基于组合预测模型的特高压工程造价预测
Cost Forecasting of UHV Project Based on Combination Forecasting Model
DOI: 10.12677/SG.2016.66043, PDF, HTML, XML, 下载: 1,618  浏览: 3,061 
作者: 温卫宁, 郑 燕, 卢艳超:国网北京经济技术研究院,北京;赵昱宣*:浙江大学电气工程学院,浙江 杭州;危雪林:江西博微新技术有限公司,江西 南昌
关键词: 特高压决策造价预测模型UHV Decision Project Cost Forecasting Model
摘要: 特高压工程造价具有投资高、规模大等特点。特高压工程造价预测对提高特高压工程建设的经济效益,指导实际工程的决策和工程管理具有重要意义。首先,根据特高压工程的特点,分析特高工程造价预测思路,提出用多种造价预测方法构建预测模型。然后,根据各预测模型结果,用熵权法计算组合预测权重。由于各方法的局限性,又以特高压工程历史数据特点对组合预测权重进行了修正,得到最终造价组合预测模型。最后,以直流换流站工程和直流线路工程说明了本文组合预测模型的有效性。
Abstract: UHV project is with high investment and large scale. The prediction of UHV project cost is of great significance to improve the economic benefits of UHV construction and to guide the decision and management of the actual project. Firstly, according to the characteristics of UHV project, this paper analyzes the cost forecasting method of UHV project, and puts forward a multi-cost-forecasting method to construct the forecasting models. Then, according to the results of each forecasting model, the Entropy Method is utilized to compute the prediction weight of each model. Due to the limitations of each method and the characteristics of historical data of UHV projects, the combination prediction weights of all used methods are modified to get the final cost combination forecasting model. Finally, the effectiveness of the combined forecasting model is illustrated by a DC Conversion Station Project and a DC Transmission Line Project.
文章引用:温卫宁, 郑燕, 赵昱宣, 卢艳超, 危雪林. 基于组合预测模型的特高压工程造价预测[J]. 智能电网, 2016, 6(6): 394-404. http://dx.doi.org/10.12677/SG.2016.66043

参考文献

[1] 凌云鹏, 阎鹏飞, 韩长占, 杨晨光. 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): 95-99.
[2] 王宁宁, 王飞, 尹彦涛, 李红, 侯郁. 基于支持向量机的换流站工程造价预测研究[J]. 建筑经济, 2016, 37(5): 48- 52.
[3] 李旺, 王绵斌, 饶娆, 颜艳, 谭忠富. 220 kV换流站工程结算阶段造价预测指标体系及模型研究[J]. 电力学报, 2014, 29(2): 145-148.
[4] 应强, 谭颖, 赤鹏军. 基于ANN的电力工程造价预测[J]. 江西电力职业技术学院学报, 2011, 24(4): 21-23.
[5] 冯瀚, 刘冰旖, 张玉鸿, 邱金鹏, 杨海燕, 周萍. 基于FCM和PSO-SVM的电力工程造价预测模型研究[J]. 华东电力, 2014, 42(12): 2713-2716.
[6] 张协奎, 舒会江. 用主成份分析法选取影响地价的主要因素[J]. 基建优化, 2000, 21(1): 25-27.
[7] Fu, J., Tong, J., Wang, Q., et al. (2010) A Data Prediction Method under Small Sample Condition by Combining Neural Network and Grey System Methods. Proceedings of SPIE—The International Society for Optical Engineering, 7997, 79971E.
https://doi.org/10.1117/12.887370
[8] Vapnik, W.N. 统计学习理论的本质[M]. 张学工, 译. 北京: 清华大学出版社, 2000.
[9] 聂宏展, 吕盼, 乔怡, 姚秀萍. 基于熵权法的输电网规划方案模糊综合评价[J]. 电网技术, 2009, 33(11): 60-64.