基于Bagging算法的水库水沙联合智能调度  

Intelligent Regulation of Reservoir Based on Bagging Algorithm

作　　者：宋星光[1] 夏利民[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410075

出　　处：《计算机工程与应用》2004年第25期218-219,232,共3页Computer Engineering and Applications

基　　金：中科院前沿领域项目; 湖南省自然科学基金项目(编号:99JJY20058)资助

摘　　要：水库水沙调度是一项非常复杂的综合性问题,存在大量的非线性关系。传统的调度方法往往难以达到满意的效果。该文提出了一种基于Bagging算法的水库调度方法。用神经网络建立水库调度预测函数,在此基础上,利用Bagging算法构造了基于神经网络的预测函数序列进行预测,预测的平均值用于水库调度。实验结果表明,符合实际情况,且具有明显的经济安全效益。Reservoir regulation is a very complicated problem with much nonlinear relation.The traditional way of regulating can not meet the demands of production.In this paper,we present a new algorithm based on Bagging for reservoir regulation.Firstly,we build a predictor for reservoir regulation using neural network.Then on the basis of this we use bagging algorithm to build a serials of predictors based on the neural network.At last,a final average value is got for reservoir regulation.Experiment -results have shown good performance in the actual situation with significant economy and security benefits.

关 键 词：水库调度 神经网络 BAGGING算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]