陆春光,葛梦亮,宋磊,吴继亮,潘国兵
LU Chunguang,GE Mengliang,SONG Lei,WU Jiliang,PAN Guobing

• 1:国网浙江省电力有限公司营销服务中心
• 2:国网浙江省电力有限公司庆元县供电公司
• 3:浙江工业大学机械工程学院

摘要(Abstract)：

为了更好地掌握省域电能替代的量化潜力，提出了一种基于Lasso-XGBoost-Stacking的预测模型。通过交叉特征量化经济发展、环保、能源价格、政策扶持与技术进步共五种影响因素以降低各影响因素之间的多重共线性，并利用Lasso回归模型评价各量化影响因素的权重。以浙江省为例进行电能替代潜力预测分析，预测MAPE（平均绝对百分比误差）为12.22%，其准确性能够满足省域电能替代量化潜力分析的要求。对浙江省多情景电能替代场景分析发现，经济发展因素对电能替代潜力的影响最大，相较于工业、农业等领域，交通业有着最大的电能替代潜力。
In order to better grasp the quantitative potential of provincial power substitution, a prediction model based on Lasso-XGBoost-Stacking is proposed. Five influencing factors, including economic development, environmental protection, energy price, policy support and technological progress, are quantified by cross-features to reduce the multicollinearity among the influencing factors. Besides, the weights of the quantified influencing factors are evaluated by using Lasso regression model. The predicted MAPE(mean absolute percentage error) of Zhejiang province is up to 12.22%, which can meet the requirements of quantitative potential analysis of power substitution in the province. The analysis of the multi-scenario power substitution scenarios in Zhejiang reveals that economic development has the greatest impact on power substitution potential, and the transportation industry has the greatest power substitution potential relative to industry, agriculture and other sectors.

关键词(KeyWords)： 电能替代;Lasso回归;XGBoost;Stacking;量化影响因素
power substitution;Lasso regression;XGBoost;Stacking;quantified influencing factors

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（B311YF220001）

作者(Author): 陆春光,葛梦亮,宋磊,吴继亮,潘国兵
LU Chunguang,GE Mengliang,SONG Lei,WU Jiliang,PAN Guobing

DOI: 10.19585/j.zjdl.202309002

参考文献(References)：

• [1]李昌祖，牛东晓，张欣岩，等.基于改进的粒子群优化BP神经网络浙江电能替代潜力预测模型[J].科学技术与工程，2020,20(13):5173-5179.LI Changzu,NIU Dongxiao,ZHANG Xinyan,et al.Zhejiang Province electric power substitution potential prediction model based on improved particle swarm optimization BP neural network[J].Science Technology and Engineering,2020,20(13):5173-5179.
• [2]王永利，蔡成聪，姚苏航，等.基于电能替代的中国碳排放演化趋势研究[J].生态经济，2022,38(10):20-28.WANG Yongli,CAI Chengcong,YAO Suhang,et al.Study on evolution trend of carbon emissions in China based on electric energy substitution[J]. Ecological Economy,2022,38(10):20-28.
• [3]张静，李昊，李文，等.面向碳中和的中国电能替代发展路径规划方法探讨[J].电力建设，2022,43(9):47-53.ZHANG Jing,LI Hao,LI Wen,et al. Discussion on the pathways of China’s electrification polices to pursue the carbon neutralization target[J]. Electric Power Construction,2022,43(9):47-53.
• [4]刘自敏，张娅.空间视角下电能替代对能源强度的影响及其机制研究[J].首都经济贸易大学学报，2022,24(2):57-70.LIU Zimin,ZHANG Ya.The influence of electric energy substitution on energy intensity from spatial perspective[J].Journal of Capital University of Economics and Business,2022,24(2):57-70.
• [5]李昌祖.浙江省电能替代潜力预测及发展策略研究[D].北京：华北电力大学，2020.LI Changzu.Study on prediction and development strategy of electric energy substitution potential in Zhejiang Province[D].Beijing:North China Electric Power University,2020.
• [6]陈吉奂，卢毓东，苗博，等.基于逻辑回归模型的电能替代用户辨识研究[J].浙江电力，2020,39(1):16-21.CHEN Jihuan,LU Yudong,MIAO Bo,et al.Research on user identification of electric energy substitution based on logistic regression model[J]. Zhejiang Electric Power,2020,39(1):16-21.
• [7]李艳梅，陈增.基于联系度优化TOPSIS法的区域电能替代潜力评估研究[J].电网技术，2019,43(2):687-695.LI Yanmei,CHEN Zeng.Study on regional electric energy substitution potential evaluation based on TOPSIS method of optimized connection degree[J].Power System Technology,2019,43(2):687-695.
• [8]苗常海，梁佳丽，郭艳飞，等.基于AHP和灰色关联分析的电能替代效果评估[J].控制工程，2018,25(5):903-909.MIAO Changhai,LIANG Jiali,GUO Yanfei,et al. Efficiency evaluation of alternative energy based on AHP and grey relation analysis[J]. Control Engineering of China,2018,25(5):903-909.
• [9]汲国强，吴姗姗，谭显东，等.2021年我国电力供需形势分析及展望[J].发电技术，2021,42(5):568-575.JI Guoqiang,WU Shanshan,TAN Xiandong,et al.Analysis and prospect of China’s power supply and demand situation in 2021[J].Power Generation Technology,2021,42(5):568-575.
• [10]唐伟.电能替代实施现状及发展趋势预判[J].中国能源，2020,42(2):35-38.TANG Wei. Current situation analysis and development trend prediction of electric energy substitution[J].Energy of China,2020,42(2):35-38.
• [11]梁毅.京津冀地区电能替代潜力预测及优化管理研究[D].北京：华北电力大学，2019.LIANG Yi.Study on prediction and optimal management of electric energy substitution potential in beijing-Tianjinhebei region[D].Beijing:North China Electric Power University,2019.
• [12]徐璐.冀北地区电能替代发展预测研究[D].北京：华北电力大学，2018.XU Lu.Study on prediction of electric energy substitution development in northern Hebei Province[D]. Beijing:North China Electric Power University,2018.
• [13]夏怀健，林海英，张文，等.基于多模型的区域电能替代发展潜力研究[J].科技管理研究，2018,38(4):241-246.XIA Huaijian,LIN Haiying,ZHANG Wen,et al.Research on development potential of regional electric energy substitution based on multi model[J].Science and Technology Management Research,2018,38(4):241-246.
• [14]王伟，杨跞，杜晓彬，等.基于混合改变惯性因子PSO-BP的短期电力负荷预测[J].宁夏电力，2017(6):28-34.WANG Wei,YANG Luo,DU Xiaobin,et al.Short-term load forecast based on PSO-BP of mixed changing weight[J].Ningxia Electric Power,2017(6):28-34.
• [15]孙毅，石墨，单葆国，等.基于粒子群优化支持向量机的电能替代潜力分析方法[J].电网技术，2017,41(6):1767-1771.SUN Yi,SHI Mo,SHAN Baoguo,et al.Electric energy substitution potential analysis method based on particle swarm optimization support vector machine[J]. Power System Technology,2017,41(6):1767-1771.
• [16] TIBSHIRANI R. Regression shrinkage and selection via the lasso:a retrospective[J].Journal of the Royal Statistical Society:Series B(Statistical Methodology),2011,73(3):273-282.
• [17] CHEN T Q,GUESTRIN C. XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.August 13-17,2016,San Francisco,California,USA.New York:ACM,2016:785-794.
• [18]浙江省统计局.浙江省统计年鉴-2021[M].北京：中国统计出版社，2021.
• [19]国家统计局能源统计司.中国能源统计年鉴-2021[M].北京：中国统计出版社，2021.
• [20]佚名.CCTD中国煤炭市场网[DB/OL].[2022-08-01].https：//www.cctd.com.cn/list-167-1.html.