架空线路改造工程造价的组合预测方法
CSTR:
作者:
通讯作者:

俞敏(1968),女,硕士,教授级高级工程师,主要从事电网工程技术经济研究;Email:yu_min0107@sina.com

中图分类号:

TM93

基金项目:

国家自然科学基金(U1910216);国网浙江省电力有限公司科技项目(5211JY17000S)


A combinational forecasting method for predicting the cost of an overhead line reconstruction project
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [17]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    架空线路改造工程造价预测是项目管控的重要环节,为提高其预测精度,提出一种组合预测方法。首先,将架空线路改造工程分解为一些子工程,分别预测各子工程造价,之后进行集成。接着,利用主成分分析法并结合专家经验,筛选出影响子工程造价的关键因素,之后,采用基于遗传算法优化的支持向量机和极限梯度提升算法对子工程造价分别进行预测。然后,借鉴博弈论中的Shapley值理论确定组合预测模型中的权重,得到组合预测模型。最后,用实际项目数据对所提出的组合预测方法进行验证,仿真结果表明,与采用单个预测模型相比,所构造的组合预测模型获得了更高的预测精度。

    Abstract:

    The cost prediction of an overhead line reconstruction project represents an important part of management and control of the project, and to improve the prediction accuracy, a combinational forecasting method is presented. An overhead line reconstruction project is first decomposed into several subprojects depending on the characteristics of the project, and the cost prediction could be made first for each subproject and then integrated. The principal component analysis and expertise of domain experts are combined to get the key factors of the subprojects. The genetic algorithm based support vector machine and extreme gradient boosting algorithm are then used for cost prediction respectively. The Shapley value theory in game theory is next employed to determine the weights of combinational forecasting so as to attain an appropriate combinational forecasting model. Finally, an actual overhead line reconstruction project is employed to demonstrate the presented combinatorial forecasting model, and more accurate prediction result is attained, compared with those attained by the genetic algorithm based support vector machine and extreme gradient boosting system independently.

    参考文献
    [1] 凌云鹏,闫鹏飞,韩长占,等.基于BP神经网络的输电线路工程造价预测模型[J].中国电力,2012,45(10):9599.LING Yunpeng,YAN Pengfei,HAN Changzhan,et al.BP neural network based cost prediction model for transmission projects[J].Electric Power,2012,45(10):9599.
    [2] 冯瀚,刘冰旖,张玉鸿,等.基于FCM和PSOSVM的电力工程造价预测模型研究[J].华东电力,2014,42(12):27132716.FENG Han,LIU Bingyi,ZHANG Yuhong,et al.Predicting model of power engineering cost based on the FCM and PSOSVM[J].East China Electric Power,2014,42(12):27132716.
    [3] 彭光金,俞集辉,崔荣,等.基于数据挖掘技术的输电工程造价估算[J].工业工程与管理,2009,14(3):9095.PENG Guangjin,YU Jihui,CUI Rong,et al.Cost estimation of power transmission projects based on data mining technology[J].Industrial Engineering and Management,2009,14(3):9095.
    [4] 王守民.基于关键影响因素的220kV变电工程本体造价预测模型[J].中国科技纵横,2011,12(1):169.WANG Shoumin.220 kV substation project cost prediction based on key factors[J].China Science and Technology Overview,2011,12(1):169.
    [5] 郭艳飞,任雪桂,鞠力,等.基于层次分析法的综合能源系统能效评估方法研究及应用[J].电力科学与技术学报,2018,33(4):121128.GUO Yanfei,REN Xuegui,JU Li,et al.The comprehensive efficiency evaluation method for integrated energy system based on AHP[J].Journal of Electrical Power Science and Technology,2018,33(4):121128.
    [6] 李春生,陈光辉.基于最大信息压缩指标与层次分析法的电力负荷组合预测模型[J].电力科学与技术学报,2008,23(1):5659.LI Chunsheng,CHEN Guanghui.Combination model for power system load forecast based on maximal information compress index and analytic hierarchy process[J].Journal of Electrical Power Science and Technology,2008,23(1):5659.
    [7] 王丰效.不同优化准则统计组合预测权系数优化[J].数学的实践与认识,2013,43(13):135139.WANG Fengxiao.Weight coefficient optimization of combination forecast by different criteria[J].Mathematics in Practice and Theory,2013,43(13):135139.
    [8] 钟波,肖智,周家启.组合预测中基于粗糙集理论的权值确定方法[J].重庆大学学报:自然科学版,2002,25(7):127130.ZHONG Bo,XIAO Zhi,ZHOU Jiaqi.Determination to weighting coefficient of combination forecast based on rough set theory[J].Journal of Chongqing University:Natural Science Edition,2002,25(7):127130.
    [9] 刘思,白桦,张凯,等.基于拟合优度赋权的农网用电需求组合预测[J].电力建设,2015,36(8):5560.LIU Si,BAI Ye,ZHANG Kai,et al.Power demand combination forecasting of rural power network based on goodness of fit empowerment[J].Electric Power Construction,2015,36(8):5560.
    [10] 陈华友.熵值法及其在确定组合预测权系数中的应用[J].安徽大学学报:自然科学版,2003,44(4):16.CHEN Huayou.Entropy method and application to determine weights of combination forecasting[J].Journal of Anhui University:Natural Science Edition,2003,44(4):16.
    [11] 秦国真.云南能源需求影响因素分析及预测[D].昆明:云南财经大学,2011.
    [12] 商立群,王守鹏.改进主成分分析法在火电机组综合评价中的应用[J].电网技术,2014,38(7):19281933.SHANG Liqun,WANG Shoupeng.Application of improved principal component analysis in comprehensive assessment on thermal power generation units[J].Power System Technology,2014,38(7):19281933.
    [13] 卢艳超,张馨.基于核主成分分析模型的输电线路工程造价评价指标[J].电力建设,2012,33(7):7377.LU Yanchao,ZHANG Xin.Cost evaluation index of transmission line project based on kernel principal component analysis model[J].Electric Power Construction,2012,33(7):7377.
    [14] 徐莹,王嘉阳,苏华英.基于遗传算法的支持向量机在径流中长期预报中的应用[J].水利与建筑工程学报,2014,12(5):4245+72.XU Ying,WANG Jiayang,SU Huaying.Application of support vector machine based on genetic algorithm to midterm and longterm runoff prediction[J].Journal of Water Resources and Architecture Engineering,2014,12(5):4245+72.
    [15] CHEN Tianqi,Guestrin C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.San Francisco,CA,USA:ACM,2016.
    [16] Friedman J H.Greedy function approximation:a gradient boosting machine[J].Annals of Statistics,2001,29(5):11891232.
    [17] 李应红,尉询楷.支持向量机和神经网络的融合发展[J].空军工程大学学报:自然科学版,2005,6(4):7073.LI Yinghong,WEI Xunkai.Fusion development of support vector machines and neural networks[J].Journal of Air Force Engineering University:Natural Science Edition,2005,6(4):7073.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

俞 敏,王愿翔,闫 园,等.架空线路改造工程造价的组合预测方法[J].电力科学与技术学报,2020,35(1):24-30.
YU Min, WANG Yuanxiang, YAN Yuan, et al. A combinational forecasting method for predicting the cost of an overhead line reconstruction project[J]. Journal of Electric Power Science and Technology,2020,35(1):24-30.

复制
分享
文章指标
  • 点击次数:272
  • 下载次数: 853
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2020-08-20
文章二维码