基于NSGA-Ⅱ-VAR的燃煤电厂负荷预测

韩伟伦; 茅大钧; 陈思勤

doi:10.19944/j.eptep.1674-8069.2024.04.005

基于NSGA-Ⅱ-VAR的燃煤电厂负荷预测

1. 上海电力大学自动化工程学院;
2. 华能国际电力股份有限公司上海石洞口第二电厂

基金项目:

国家自然科学基金项目(52005131)

中国华能集团有限公司2022年度科技项目(HNKJ22-HF22)

详细信息

作者简介:
韩伟伦(1994—),男,硕士研究生,主要从事智慧电厂等方面的研究,383507304@qq.com;陈思勤(1970—),女,教授级高级工程师,主要从事电厂生产过程自动化和智能化等方面的研究,chensiqin36881@hotmail.com

通讯作者:
茅大钧(1966—),男,教授,主要从事智慧燃料、故障预警等方面的研究,maodajun@sina.cn

中图分类号: TP18;TM621
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2023-12-03

Load forecasting for coal-fired power plants based on NSGA-Ⅱ-VAR

1. Shanghai Electric Power University;
2. Huaneng International Power Co., Ltd.,Shanghai Shidongkou Second Power Plant

摘要

摘要: 燃煤电厂负荷预测的意义在于可以预先了解未来一段时间内的电力需求情况，从而合理安排发电设备的运行和停机维修时间，避免能源浪费、提高发电效率；此外，在燃煤电厂参与深度调峰、配煤掺烧的大背景下，为了确保混煤发热量适应负荷需求，提高燃烧效率，需要提前预知未来一段时间的负荷。本文提出一种基于快速非支配排序遗传算法（non-dominated sorting genetic algorithmⅡ，NSGA-Ⅱ）优化向量自回归模型（vector autoregression,VAR）的燃煤电厂负荷预测方法。该方法将历史过热蒸汽时间序列、历史再热蒸汽时间序列和历史发电量序列一起作为VAR模型的输入变量，预测未来8 h的发电负荷，同时使用NSGA-Ⅱ算法优化VAR模型的阶数和截距，从而提高了预测模型的精度。测试阶段，选取上海某机组2022年10月25日—2022年10月30日为数据样本区间，建立初始化预测模型；在2022年10月31日8:00—2022年11月1日16:00样本区间上测试模型效果，并使用NSGA-Ⅱ算法根据测试结果优化VAR模型；在2022年11月2日8:00—2022年11月3日16:00的样本区间上进一步测试优化后的模型预测精度。测试结果表明：预测均方根误差为15.341 MW，平均绝对误差为7.839 MW，和其他时序预测模型对比精度有所提高。该模型可实际运用于同类煤电机组的负荷预测，从而为后续运行决策提供参考。
- 燃煤电厂 /
- 燃烧效率 /
- 负荷预测 /
- NSGA-Ⅱ算法 /
- VAR模型
Abstract: The significance of load forecasting for coal-fired power plants lies in the fact that it is possible to know in advance the demand for electricity in the future period of time, so as to rationally arrange the operation and downtime of power generation equipment for maintenance, avoid energy waste, and improve the efficiency of power generation;moreover, in the context of coal-fired power plants participating in in-depth peaking and coal blending, it is necessary to predict in advance the future period of time in order to ensure that the coal blending heat generation capacity is adapted to the demand for loads and to improve the efficiency of combustion. In this paper, a load forecasting method for coal-fired power plants based on the fast Non-dominated Sorting Genetic Algorithm Ⅱ（NSGA-Ⅱ） optimized Vector Autoregression（VAR） model is proposed. The method takes the historical superheated steam time series, the historical reheated steam time series, and the historical power generation series together as the input VARiables of the VAR model to predict the power generation load in the next 8 hours, and at the same time uses the NSGA-Ⅱ algorithm to optimize the order and intercept of the VAR model, thus improving the accuracy of the prediction model.In the testing stage, the data sample interval from October 25, 2022 to October 30, 2022 for a unit in Shanghai is selected to establish the initialized prediction model; the model effect is tested on the sample interval from 8: 00 on October 31, 2022 to 16:00 on November 1, 2022, and the VAR model is optimized according to the test results using the NSGA-Ⅱ algorithm; and the VAR model is optimized on the sample interval from 8:00 on October 2, 2022 to 16:00on November 2, 2022 using the NSGA-Ⅱ algorithm; the VAR model is optimized according to the test results in the test stage. The prediction accuracy of the optimized model is further tested on the sample interval from 8:00 on November 2, 2022 to 16: 00 on November 3, 2022, using the NSGA-Ⅱ algorithm to optimize the VAR model based on the test results. The results show that the root-mean-square error of the prediction is 15.341 MW, and the average absolute error is 7.839 MW, which is improved compared with other time series prediction models. Therefore, the model can be practically applied to the load forecasting of similar coal power units, thus providing a reference for subsequent operation decisions.
- coal-fired power plant /
- combustion efficiency /
- load forecasting /
- NSGA-Ⅱ algorithm /
- VAR model

HTML全文

参考文献(36)

[1]	杨海瑞,杨冬,刘欢鹏.“燃煤电厂深调峰技术”专题客座主编致读者[J].洁净煤技术,2023,29(6):3-6. YANG Hairui, YANG Dong, LIU Huanpeng.Guest editor-in-chief of"deep peaking technology for coal-fired power plants"to readers[J]. Clean Coal Technology, 2023,29(6):3-6.
[2]	杨冬锋,刘厚伟,孙勇,等.考虑绿证交易机制与碳捕集电厂深度调峰补偿的多主体联合调峰优化调度[J].电网技术,2024,48(1):100-112. YANG Dongfeng, LIU Houwei, SUN Yong, et al. Optimized dispatch of multi-initiative joint peaking considering green certificate trading mechanism and deep peaking compensation for carbon capture power plants[J]. Power Grid Technology, 2024,48(1):100-112.
[3]	胡涛,茅大钧,程鹏远,等.基于煤质预测的多目标优化配煤方法研究[J].热能动力工程,2021,36(12):151-156. HU Tao, MAO Dajun, CHENG Pengyuan, et al. Research on multiobjective optimization of coal blending method based on coal quality prediction[J].Thermal Power Engineering,2021,36(12):151-156.
[4]	胡涛,茅大钧,程鹏远,等.基于火电厂发电量预测的多目标配煤方法[J].煤炭转化,2021,44(4):73-80. HU Tao, MAO Dajun, CHENG Pengyuan, et al. Multi-objective coal allocation method based on power generation forecast of thermal power plant[J].Coal Conversion,2021,44(4):73-80.
[5]	丁伟,任少君,司风琪,等.一种基于HMF的火电机组短期负荷预测方法[J].热能动力工程,2020,35(1):191-197. DING Wei, REN Shaojun, SI Fengqi, et al. A short-term load forecasting method for thermal power units based on HMF[J].Thermal Power Engineering,2020,35(1):191-197.
[6]	王力光,封亚钊,王涛,等.基于IHMF算法的火电机组短期负荷预测研究[J].能源研究与利用,2021(1):47-50. WANG Liguang, FENG Yazhao, WANG Taoet al. Study on shortterm load forecasting of thermal power units based on IHMF algorithm[J].Energy Research and Utilization,2021(1):47-50.
[7]	马良玉,成蕾.考虑回热循环的超超临界机组负荷预测神经网络模型[J].热力发电,2016,45(4):19-27+34. MA Liangyu,CHENG Lei.Neural network model for load prediction of ultra-supercritical unit considering heat return cycle[J].Thermal Power Generation,2016,45(4):19-27+34.
[8]	程鹏远,茅大钧,胡涛.基于移动平均及LSTM组合模型的火电厂日发电量预测研究[J].青海电力,2021,40(4):7-10+26. CHENG Pengyuan, MAO Dajun, HU Tao. Research on daily powergeneration prediction of thermal power plant based on moving average and LSTM combination model[J].Qinghai Electric Power,2021,40(4):7-10+26.
[9]	张然然,刘鑫屏.火电机组超短期负荷预测[J].热力发电,2018,47(7):52-57. ZHANG Ranran, LIU Xinping. Ultra-short-term load forecasting for thermal power units[J].Thermal Power Generation,2018,47(7):52-57.
[10]	李元,刘雨田,冯立伟.基于斯皮尔曼相关分析的非线性动态过程特征提取与故障检测[J].山东科技大学学报(自然科学版),2023,42(2):98-107. LI Yuan, LIU Yutian, FENG Liwei. Nonlinear dynamic process feature extraction and fault detectionbased on spearman correlation analysis[J].Journal of Shandong University of Science and Technology(Natural Science Edition),2023,42(2):98-107.
[11]	赵慧超,刘耀东,刘铭礼,等.基于Spearman相关性和燃烧三维数值计算的汽油机碳氢排放分析[J/OL].吉林大学学报(工学版), 1-10.[2024-04-22]. http://doi. org. shiep. vpn358. com/10.13229/j.cnki.jdxbgxb.20230590.ZHAO Huichao, LIU Yaodong, LIU Mingli, et al. Hydrocarbon emission analysis of gasoline engine based on Spearman's correlation and combustion three-dimensional numerical calculation[J/OL].Journal of Jilin University(Engineering Edition),1-10.[2024-04-22]. http://doi.org.shiep.vpn358.com/10.13229/j.cnki.jdxbgxb.20230590.
[12]	王仲平,何黎黎,丁更乾.基于EMD-LSTM-ARMA模型短期发电量组合预测[J].现代电子技术,2023,46(3):151-155. WANG Zhongping, HE Lili, DING Gengqian. Short-term power generation combination prediction based on EMD-LSTM-ARMA model[J].Modern Electronic Technology,2023,46(3):151-155.
[13]	滕陈源,丁逸超,张有兵,等.基于VMD-Informer-BiLSTM模型的超短期光伏功率预测[J].高电压技术,2023,49(7):2961-2971. TENG Chenyuan, DING Yichao, ZHANG Youbing, et al. Ultrashort-term photovoltaic power prediction based on VMDInformer-BiLSTMmodel[J].High Voltage Technology,2023,49(7):2961-2971.
[14]	HESAMIAN G, TORKIAN F, JOHANNSSEN A, et al. An exponential autoregressive time series model for complex data[J].Mathematics,2023,11(19):3329-3337.
[15]	NIHARIKA B, SINGH MD, ARUN K, et al. Humbert generalized fractional differenced ARMA processes[J]. Communications in Nonlinear Science and Numerical Simulation,2023(9):125.
[16]	JALAL M U. Investigating the impulse responses of renewable energyin the context of China:A bayesian VAR approach[J].Renewable Energy,2023,219(2):9981-9989.
[17]	刘洪,王丹阳,高跃伟.稳态随机先验下MF-VAR预测模型及其应用[J].统计与决策,2023,39(5):22-26. LIU Hong, WANG Danyang, GAOYuewei. MF-VAR forecasting model and its application under steady state stochastic prior[J].Statistics and Decision Making,2023,39(5):22-26.
[18]	谢林林,姚雪松,王志勇.金融发展、科技创新与产业升级—基于VAR和中介效应模型的实证研究[J].技术经济与管理研究,2023(9):42-47. XIE Linlin, YAO Xuesong, WANG Zhiyong.Financial development,scientific and technological innovation and industrial upgrading:anempirical study based on VAR and mediation effect model[J].Research on Technological Economy and Management,2023(9):42-47.
[19]	张筱峰,符环宇.美联储加息对中国多层次债券市场的溢出效应—基于TVP-SV-VAR模型的实证研究[J].经济问题,2023(12):34-41. ZHANG Xiaofeng, FU Huanyu.Spillover effects of Fed's interest rate hike on China's multilevel bond market--an empirical study based on TVP-SV-VAR model[J].Economic Issues,2023(12):34-41.
[20]	崔惠颖,赵海文.经济政策不确定性、企业家信心与出口贸易——基于TVP-SV-VAR模型的实证分析[J].技术经济与管理研究,2023(10):94-99. CUI Huiying, ZHAO Haiwen. Economic policy uncertainty,entrepreneurial confidence and export trade-an empirical analysis basedon TVP-SV-VAR model[J].Research on Technical Economics and Management,2023(10):94-99.
[21]	MALAGHBP R. Adaptive information-based methods for determining the co-integration rank inheteroskedastic VAR models[J].Econometric Reviews,2023,42(9):725-757.
[22]	YONGMIAO S T Z.Fast estimation of a large TVP-VAR model with score-driven volatilities[J]. Journal of Economic Dynamics and Control,2023,157(6):11157-11166.
[23]	陈腾,阮舟,郑志敏.基于VAR和集成神经网络分位数回归的短期负荷概率预测[J].电力需求侧管理,2023,25(6):63-68. CHEN Teng, RUAN Zhou, ZHENG Zhimin. Short-term load probability forecasting based on VAR and integrated neural network quantile regression[J]. Electricity Demand Side Management, 2023,25(6):63-68.
[24]	寇露彦,廖竞,李学俊,等.基于VAR模型的加拿大气候变化预测[J].计算机与现代化,2022(10):13-18. KOU Luyan, LIAO Jing, LI Xuejun, et al. Climate change prediction in Canada based on VAR model[J]. Computer and Modernization,2022(10):13-18.
[25]	范涛涛,寇艳廷,刘晨,等.时间序列分析中数据的平稳性判定研究[J].现代电子技术,2013,36(4):66-68,72. FAN Taotao, KOU Yanting, LIU Chen, et al. Hongchan.Research on the determination of smoothness of data in time series analysis[J]. Modern Electronic Technology,2013,36(4):66-68,72.
[26]	管河山,邹清明,罗智超.时间序列平稳性分类识别研究[J].统计与信息论坛,2016,31(4):3-8. GUAN Heshan, ZOU Qingming, LUO Zhichao. Research on classification identification of time series smoothness[J]. Statistics and Information Forum,2016,31(4):3-8.
[27]	王倩,郝文倩,廖泽芳.官方新闻对人民币汇率变动的影响——基于TVP-VAR模型的研究[J].管理现代化,2024(2):38-51. WANG Qian, HAO Wenqian, LIAo Zefang. The impact of official news on RMB exchange rate changes-a study based on TVPVAR model[J]. Management Modernization,2024(2):38-51.
[28]	İSMAIL C,HAKAN K.Forecasting the dynamics of the Istanbul real estate market with the Bayesian time-varying VAR model regarding housing affordability[J].Habitat International,2024(9):13035-13043.
[29]	CAO Huimin, WANG Ping, ZHANG Surong, et al.Research on the relationship between environmental and economic coupling systems in bohai bay area based on a vector autoregression(VAR)model[J].Journal of Ocean University of China,2024,23(2):557-566.
[30]	ZHANG Q, WEI R. Carbon reduction attention and financial market stress:a network spillover analysis based on quantile VAR modeling[J]. Journal of environmental management, 2024(8):120640-120652.
[31]	李超文,尹瑞雪.基于GA-BP与NSGA-Ⅱ的数控铣削参数优化研究[J].工具技术,2024,58(3):86-92. LI Chaowen, YIN Ruixue. Research on optimization of CNC milling parameters based on GA-BP and NSGA-Ⅱ[J]. Tool Technology,2024,58(3):86-92.
[32]	叶恒昌,龚红英,张志强,等.基于响应面法和NSGA-Ⅱ的接线盒仿真优化[J].锻压技术,2023,48(4):72-76. YE Hengchang, GONG Hongying, ZHANG Zhiqiang, et al.Simulation optimization of junction box based on response surface method and NSGA-Ⅱ[J]. Forging Technology,2023,48(4):72-76.
[33]	SHI S, XIONG H. Solving the multi-objective job shop scheduling problems with overtime consideration by an enhanced NSGA-Ⅱ[J].Computers Industrial Engineering,2024(3):19011-19023.
[34]	LI J, TAO L, CHEN Y, et al. Heat dissipation optimization of ventilated brake disc recirculation zone based on NSGA-II algorithm[J]. Proceedings of the Institution of Mechanical Engineers, Part D:Journal of Automobile Engineering,2024,238(5):1263-1276.
[35]	杨昊霖,王茹芸,罗利敏,等.基于改进NSGA-II算法的RV减速器参数多目标优化研究[J/OL].机电工程,2024:1-10.[2024-04-23]. http://h-p. kns. cnki. net. shiep. vpn358. com/kcms/detail/33.1088.TH.20231129.1426.009.html. YANG Haolin, WANG Ruyun, LUO Limin, et al. Research on multiobjective optimization of RV gearbox parameters based on improved NSGA-II algorithm[J/OL]. Electromechanical Engineering, 2024:1-10.[2024-04-23]. http://h-p. kns. cnki. net. shiep. vpn358. com/kcms/detail/33.1088.TH.20231129.1426.009.html.
[36]	李二超,刘辰淼.Pareto解集旋转的分类多策略预测动态多目标优化[J/OL].计算机工程与应用,2024:1-18.[2024-04-23].http://h-p. kns. cnki. net. shiep. vpn358. com/kcms/detail/11.2127. tp.20240318.0902.003.html.LI Erchao, LIU Chenmiao. Dynamic multi-objective optimization for categorical multi-strategy prediction with Pareto solution set rotation[J/OL]. Computer Engineering and Applications, 2024:1-18.[2024-04-23]. http://h-p.kns.cnki.net.shiep.vpn358.com/kcms/detail/11.2127.tp.20240318.0902.003.html.