Please wait a minute...
浙江大学学报(工学版)
J4  2011, Vol. 45 Issue (6): 1100-1103    DOI: 10.3785/j.issn.1008-973X.2011.06.023
    
Genetic least squares support vector machine approach
to hourly water consumption prediction
CHEN Lei
College of Civil Engineering and Architecture, Zhejiang University of Technology, Hangzhou 310014, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

As traditional least squares support vector machine(LSSVM) parameter selection using cross-validation is timeconsuming, a city hourly water consumption forecasting method based on genetic algorithm(GA) and LSSVM was proposed. An autocorrelation method was used to analyze the hourly water consumption series according to the strong serial correlation. A self-adaptive binary GA was introduced to optimize the hyper-parameters of LSSVM, and the individual fitness values in GA were determined by cross-validation. Then a hourly water consumption forecasting model was built. Case study shows that the proposed hourly water consumption forecasting method based on GA and LSSVM has higher computing speed and better estimating performance than the traditional LSSVM–based method.

Published: 14 July 2011
CLC:  TU 991.33  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

CHEN Lei. Genetic least squares support vector machine approach
to hourly water consumption prediction. J4, 2011, 45(6): 1100-1103.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2011.06.023     OR     https://www.zjujournals.com/eng/Y2011/V45/I6/1100


遗传最小二乘支持向量机法预测时用水量

为解决传统最小二乘支持向量机采用交叉验证确定参数耗时较长的问题,提出基于遗传算法和最小二乘支持向量机的城市时用水量预测方法.根据城市时用水量序列具有较强相关性的特点,利用自相关系数法分析时用水量序列的变化规律,并引入二进制编码的自适应遗传算法优化最小二乘支持向量机的超参数,采用交叉验证法确定遗传算法个体的适应值,建立了时用水量预测模型.实例分析表明：与基于传统最小二乘支持向量机的时用水量预测方法相比,基于遗传算法和最小二乘支持向量机的时用水量预测方法计算速度更快,预测精度更高.

［1］ VAPNIK V N. The nature of statistical learning theory ［M］. New York: Springer, 1995.
［2］ 王亮,张宏伟,牛志广.支持向量机在城市用水量短期预测中的应用［J］.天津大学学报,2005,38(11): 1021-1025.
WANG Liang, ZHANG Hongwei, NIU Zhiguang. Application of support vector machines in shortterm prediction of urban water consumption［J］.Journal of Tianjin University, 2005,38(11): 1021-1025.
［3］ 俞亭超,张土乔,柳景青.峰值识别的SVM模型及在时用水量预测中的应用［J］.系统工程理论与实践,2005,25(1): 134-137.
YU Tingchao, ZHANG Tuqiao, LIU Jingqing. SVM model with peak value recognition and its application to hourly water consumption forecasting［J］. System Engineering–Theory & Practice, 2005, 25(1): 134-137.
［4］ SUYKEN J A K, VAN G T, DE M B, et al. Least squares support vector machines［M］. Singapore: World Scientific, 2002: 71-111.
［5］ 王小平,曹力明.遗传算法理论、应用与软件实现［M］.西安:西安交通大学出版社,2002: 73-74.
［6］ VAN G T, SUYKEN J A K, BAESENS B, et al. Benchmarking least squares support vector machine classifiers［J］. Machine Learning, 2004, 54(1): 5-32.
［7］ 丁晶,邓育仁.随机水文学［M］.成都:成都科技大学出版社,1988: 18-20.
[1] LI Hong-wei, WANG Meng-lin, LV Mou, LI Hong-yan. Simulation of contamination source identification in water
supply system and analysis of influencing factors[J]. J4, 2011, 45(1): 81-86.
[2] CHEN Cheng, SHU Ting-Chao, ZHANG Cha-Jiao. Detecting accidental contaminations in municipal water networks[J]. J4, 2010, 44(8): 1604-1607.