面向农业无线传感网的数据约简方法研究

Research on Wireless Sensor Network Oriented Agricultural Data Reduction Method

针对农业无线传感网络(Wireless Sensor Networks,WSN)能源有限,而发送大量冗余数据造成节点能耗高的问题,本文提出一种基于节点相关性分析进行数据约简的方法。首先利用皮尔逊相关分析分别对传感节点内与相邻节点间数据进行相似度分析;其次,进行数据预测;最后,对皮尔逊相关系数进行改进,使算法能够适用于实际农业环境感知存在异常数据的情况。实验结果表明,该方法在数据约简精度几乎不受影响的前提下,约简率可达69%,适用于传感节点级数据约简。

For the problem of limited energy in agricultural Wireless Sensor Networks(WSN) and high energy consumption of nodes caused by sending a large amount of redundant data,this paper proposes a method for data simplification based on node correlation analysis.Firstly,Pearson correlation analysis is used to analyze the similarity of data within sensing nodes and between neighboring nodes respectively;secondly,data prediction is performed;finally,Pearson correlation coefficients are improved so that the algorithm can be applied to the situation where abnormal data exist in the actual agricultural environment sensing.The experimental results show that the method is suitable for data simplification at the sensing node level with a simplification rate of 69% with almost no effect on data simplification accuracy.