基于改进RSSI测距的LSSVR三维WSN定位算法

针对基于RSSI测距的定位算法定位误差较大的问题,通过加入多组已知节点之间的距离和接收功率作为参考,提出了一种改进的RSSI测距算法,并将改进的RSSI测距作为最小二乘支持向量回归机LSSVR的输入向量,获得基于改进RSSI测距的LSSVR三维定位算法模型。MATLAB仿真结果表明,在节点随机分布的三维环境中,基于改进RSSI测距的LSSVR定位算法的定位误差比传统LSSVR定位算法减小了13.6%~21.2%,另外,可以通过增加已知节点数量等方法,进一步提高目标定位的准确性。

A LSSVR Three-dimensional WSN Nodes Location Algorithm Based on Improved RSSI

In consideration of the significant localization error of the traditional RSSI algorithm, the paper will apply SVR in WSN location algorithm and combined RSSI location algorithm with LSSVR. Firstly, improve RSSI algorithm by the reference of distances and the received powers between anchor nodes. And then use the improved RSSI ranging as the input vector of LSSVR machine. The simulation show that in the 3D environment where the nodes are randomly distributed, the average localization error of LSSVR based on improved RSSI reduces 13.6%~21.2%, compared with the traditional LSSVR location algorithm. And increasing the number of anchor nodes will improve the accuracy of target localization to a higher degree.