摘要
针对目前我国现代泵站水闸综合自动化控制信息系统的发展现状,通过研究分布式系统中的时延和网络阻塞问题,提出了一种基于支持向量回归(ε-SVR)预测的分布式算法模型,该算法能够有效的预测时延变化,预测效果超过同类型的预测方法。实验和应用表明:与同类型预测方法相比,该模型不但能够在预测效果上达到现有预测水平,而且能大大提高预测速度,适应实时预测的需要。
As to the domestic background and ,significance in sluice integrated automation control system of pumping station,one distribution algorithm model based on ε-support vector regression-based static prediction is designed with studying the network delay and congestion of distribution system.This algorithm can work well in real systems,and it will give more precise results than other prediction models.The results of experiments show that the dynamic prediction model based onsupport vector regression-based static prediction can work well in real-time and provide accuracy comparable to or even better than that of BP-ANN methods.
出处
《工业控制计算机》
2013年第2期63-64,共2页
Industrial Control Computer
