基于遗传优化最小二乘支持向量机的变电站全寿命周期成本预测模型

doi:10.11930.2015.11.142

摘要/Abstract

摘要： 变电站设备多、投入资金大，建立合理的变电站LCC预测模型，是提高电网资产管理效率的重要手段，其中如何保证算法收敛能力和模型预测精度是目前的研究难点。建立了基于GA优化最小二乘支持向量机的变电站LCC预测模型，选取变电站全寿命周期各阶段的一些具有代表性的指标作为预测模型输入向量，变电站LCC总成本作为输出向量。通过算例，对比了传统LS-SVM预测模型、BP神经网络预测模型和GA优化LS-SVM预测模型的预测结果及性能指标，验证了GA优化LS-SVM预测模型性能的优越性，以便在新建变电站时，实现快速、高效的变电站LCC的预测，有助于实现电网规划时变电站的经济技术评估。

关键词: 变电站, 全寿命周期成本, 遗传算法, 支持向量机

Abstract: Because of large number of equipment and investment during substation construction, building a reasonable life cycle cost (LCC) prediction model is an important means of improving grid assets management efficiency. The methods to ensure convergence capability and improve prediction accuracy are difficulties in current study. A substation LCC prediction model based on least squares support vector machine optimized by GA is proposed. The method use some representative indexes as predictive model input vectors and the total substation LLC cost as the output vector. The results from traditional LS-SVM prediction model, BP neural network prediction model and GA optimized LS-SVM prediction model are compared on selected examples. The comparison verifies superior performance of proposed model. The proposed method can be used during new substation planning and construction to predict station LLC quickly and efficiently.

Key words: substation, life cycle cost, genetic algorithm, support vector machine

中图分类号:

TM711

乔国华，郭路遥，吴一敌，李晶，贾朝阳，郝锋，詹翔灵，王亚运. 基于遗传优化最小二乘支持向量机的变电站全寿命周期成本预测模型[J]. 中国电力, 2015, 48(11): 142-148.

QIAO Guohua, GUO Luyao, Wu Yidi, LI Jing, JIA Zhaoyang, HAO Feng, ZHAN Xiangling, WANG Yayun. Substation Life Cycle Cost Prediction Model of the Least Squares Support Vector Machine Optimized by Genetic Algorithm[J]. journal1, 2015, 48(11): 142-148.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930.2015.11.142

https://www.electricpower.com.cn/CN/Y2015/V48/I11/142

参考文献

[1] 李泓泽，郎斌．全生命周期造价管理在电力工程造价管理中的应用研究[J]．华北电力大学学报，2008（ｌ）：7－11．
LI Hongze, LANG Bin. The application of the whole life cycle engineering cost management on the electricity engineering field[J]. Journal of North China Electric Power University, 2008(l): 7-11．
[2] 丘文千．对变电站建设规模的思考与探讨[J]．浙江电力，2008（5）：5-8．
QIU Wenqian. Thoughts and study on the substation capacity scale[J]. Zhejiang Electric Power, 2008(5): 5-8．
[3] 徐翀．全寿命周期成本管理在电力设备管理中的应用探讨[J]．中国电力，2010，43（3）：72－74．
XU Chong. Research of the apphcatlon in power equipments LCC management [J]. Electric Power, 2010, 43(3): 72-74.
[4] 韩豫，胡继军，查申森，等．变电站全寿命周期设计的理论及应用[J]．中国电力，2011，44（3）：23－26．
HAN Yu, HU Jijun, ZHA Shensen, et al. Key theory and application of substation life cycle design[J]. Electric Power, 2011, 44(3): 23-26．
[5] 刘田．基于效能-全寿命周期成本的变电站经济性评价[D]．杭州：浙江大学，2013．
[6] 路石俊．内蒙古500 kV变电站全生命周期成本管理研究[D]．北京：华北电力大学，2010．
[7] 蔡毅，邢岩，胡丹．敏感性分析综述[J]．北京师范大学学报，2008，44（1）：9－16．
CAI Yi, XING Yan, HU Dan. On sensitivity analysis[J]. Journal of Beijing Normal University, 2008, 44(1): 9-16.
[8] VAPNIK V N． The nature of statistical learning theory[M]． New York: Springer, 2000．
[9] 董明，孟源源，徐长响，等．基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J]．中国电机工程学报，2003，23（7）： 88－92．
DONG Ming, MENG Yuanyuan, XU Changxiang, et al. Fault diagnosis model for power transformer based on support vector machine and dissolved gas analysis[J]. Proceedings of the CSEE, 2003, 23(7): 88-92．
[10] 牛东晓，刘达，陈广娟，等．基于遗传优化的支持向量机小时负荷滚动预测[J]．电工技术学报，2007，22（6）：148－153．
NIU Dongxiao, LIU Da, CHEN Guangjuan, et al. Support vector machine models optimized by genetic algorithm for hourly load rolling forecasting[J]. Transactions of China Electrotechnical Society, 2007, 22(6): 148-153．
[11] 张学工．关于统计学习理论与支持向量机[J]．自动化学报，2000，26（1）：32－42．
ZHANG Xuegong. Introduction to statistical learning theory and support vector machines [J]. Acta Automatica Sinica, 2000, 26(1):32-42．
[12] KEERTHI S S, LIN C J． Asymptotic behaviors of supportvector machines with Gaussian kernel[J]． Neural Computation, 2003, 15(7): 1667-1689．
[13] SUYKENS J A K, VANDEWALLE J． Least squares support vector machine classifiers[J]． Neural Processing Letters, 1999, 9(3): 293-300．
[14] 王群京，鲍晓华，倪有源，等．基于支持向量机和遗传算法的爪极发电机建模及参数优化[J]．电工技术学报，2006， 21（4）：57－61．
WANG Qunjing, BAO Xiaohua, NI Youyuan, et al. Modeling and parameter optimization of the claw-pole alternator based on support vector machines and genetic algorithms[J]. Transactions of China Electrotechnical Society, …, 21(4): 57-61.
[15] 王春林，周昊，李国能，等．基于支持向量机与遗传算法的灰熔点预测[J]．中国电机工程学报，2007，27（8）：11－15．
WANG Chunlin, ZHOU Hao, LI Guoneng, et al. Combining support vector machine and genetic algorithm to predict ash fusion temperature [J]. Proceedings of the CSEE, 2007, 27(8): 11-15．
[16] 徐玉琴，任正，詹翔灵，等．电力变压器全寿命周期成本建模及其综合敏感性分析[J]. 华北电力大学学报：自然科学版，2014，41（6）：80－87．
XU Yuqin, REN Zheng, ZHAN Xiangling, et al. Life cycle cost model and comprehensive sensitivity analysis of power transformer[J]. Journal of North China Electric Power University: Natural Science Edition, 2014, 41(6): 80-87.
[17] 彭路．支持向量机分类算法研究与应用[D]. 长沙：湖南大学，2007．
[18] 董春曦，饶鲜，杨绍全，等. 支持向量机参数选择方法研究[J]. 系统工程与电子技术，2004，26（8）：1117-1120.
DONG Chunxi, RAO Xian, YANG Shaoquan, et al. Method for selecting the parameters of support vector machines[J]. Systems Engineering and Electronis, 2004, 26(8): 1117-1120.
[19] 祝晓燕，张金会，付士鹏，等．基于改进PSO的SVM参数优化及在网速预测中的应用[J]. 中国电力，2013，46（11）：105－108．
ZHU Xiaoyan, ZHANG Jinhui, FU shipeng, et al. Parameter optimization of SVM based on improved PSO and its application in wind speed predictions[J]. Electric Power, 2013, 46(11): 105-108.