Model combining support vector machine with genetic algorithm in urban water demand forecast application
This paper introduces a model which combine support vector machine with genetic algorithm to forecast city water demand forecast. With the scarcity and the sharply increasing conflict of supply and demand of water resources, the forecast of water demand is becoming an effective way to the water resource programming and management. Yet the scarce samples and the self limitation of the conventional forecast method make the precision low. The support vector regression machine (SVRM) is based on Statistics Learning Theory with the rule of the structure risk minimum. It has some merits, such as dealing with the data of small sample, the high dimension, the global optimization and the excellent generalization ability. As far as the problem of the memory which the accessing kernel matrix increases with the number of samples is concerned, solving the Lagrange multipliers (the coefficient of the samples) is the difficult. The paper adopts the common optimal method-genetic algorithm (GA) to solve the sample coefficients. Compared with the traditional models of urban water demand forecast, GA-SVRM is based on the stable math theory, has the high precision forecast, better applicability, general value in the complex water demand forecast.
Water demand forecast model Support vector machine Statistics learning theory Genetic algorithm
Lingling Zhang Guoqing Shi Taozhen Huang
Department of Administration, School of Public Administration, Hohai University, Nanjing, 210098, China
国际会议
北京
英文
461-465
2007-08-18（万方平台首次上网日期，不代表论文的发表时间）