西安市供暖期日燃气负荷预测方法

doi:10.11755/j.issn.1006-7639(2021)-05-0857

摘要/Abstract

摘要：

利用西安市2009年11月15日至2019年3月14日供暖期燃气负荷及气象观测逐日资料,分析西安市供暖期、节假日、双休日燃气负荷的变化规律,采用相关分析方法,筛选相关性显著的因子作为燃气负荷影响因子。在此基础上,采用多元线性回归分析方法,构建供暖期日燃气负荷预测模型,并对模型进行检验评估。结果表明:近10 a西安市供暖期燃气用量逐年增加,且日燃气负荷呈单峰型波动变化,峰值出现在1月。供暖期燃气负荷具有双休日、节假日效应,其燃气负荷明显低于工作日,且节假日越长影响越明显。供暖期燃气负荷与前一日燃气负荷呈显著正相关,而与最高气温、最低气温、平均气温及人体舒适度等气象因子呈显著负相关,分离基础燃气负荷后的供暖燃气负荷与上述气象因子的相关性明显提高。基于上述5个影响因子构建的供暖期日燃气负荷动态预测模型,经检验,平均相对误差为3.4%,且用气高峰期模型预测更稳定,相对误差为2.77%,能够满足天然气公司供暖期燃气调度需求。

关键词: 燃气负荷, 供暖期, 影响因子, 预测方法

Abstract:

Based on daily gas load and meteorological observation data during heating period in Xi’an of Shaanxi Province from 15 November 2009 to 14 March 2019, the variation characteristics of gas load in heating period, holidays and weekends were analyzed. The significant influence factors on gas load were selected by using correlation analysis. And on this basis the daily forecast model of gas load in heating period was established by using multiple linear regression method, then the forecast model was tested. The results show that the natural gas consumption during heating period gradually increased in Xi’an in past 10 years, the daily gas load presented a single-peak pattern change, and the peak appeared in January. The weekend and holidays effects of gas load were obvious during heating period, the gas consumption on weekend and holiday was less than that on working days, and the longer holiday was, the less gas load was. The gas load was significantly and positively correlated with gas load on previous day, while that was significantly and negatively correlated with meteorological factors of the maximum and minimum temperature, mean temperature and human body comfortable degree, and the correlation between heating gas load separated from actual gas load and meteorological factors obviously improved. Based on the above five influence factors, the dynamic forecast model of daily heating gas load was established by using multiple linear regression method. Upon inspection, the average relative error of the model was 3.4%, and the model was more stable in rush hours of using gas, the average relative error was 2.77%, which could meet gas dispatch needs of natural gas companies.

Key words: gas load, in heating period, influence factors, prediction method

中图分类号:

P49
TU996

高红燕,杨艳超,张曦,王丹,崔瑜,解峰. 西安市供暖期日燃气负荷预测方法[J]. 干旱气象, 2021, 39(5): 857-863.

GAO Hongyan,YANG Yanchao,ZHANG Xi,WANG Dan,CUI Yu,XIE Feng. Forecast Method of Daily Gas Load During Heating Period in Xi’an of Shaanxi Province[J]. Journal of Arid Meteorology, 2021, 39(5): 857-863.

图/表 6

图1 西安市平均燃气负荷逐日变化(a)和供暖期、非供暖期燃气负荷年际变化(b)

Fig.1 The daily variation of average gas load (a) and inter-annual changes of gas load in heating period and non-heating period (b) in Xi’an of Shaanxi Province

图2 2009—2018年西安市供暖期燃气负荷和平均气温逐年(a)及多年平均(b)日变化

Fig.2 The daily changes of gas load and average temperature in heating period in each year (a) and their multi-year mean daily changes (b) from 2009 to 2018 in Xi’an of Shaanxi Province

图3 西安市元旦(a)、春节假期(b)及其前后和供暖期一周(c)燃气负荷逐日变化

Fig.3 The daily variation of gas load in New Year (a) and Spring Festival holidays (b) and their around and a week in heating period (c) in Xi’an of Shaanxi Province

表1 西安市供暖期燃气负荷、供暖燃气负荷与敏感因子的相关系数

Tab.1 Correlation coefficients between gas load, heating gas load and sensitivity factors in heating period in Xi’an of Shaanxi Province

类型	前一日燃气负荷	最高气温	最低气温	平均气温	人体舒适度指数
供暖期燃气负荷	0.987	-0.387	-0.336	-0.388	-0.127
供暖燃气负荷	0.985	-0.467	-0.436	-0.485	-0.414

图4 西安市供暖燃气负荷与影响因子散点图 (a)前一日燃气负荷,(b)最高气温,(c)最低气温,(d)平均气温,(e)人体舒适度指数

Fig.4 Scatter diagrams between heating gas load and impact factors in Xi’an of Shaanxi Province (a) gas load on previous day, (b) the maximum temperature, (c) the minimum temperature, (d) average temperature, (e) comfortable degree of human body

图5 西安市2018年供暖期燃气负荷预测值与实际消耗量对比(a)及相对误差(b)

Fig.5 The comparison of predicted value of gas load in heating period with actual consumption (a) and relative error (b) in 2018 in Xi’an of Shaanxi Province

参考文献 25

[1]	王耀庭, 孟春雷, 苗世光, 等. 基于人口和能耗数据估算北京人为热排放[J]. 干旱气象, 2020, 38(1):89-99.
[2]	祁栋林, 李晓东, 胡爱军, 等. 1991—2013年西北地区省会城市PM₁₀浓度变化特征[J]. 干旱气象, 2016, 34(4):656-662.
[3]	丁锋, 刘运良, 刘建波, 等. 气象条件对城市燃气日负荷的影响[J]. 煤气与热力, 2007, 27(2):17-20.
[4]	张中秀, 周伟国, 姚健, 等. 城市燃气负荷的气温响应特性研究[J]. 煤气与热力, 2008, 28(10):11-13.
[5]	罗志鹏, 牟军, 吴渊. 西安市冬季天然气用气负荷与气温关系分析[J]. 辽宁化工, 2012, 41(3):276-278.
[6]	张鸿彦. 燃气日用气负荷预测模型的研究[J]. 河南工程学院学报(自然科学版), 2013, 25(2):28-33.
[7]	PELIKAN E, SIMUNEK M. Risk management of the natural gas consumption using genetic algorithms[J]. Neural Network World, 2005, 15(5):425-436.
[8]	VONDRÁČEK J, PELIKÁN E, KONÁR O, et al. A statistical model for the estimation of natural gas consumption[J]. Appied Energy, 2008, 85(5):362-370.
[9]	SOLDO B. Forecasting natural gas consumption[J]. Applied Energy, 2012, 92:26-37. DOI URL
[10]	YU F, XU X Z. A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network[J]. Appied Energy, 2014, 134:102-113.
[11]	ERVURAL B C, BEYCA O F, ZAIM S. Model estimation of ARMA using genetic algorithms: a case study of forecasting natural gas consumption[J]. Procedia-Social and Behavioral Sciences, 2016, 235:537-545. DOI URL
[12]	WU H C, LU C N. A data mining approach for spatial modeling in small area load forecast[J]. IEEE Transactions on Power Systems, 2002, 17(2):516-521. DOI URL
[13]	何洋. 城市燃气负荷智能预测系统的开发及应用[D]. 上海: 上海师范大学, 2015.
[14]	王树刚, 王继红, 端木琳, 等. 城市燃气负荷的短期预测[J]. 天然气工业, 2010, 30(5):104-107.
[15]	康琪, 林军. 分解组合模型在短期燃气预测中的应用[J]. 微型机与应用, 2013, 32(16):92-96.
[16]	陈碧璇, 孙兰东, 许瀚卿. 上海市气象条件对燃气能源消耗影响研究[J]. 上海节能, 2016(7):366-370.
[17]	顾婷婷, 骆月珍, 张青, 等. 基于气象因子杭州市燃气负荷预测研究[J]. 气象与环境学报, 2017, 33(3):107-112.
[18]	韩玥, 邓卫疆, 高强, 等. 基于气象因子的西青开发区燃气负荷模型研究[J]. 天津科技, 2018, 45(5):73-79.
[19]	焦文玲, 邹涛, 巩晓峰, 等. 燃气日负荷影响因素的相关分析和偏相关分析[J]. 煤气与热力, 2010, 30(5):1-5.
[20]	周伟国, 张中秀, 姚健. 城市燃气负荷的混沌特性与预测[J]. 同济大学学报(自然科学版), 2010, 38(10):1511-1515.
[21]	刘东京, 周伟国, 张中秀. 综合气象指标对燃气负荷的影响[J]. 上海煤气, 2018(1):34-37.
[22]	曾艳, 黎杰清, 姚伊迪, 等. 基于小波神经网络的燃气系统短期负荷预测[J]. 贵州师范大学学报(自然科学版), 2011, 29(4):69-72.
[23]	李持佳, 焦文玲, 赵林波. 燃气短期负荷预测的小波分析综合模型[J]. 天然气工业, 2007, 27(8):103-108.
[24]	陈川, 陈冬林, 何李凯. 基于BPNN-EMD-LSTM组合模型的城市短期燃气负荷预测[J]. 安全与环境工程, 2019, 26(1):149-154.
[25]	吴兑, 邓雪娇. 环境气象学与特种气象预报[M]. 北京: 气象出版社, 2007:170-171.