XGBoost-based regulation and prediction method for the heating station's heating system

doi:10.3969/j.issn.2097-0706.2023.12.005

Abstract

Abstract:

Accurate prediction and control of heating stations provide solid data support for the heating systems' energy consumption reduction， users' thermal comfort improvement and pollutant emission alleviation. Making full use of a heating station's key data， such as historical operating states，the set openings of valves and the weather characteristics， a heating station control and prediction method based on Extreme Gradient Boost（XGBoost） is proposed to make accurate regulation on secondary heating supply and return water temperature. Preprocessing， feature construction and model training are conducted on the data above，then a heating station temperature response prediction model is generated. Combining the model and temperature delay time of the secondary network， the valve control strategy is thereafter made. The error between the 24 h predicted temperature and the measured temperature is kept within 0.47 ℃， which verifies the accuracy and reliability of the heating station temperature response prediction model. The proposed strategy can guide the temperature control of heating stations.

Key words: heating station, XGBoost, model training, valve control, prediction accuracy, intelligent heating

CLC Number:

TK11

YONG Hezhong, ZHANG Ning, HUANG Wei, WEI Zheng, WU Yanling, ZHONG Wei. XGBoost-based regulation and prediction method for the heating station's heating system[J]. Integrated Intelligent Energy, 2023, 45(12): 36-42.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

References 20

[1]	钟崴, 陆烁玮, 刘荣. 智慧供热的理念、技术与价值[J]. 区域供热, 2018(2): 1-5.
[2]	王肖, 顾洁, 周浩. 基于全网平衡理论的热力站个性化质调节[J]. 煤气与热力, 2018, 38(6):8-13.
	WANG Xiao, GU Jie, ZHOU Hao. Individualized constant flow control of substations based on whole network equilibrium theory[J]. Gas & Heat, 2018, 38(6):8-13.
[3]	张军. 二级网调节在集中供热系统中技术与经济性分析[J]. 中外企业家, 2019(33): 184-185.
[4]	王睿鑫, 周志刚, 荆强, 等. 高校供热系统调控策略优化研究[J]. 煤气与热力, 2020, 40(11):1-8,43-44.
	WANG Ruixin, ZHOU Zhigang, XING Qiang, et al. Research on optimizing control strategy of heating system in colleges and universities[J]. Gas & Heat, 2020, 40(11):1-8,43-44.
[5]	刘剑, 付国栋, 付强, 等. 以用户室温作为调控目标的二次网智能平衡技术的应用[J]. 区域供热, 2020(4):129-133,145.
[6]	邵博, 孙春华, 齐承英. 供暖状态下建筑热特性仿真分析[J]. 暖通空调, 2017, 47(1): 124-128.
	SHAO Bo, SUN Chunhua, QI Chengying. Building thermal characteristic simulation under heating condition[J]. Heating Ventilating & Air Conditioning, 2017, 47(1): 124-128.
[7]	ZHONG W, HUANG W, LIN X J, et al. Research on data-driven identification and prediction of heat response time of urban centralized heating system[J]. Energy, 2020, 212: 118742. doi: 10.1016/j.energy.2020.118742
[8]	朱铁军, 李忠波. 公共建筑分时间歇调控模式研究与应用[J]. 区域供热, 2016(6): 80-85.
[9]	李仲博, 贾萌, 康焱, 等. 基于MPC方法的供热系统一次侧流量实时预测[J]. 系统仿真学报, 2021, 33(1):180-188. doi: 10.16182/j.issn1004731x.joss.19-0148
	LI Zhongbo, JIA Meng, KANG Yan, et al. Real-time prediction of primary flow by MPC method in heating system[J]. Journal of System Simulation, 2021, 33(1):180-188. doi: 10.16182/j.issn1004731x.joss.19-0148
[10]	XUE P N, JIANG Y, ZHOU Z G, et al. Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms[J]. Energy, 2019, 188: 116085. doi: 10.1016/j.energy.2019.116085
[11]	CHEN Y T, ZHANG D X. Theory-guided deep-learning for electrical load forecasting(TgDLF) via ensemble long short-term memory[J]. Advances in Applied Energy, 2021, 1: 100004. doi: 10.1016/j.adapen.2020.100004
[12]	薛普宁, 周志刚, 蒋毅, 等. 基于机器学习的供热系统热负荷多步递归预测[J]. 煤气与热力, 2019, 39(7):20-27.
	XUE Puning, ZHOU Zhigang, JIANG Yi, et al. Multi-step ahead recursive prediction of heat load of heating system based on machine learning[J]. Gas & Heat, 2019, 39(7):20-27.
[13]	赵秉文, 李婉, 金宇. 基于PSO-LSSVM的供热负荷预测研究[J]. 建筑节能, 2021, 49(6):46-49,78.
	ZHAO Bingwen, LI Wan, JIN Yu. Heating load prediction based on PSO-LSSVM[J]. Building Energy Efficiency, 2021, 49(6):46-49,78.
[14]	秦浩宇. 建筑计量供热系统动态调控特性与节能研究[D]. 北京: 北京建筑大学, 2017.
	QIN Haoyu. Study on building dynamic adjustment performance and energy-saving of heat metering system[D]. Beijing: Beijing University of Civil Engineering and Architecture, 2017.
[15]	姜永增, 刘涛, 潘军刚. 基于实际热需求的单一建筑类型区域供热系统节能调控方法研究[J]. 建筑节能, 2020, 48(12):99-104.
	JIANG Yongzeng, LIU Tao, PAN Jungang. Energy-saving regulation method of district heating system of single building type based on actual heat demand[J]. Building Energy Efficiency, 2020, 48(12):99-104.
[16]	李婉, 赵秉文, 陈军松, 等. 基于负荷预测的热网运行调控策略[J]. 浙江建筑, 2020, 37(6):57-60,64.
	LI Wan, ZHAO Bingwen, CHEN Songjun, et al. Operation control strategy of heat network based on load prediction[J]. Zhejiang Construction, 2020, 37(6):57-60,64.
[17]	王义, 杨志伟, 吴坡, 等. 计及高比例分布式光伏能源接入的配电网状态估计[J]. 综合智慧能源, 2022, 44(10):12-18. doi: 10.3969/j.issn.2097-0706.2022.10.002
	WANG Yi, YANG Zhiwei, WU Po, et al. State estimation for the distribution network with high-proportion distributed photovoltaic energy[J]. Integrated Intelligent Energy, 2022, 44(10): 12-18. doi: 10.3969/j.issn.2097-0706.2022.10.002
[18]	梁曦文, 王映品, 李林, 等. 有源电力滤波器直流电压简单模糊比例控制[J]. 综合智慧能源, 2022, 44(4):28-35. doi: 10.3969/j.issn.2097-0706.2022.04.004
	LIANG Xiwen, WANG Yingpin, LI Lin, et al. Simple fuzzy proportional control on DC-link voltage of active power filters[J]. Integrated Intelligent Energy, 2022, 44(4):28-35. doi: 10.3969/j.issn.2097-0706.2022.04.004
[19]	李珠林, 李慧, 刘思嘉, 等. 基于MPCC-PIγDμ控制的直驱永磁风力发电系统[J]. 电力系统及其自动化学报, 2023, 35(5):1-10.
	LI Zhulin, LI Hui, LIU Sijia, et al. Direct-driven permanent magnet wind power generation system based on MPCC-PIγDμ control[J]. Proceedings of the CSU-EPSA, 2023, 35(5):1-10.
[20]	高明, 陈家豪, 王丽晓, 等. 考虑光伏不确定性因素的电力系统概率潮流三点估计法[J]. 综合智慧能源, 2022, 44(9):1-10. doi: 10.3969/j.issn.2097-0706.2022.09.001
	GAO Ming, CHEN Jiahao, WANG Lixiao, et al. A three-point probabilistic load flow estimation algorithm for the power system considering photovoltaic uncertainties[J]. Integrated Intelligent Energy, 2022, 44(9):1-10. doi: 10.3969/j.issn.2097-0706.2022.09.001

时间	一次供水温度/ ℃	一次供水压力/MPa	阀门开度/ %	二次回水温度/ ℃	天气温度/ ℃	阀门预设开度/ %	二次供水温度/ ℃
07:00	83.21	0.81	21	45.60	-2.0	21	21.00
08:00	84.13	0.83	21	45.23	-1.4	21	21.00
09:00	85.00	0.83	21	45.12	0.0	21	21.00
10:00	85.76	0.83	21	44.98	1.0	21	21.00
11:00	86.45	0.85	21	44.85	1.5	21	21.00
12:00	87.23	0.82	20	44.35	2.3	20	20.00
13:00	88.00	0.87	19	44.20	3.0	19	19.00
14:00	89.49	0.87	19	43.88	2.8	19	19.00
15:00	90.22	0.87	19	43.50	2.6	19	19.00
16:00	91.24	0.88	18	43.44	2.5	18	18.00
17:00	92.57	0.88	18	43.28	2.5	18	18.00
18:00	92.88	0.88	18	43.16	2.4	18	18.00
19:00	93.15	0.88	18	43.07	2.0	18	18.00