	0.063	0.015	0.053	0.043	0.056	0.040
≥24 ℃	比重区间	(0.000,0.000)	(0.000,0.000)	(0.023,0.023)	(0.000,0.000)	(0.022,0.022)	(0.015,0.015)	(0.019,0.019)
	总体成数Z值	1.932	2.080	0.763	1.600	0.730	0.105	0.592
	样本与总体比重差异	是	是	否	否	否	否	否
	样本比重	0.000	0.000	0.023	0.000	0.021	0.014	0.019

Table 2

Table 3

Comparison of the results of different sampling methods

项目		室温总体	整群抽样	分层随机抽样（20%）	分层系统抽样（20%）
总体均值μ/℃		21.457	21.346	21.379	21.447
标准差σ/℃		2.159	1.996	1.967	1.980
样本量n		1 887	378	378	382
平均误差 $σ x ¯$ /℃		—	0.103	0.107	0.098
<18 ℃	比重区间	—	(0.153,0.233)	(0.156,0.236)	(0.140,0.216)
<18 ℃	Z值	0.184	0.193	0.196	0.178
18~20 ℃	比重区间	—	(0.154,0.155)	(0.194,0.195)	(0.154,0.156)
18~20 ℃	Z值	0.178	0.152	0.189	0.152
20~22 ℃	比重区间	—	(0.618,0.618)	(0.561,0.561)	(0.637,0.637)
20~22 ℃	Z值	0.583	0.614	0.556	0.633
22~24 ℃	比重区间	—	(0.040,0.040)	(0.045,0.045)	(0.029,0.029)
22~24 ℃	Z值	0.040	0.034	0.040	0.024
≥24℃	比重区间	—	(0.008,0.008)	(0.019,0.019)	(0.013,0.013)
≥24℃	Z值	0.015	0.007	0.019	0.013

Table 3

References 18

[1]	王有为. 谈“碳”——碳达峰与碳中和愿景下的中国建筑节能工作思考[J]. 建筑节能, 2021, 49(1):1-9.
	WANG Youwei. China's building energy efficiency efforts to peaking carbon dioxide emissions and achieving carbon neutrality[J]. Journal of Building Energy Efficiency, 2021, 49(1):1-9.
[2]	李炜, 严川, 盛庆博, 等. 大数据背景下智能配电网运营管理方法研究[J]. 华电技术, 2021, 43(8): 33-40.
	LI Wei, YAN Chuan, SHENG Qingbo, et al. Study on smart distribution network operation and management methods in the context of big data[J]. Huadian Technology, 2021, 43(8): 33-40.
[3]	卞阳, 赵奇剑, 胡水军, 等. 基于云平台的智能配电网电能质量监测预警研究与应用[J]. 华电技术, 2021, 43(1): 31-37.
	BIAN Yang, ZHAO Qijian, HU Shuijun, et al. Research and application on power quality monitoring and warning of intelligent power distribution network based on cloud platform[J]. Huadian Technology, 2021, 43(1): 31-37.
[4]	刘巧玲, 杜志敏, 晋欣桥. VAV空调系统室内温度传感器位置的影响研究[J]. 建筑热能通风空调, 2013, 32(1):11-14.
	LIU Qiaoling, DU Zhimin, JIN Xinqiao. A Study on the effect of location of indoor temperature sensor's of VAV air conditioning system[J]. Building Energy & Environment, 2013, 32(1):11-14.
[5]	程雪. 智慧供暖建筑室内平均温度监测方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2021.
[6]	梁媛, 孙春华, 赵子安, 等. 供暖居住建筑代表温度确定方法研究[J]. 建筑节能, 2019, 47(2):11-15.
	LIANG Yuan, SUN Chunhua, ZHAO Zi'an, et al. Determining method of representative temperature of heating residential buildings[J]. Building Energy Efficiency, 2019, 47(2):11-15.
[7]	王淞, 董重成. 分户计量供暖系统室内温度波动规律研究[J]. 节能技术, 2005, 23(131):257-260,269.
	WANG Song, DONG Zhongcheng. Research on fluctuation laws of indoor temperature house-hold and heat metering system[J]. Energy Conservation Technology, 2005, 23(131):257-260,269.
[8]	陈军伟. 无线传感器网络中基于特征分析的缺失数据恢复方法研究[D]. 重庆: 重庆邮电大学, 2016.
[9]	张婷婷. 基于时空相关性的传感器感知数据缺失重建方法研究[D]. 西安: 长安大学, 2019.
[10]	翟勇, 李洪海, 苑丽伟, 等. 基于均值漂移聚类算法的数据清洗方法研究[C]// 第三届智能电网会议论文集. 2018:113-117.
[11]	郭佳昌, 兰芸, 薛普宁, 等. 供热管网运行数据异常校正方法研究[J]. 煤气与热力, 2020, 40(11):8-13,41-42.
	GUO Jiachang, LAN Yun, XUE Puning, et al. Study on correction method for abnormal operation data of heating network[J]. Gas & Heat, 2020, 40(11):8-13,41-42.
[12]	李现霞, 王欣, 葛云启. 室温采集装置及供热二级管网智能化改造[J]. 煤气与热力, 2021, 41(2):11-12,41-42.
	LI Xianxia, WANG Xin, GE Yunqi. Intelligent transformation of room temperature acquisition device and secondary heating network[J]. Gas & Heat, 2021, 41(2):11-12,41-42.
[13]	郝爽, 李国良, 冯建华, 等. 结构化数据清洗技术综述[J]. 清华大学学报(自然科学版), 2018, 58(12):1037-1050.
	HAO Shuang, LI Guoliang, FENG Jianhua, et al. Survey of structured data cleaning methods[J]. Journal of Tsinghua University(Science and Technology), 2018, 58(12):1037-1050.
[14]	冯宪凯. 基于聚类算法的数据清洗研究[D]. 镇江: 江苏科技大学, 2019.
[15]	同济大学数学系. 概率论与数理统计[M]. 北京: 人民邮电出版社, 2017.
[16]	任和, 郝斌, 齐金洲. 同一楼内住户位置差异对耗热量及热费的影响[J]. 建筑节能, 2008, 36(10):1-4.
	REN He, HAO Bin, QI Jinzhou. Influence of position diversity on the heat consumption and heat fees in the same floor[J]. Construction Conserves Energy, 2008, 36(10):1-4.
[17]	李强. 居住建筑用户位置对耗热量及热价影响研究[D]. 天津: 天津大学, 2014.
[18]	冯士雍, 倪加勋, 邹国华. 抽样调查理论与方法[M]. 2版. 北京: 中国统计出版社, 2012.

信息类别	项目	参数
热力站信息	机组数量	8
	系统形式	板换间供热,电调阀控制系统
	采暖方式	地暖
	入住率/%	70左右
住户信息	住户编码	具体到门牌号
	测点总数（户数）	4 500
	供热面积/m²	50~150
	住户位置	中间、边角、顶层
	缴费状态	供暖、停暖
楼栋信息	楼栋数量	94
楼栋信息	楼层类型	15层（多层）,33层（高层）
室内温度数据源	室内温度/℃	5~30
	采集间隔/min	20
	采集时间	2021-12-23—25
室外温度数据源	室外温度/℃	-5~13
	采集间隔/min	10
	采集时间	2021-12-23—25