计算机应用 ›› 2010, Vol. 30 ›› Issue (1): 127-129.

• 网络与通信 • 上一篇    下一篇

无线传感器网络中基于SVR的节点数据预测算法

邹长忠   

  1. 福州大学 数学与计算机科学学院
  • 收稿日期:2009-07-09 修回日期:2009-08-21 发布日期:2010-01-01 出版日期:2010-01-01
  • 通讯作者: 邹长忠
  • 基金资助:
    福建省自然科学基金计划资助项目;福州大学科技发展基金资助项目

Node data prediction based on SVR in wireless sensor network

ZOU ChangZhong   

  • Received:2009-07-09 Revised:2009-08-21 Online:2010-01-01 Published:2010-01-01
  • Contact: ZOU ChangZhong

摘要: 线传感器网络主要用于收集环境的信息,但是由于能量的限制或者安全性等问题,存在无线传感器网络节点失效问题,一旦节点失效,将不能收集后续数据,如何预测节点将来的数据成为一个关键问题。提出一种基于支持向量回归(SVR)的节点数据预测算法,充分利用节点先前收集的数据,预测未来的数据。从仿真实验上,证明该算法的有效性和较小的预测误差率。

关键词: 无线传感器, 节点, 数据预测, 算法, 支持向量回归

Abstract: Wireless sensor network is mainly used in collecting the environment information, but due to limited energy and security some nodes are easy to break down, thus these nodes will not collect data. How to forecast the sequent data will become a key problem. In this paper, a data estimating algorithm based on Support Vector Regression (SVR) in Wireless Sensor Network (WSN) was proposed which used the previous data to estimate the sequent data. The simulation shows that the scheme is efficient and of less prediction error.

Key words: wireless sensor networks, node, data prediction, algorithm, Support Vector Regression (SVR)