三支残差修正的燃气负荷预测

doi:10.3778/j.issn.1002-8331.2105-0111

摘要/Abstract

摘要： 燃气负荷的准确预测对于燃气调度、规划燃气使用有着重要的意义。单一的预测模型在燃气负荷预测中不能取得很好的预测效果，故基于燃气负荷数据的特点设计了一种三支残差修正的燃气负荷组合预测模型。首先基于燃气负荷数据特点，采用鲁棒局部加权回归对负荷序列进行了分解，针对分解后的趋势项、周期项、余项设计了ARIMA（autoregressive integrated moving average）和LightGBM（light gradient boosting machine）的组合预测模型，然后结合三支决策理论设计了三支残差修正法对LightGBM的预测结果进行修正。实验结果表明该组合模型的表现良好，预测效果优于常见单一模型。

关键词: 燃气负荷预测, 三支决策, 时序预测, ARIMA, LightGBM, 鲁棒局部加权回归

Abstract: Accurate prediction of gas load is very important to dispatch and plan gas usage. A single forecasting model can not achieve good forecasting effects in gas load forecasting. Therefore, this paper designs a combined forecasting model with three-way residual correction according to the characteristics of gas load data. The model firstly decomposes load sequence with robust locally weighted regression, then the combination of ARIMA（autoregressive integrated moving average） and LightGBM（light gradient boosting machine） is designed for the decomposed trend item, periodic item and remaining item, and three-way residual correction is designed to correct the prediction of LightGBM based on three-way decision. The experiment shows that the proposed combined model performs well and the prediction is better than common single models.

Key words: gas load forecasting, three-way decision, time series, ARIMA, LightGBM, robust locally weighted regression

王兵, 吴思琪, 方宇. 三支残差修正的燃气负荷预测[J]. 计算机工程与应用, 2022, 58(22): 291-296.

WANG Bing, WU Siqi, FANG Yu. Gas Load Forecasting with Three-Way Residual Correction[J]. Computer Engineering and Applications, 2022, 58(22): 291-296.

参考文献

[1] AKPINAR M，YUMU?AK N.Daily basis mid-term demand forecast of city natural gas using univariate statistical techniques[J].Journal of the Faculty of Engineering and Architecture of Gazi University，2020，35（2）：725-741.
[2] FABBIANI E，MARZIALI A，NICOLAO G D.Short-term forecasting of Italian gas demand[J].Oil，Gas and Coal Technology，2021，26（2）：184-201.
[3] ANELKOVI A S，BAJATOVI D.Integration of weather forecast and artificial intelligence for a short-term city-scale natural gas consumption prediction[J].Journal of Cleaner Production，2020，266：122096.
[4] YUKSELTAN E，YUCEKAYA A，BILGE A H，et al.Forecasting models for daily natural gas consumption considering periodic variations and demand segregation[J].Socio-Economic Planning Sciences，2021，74：100937.
[5] ZHOU W，PAN J，DING S.Application of a novel discrete grey model for forecasting natural gas consumption：a case study of Jiangsu Province in China[J].Energy，2020，200：117443.
[6] WU W，MA X，ZENG B，et al.A novel grey Bernoulli model for short-term natural gas consumption forecasting[J].Applied Mathematical Modelling，2020，84：393-404.
[7] 张彤.基于WT_LMD与GRU的短期燃气负荷预测方法[D].上海：上海师范大学，2019.
ZHANG T.A combined forecasting model based on improved LMD algorithm and GRU[D].Shanghai：Shanghai Normal University，2019.
[8] 王晓霞，徐晓钟.基于集成深度学习算法的燃气负荷预测方法[J].计算机系统应用，2019，28（12）：47-54.
WANG X X，XU X Z.Gas load forecasting method based on integrated deep learning algorithms[J].Computer Systems & Applications，2019，28（12）：47-54.
[9] 龚承柱，李兰兰，杨娟，等.基于EMD-PSR-LSSVM的城市燃气管网短期负荷预测[J].系统工程理论与实践，2014，34（11）：267-274.
GONG C Z，LI L L，YANG J.An integrated short-term load forecasting approach for urban gas pipeline network based on EMD，PSR and LSSVM[J].Systems Engineering-Theory & Practice，2014，34（11）：267-274.
[10] 陆继翔，张琪培，杨志宏，等.基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J].电力系统自动化，2019，43（8）：191-197.
LU J X，ZHANG Q P，YANG Z H.Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J].Automation of Electric Power Systems，2019，43（8）：191-197.
[11] 宋娟，廖尚泰.基于BP神经网络与多元线性回归的短期燃气负荷预测[J].宁夏工程技术，2019，18（4）：343-346.
SONG J，LIAO S T，YANG J.Short-term gas load forecasting based on BP neural network and multivariable linear regression[J].Ningxia Engineering Technology，2019，18（4）：343-346.
[12] 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）：153-158.
CHENG C，CHENG D L，HE L K.Short-term forecast of urban natural gas load based on BPNN-EMD-LSTM combined model[J].Safty and Environmental Engineering，2019，26（1）：153-158.
[13] YANG B，LI J.Complex network analysis of three-way decision researches[J].International Journal of Machine Learning and Cybernetics，2020，11（5）：973-987.
[14] LI B，TIAN L，CHEN D，et al.An adaptive dwell time scheduling model for phased array radar based on three-way decision[J].Journal of Systems Engineering and Electronics，2020，31（3）：500-509.
[15] LI X，WANG H，XU Z S.Work resumption after epidemic using three-way decisions[J].International Journal of Fuzzy Systems，2021，23（3）：630-641.
[16] 方宇，高磊，刘忠慧.基于三支决策的广义代价敏感近似属性约简[J].南京理工大学学报，2019，43（4）：481-488.
FANG Y，GAO L，LIU Z H.Generalized cost-sensitive approximate attribute reduction based on three-way decisions[J].Journal of Nanjing University of Science and Technology，2019，43（4）：481-488.
[17] YAO J T，AZAM N.Web-based medical decision support systems for three-way medical decision making with game-theoretic rough sets[J].IEEE Transactions on Fuzzy Systems，2015，23（1）：3-15.
[18] YU H，ZHANG C，WANG G Y.A tree-based incremental overlapping clustering method using the three-way decision theory[J].Knowledge-Based Systems，2016，91：189-203.
[19] JIA X Y，LIAO W H，TANG Z M，et al.Minimum cost attribute reduction in decision-theoretic rough set models[J].Information Sciences，2013，219：151-167.
[20] 方宇，闵帆，刘忠慧，等.序贯三支决策的代价敏感分类方法[J].南京大学学报（自然科学），2018，54（1）：148-156.
FANG Y，MIN F，LIU Z H，et al.Sequential three-way decisions based cost-sensitive approach to classification[J].Journal of Nanjing University（Natural Science），2018，54（1）：148-156.
[21] 高铁梅.计量经济分析方法与建模[M].北京：清华大学出版社，2006：152.
GAO T M.Econometric analysis methods and modeling[M].Beijing：Tsinghua University Press，2006：152.
[22] YU X.Light gradient boosting machine：an efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data[J].Agricultural Water Management，2019，225：105758.
[23] CLEVELAND R B，CLEVELAND W S.STL：a seasonal-trend decomposition procedure based on Loess[J].Journal of Official Statistics，1990，6（1）：3-33.
[24] CLEVELAND W S.Robust locally weighted regression and smoothing scatterplots[J].Journal of the American Statistical Association，2012，74（368）：829-836.
[25] YAO Y Y，DENG X.Sequential three-way decisions with probabilistic rough sets[C]//Proceedings of the 10th IEEE International Conference on Cognitive Informatics and Cognitive Computing，2011：18-20.
[26] YAO Y Y.Three-way decision and granular computing[J].International Journal of Approximate Reasoning，2018，103：107-123.