Research On Wireless Network Node Location Technology For Internet Of Things

As the product of the third revolution of information technology industry,the Internet of Things has developed rapidly and applied to all aspects of social life.The Internet of Things relies on network communication technology to connect sensor devices and realize information exchange,it can be applied to sensor device location,intelligent identification and network management.As the underlying supporting technology of the Internet of Things location awareness,wireless sensor network can effectively sense,process and transmit the data information of the network monitoring area through cooperation,it is widely used in defense military,aerospace,transportation,disaster relief and other fields.As one of the important information of wireless sensor network applications,if the location information of nodes is missing,the data information sensed by wireless sensor network will be meaningless.Therefore,how to provide accurate location-aware services has become a key part of the Internet of Things application.Node localization with high accuracy,stability and real-time performance is a hot research topic in wireless sensor networks.Aiming at the problems of low positioning accuracy,low positioning efficiency and weak adaptive ability in current wireless network node technology,this paper follows the latest research and development directions at home and abroad and proposes a Monte Carlo mobile node positioning algorithm based on sampling optimization.Based on the Monte Carlo algorithm,the Newton interpolation method and differential evolution algorithm are used to optimize the sampling process,then the positioning performance of the algorithm is improved.Aiming at the problem that the wireless sensor network is difficult to guarantee the real-time and effectiveness of monitoring information due to end-to-end data delay,a location prediction model based on adaptive cuckoo algorithm to optimize radial basis function neural network is proposed.The location prediction model of the network combines the idea of adaptive cuckoo search algorithm to optimize the parameters in the neural network to improve the prediction performance of the model and can meet the requirements of high real-time scene for the accuracy of mobile node positioning.Finally,the proposed Monte Carlo localization algorithm based on sampling optimization and the location prediction model of mobile nodes are simulated and validated.The simulation results show that compared with other mainstream algorithms,the proposed algorithm has significantly improved the timeliness,robustness and accuracy of node location.By comparing and analyzing the output results of the model,the model proposed in this paper can accurately predict the location information of the nodes in the future.