International Journal of Frontiers in Engineering Technology, 2022, 4(1); doi: 10.25236/IJFET.2022.040101.
Jianqing Li1, Chenchen Wang2, Liming Chen3
1State Grid Anhui Electric Power Co., Ltd. Economic Research Institute, Anhui, China
2China Energy Engineering Group Anhui Electric Power Design Institute Co., Ltd., Anhui, China
3State Grid Anhui Electric Power Co., Ltd., Anhui, China
Transmission engineering is an important part of electric power infrastructure engineering, accurate cost prediction can effectively control the project budget and promote the fine management of electric power enterprises. However, the influence factors of transmission engineering cost are complex, and the traditional prediction method cannot meet the requirements of network refinement development. In this paper, the importance of random forest features is used to extract the key influencing factors, and the grid search method is used to select the optimal random forest parameters and train the random forest model. Finally, the random forest model is tested by actual engineering data and compared with the prediction results of the supporting vector machine model. The results show that the relative error of the stochastic forest model is low, which provides a certain reference value for the cost budget of transmission engineering.
Transmission Line, Engineering Cost, Data Mining, Random Forest
Jianqing Li, Chenchen Wang, Liming Chen. Transmission Engineering Cost Prediction Based on Data Mining. International Journal of Frontiers in Engineering Technology (2022), Vol. 4, Issue 1: 1-6. https://doi.org/10.25236/IJFET.2022.040101.
[1] Wei Xuelin.Guangxi Economy, 2008(11):36-37. (in Chinese)
[2] Abdel-Khalek H., Schafer M., Vasquez R., et al. Forecasting cross-border power transmission capacities in Central Western Europe using artificial neural networks[J]. Energy Informatics, 2019, 2(1) (in Chinese)
[3] Zhang Yuchen, ZHANG Yulin, FENG Chunfei et al.Research on transmission line cost Prediction Model based on BP neural network model [J]. Electric Power Big Data, 2020, 23(06):35-42 (in Chinese)
[4] Wang Jiao. Analysis of main Factors influencing the cost of 500KV substation Project [J].Journal of Engineering Management, 2012, 26(06):66-69 (in Chinese)
[5] Hao Yaogang.Analysis on the Influencing Factors of transmission line Construction Cost [J]. 2011:5 (in Chinese)
[6] Lu Yanchao, ZHENG Yan, Zhao Biao.Analysis of the external environmental impact of power transmission and transformation Project [J]. China Electric Power, 2012, 45(10):100-103 (in Chinese)
[7] Peng Guangjin, YU Jihui, Cui Rong et al.Transmission engineering cost Estimation Based on Data Mining Technology [J]. Industrial Engineering and Management, 2009, 14(03):90-95 (in Chinese)
[8] Wang Jiao, LIU Yanchun.Pso-SVR Project Cost Prediction Model based on Grey Correlation Analysis [J]. Journal of Huaqiao University (Natural Science Edition), 2016, 37(06):708-713 (in Chinese)
[9] Ling Yunpeng, YAN Pengfei, Han Changzhan et al.Power Transmission Line Project cost Prediction Model based on BP neural network [J]. China Electric Power, 2012, 45(10):95-99 (in Chinese)
[10] Xu Li, Li Zhuoran.Research on Construction Cost Prediction Model of UHV Transmission Line -- Based on Factor Analysis and BP Neural Network [J].Industrial Technology Economics, 2017, 36(07):18-26 (in Chinese)
[11] Geng Pengyun, AN Lei, Wang Xin.Construction and Implementation of transmission Engineering Cost Prediction Model Based on Data Mining Technology [J]. Modern Electronic Technique, 2018, 41(04):157-160 (in Chinese)
[12] Zhang Yixiao, GUO Wenpu, Kang Kai et al.TDOA/DOA Joint Positioning Method Based on Clustering and Grid Search [J]. Tactical Missile Technology, 2020(01):105-112 (in Chinese)