基于K-Means的水下传感器网络AUV数据收集方法

A data collection method for AUV based on K-Means in underwater sensor networks

水下传感器网络(underwater sensor networks,UWSNs)具有节点稀疏布置的特点,目前主要采用自主式水下航行器(autonomous underwater vehicle,AUV)收集网络中的数据,其中AUV如何移动从而高效地完成数据收集任务是一个关键问题。文章提出了一种基于K-Means的水下传感器网络AUV数据收集方法,首先利用K-Means聚类理论对水下传感器网络进行划分,并以节点通信范围为约束条件得到网络划分结果,即多个网络子集,又称"子团";然后针对网络的变化,节点自主调整子团的结构并确定数据收集点;最后依据多个数据收集点形成AUV的最优移动路径。大量的实验结果表明该方法可以有效地规划出AUV的移动路径,不仅可以完成全网数据收集任务,而且具有耗时短、能耗效率高的优点。

Underwater sensor networks(UWSNs)has specific character of sparsely deployed sensors.At present,a solution that involves the use of autonomous underwater vehicle(AUV)to collect data from the individual sensor node has been widely applied,for which the path planning for the AUV is a key problem.In this paper,a data collection method for the AUV based on K-Means in the UWSNs is proposed.Firstly,the UWSNs are divided by related K-Means algorithm and the final division result,namely network subsets or“subclusters”,is formed with the constraint of communication radius of sensors.Secondly,the sensors adjust the architecture of subclusters to the variations of the sensor networks and compute the optimized data collection points.Finally,the optimal path for the AUV is formed based on the data collection points.Extensive experiments have demonstrated that the proposed method can effectively plan the path for the AUV to gather data from all sensors with advantages such as short data collection time and high energy efficiency.