RSSI Localization Based On Improved Intelligent Algorithm Optimization

Wireless Sensor Networks(WSNs)can monitor and record various information within the deployed area according to the needs of actual application scenarios,usually collected by one or more sets of sensors.Accurate positioning is a piece of indispensable and important information in many application fields of WSNs.Improving positioning accuracy and reducing positioning errors have become one of important research directions in the field of WSNs.Ranging-based positioning technology has higher accuracy,lower application cost,and less energy consumption compared to non-ranging methods,making it widely used.In response to the problem of environmental interference in the ranging process of traditional Received Signal Strength Indicator(RSSI)positioning technology,resulting in ranging errors,and the inability to adjust errors during the positioning stage,resulting in low positioning accuracy,multiple improvement strategies are proposed for optimization.The main research work and innovative points are as follows:(1)During the RSSI ranging process,the complex spatial environment can cause varying degrees of interference to the propagation of signals,resulting in significant fluctuations in the measured RSSI values and significant error effects on subsequent positioning.This article uses Gaussian Kalman hybrid filtering to optimize the measured RSSI values,improve the reliability of RSSI values,and establish an accurate ranging model to obtain accurate distance values between nodes..(2)Aiming at the problem that the accuracy of the basic positioning algorithm is not high and it is difficult to meet the actual needs,RSSI positioning based on improved particle swarm optimization(IPSO)optimization based on multi-strategy is proposed.The original particle swarm algorithm is improved by using chaotic mapping to initialize the population,adjusting the nonlinear inertia weight,and integrating the crossover and mutation ideas of the genetic algorithm.The distance value measured in the ranging stage is applied to the fitness function constructed by the improved algorithm,and calculated as a parameter,and the position of the optimal fitness value is the coordinate of the unknown node.Simulation experiments show that the algorithm effectively improves the positioning accuracy.(3)There are many types of intelligent optimization algorithms,with different characteristics and improvement methods.In order to further improve the positioning accuracy,RSSI positioning based on the improvement sparrow search algorithm(ISSA)optimization is proposed.The cubic chaos mapping was used to initialize the sparrow population,the ideas of the flock algorithm were used to improve the position movement of the finder,the Levy flight strategy was integrated into the follower position update process,and finally the reverse learning and Cauchy perturbation were used to enhance the ability to jump out of the local extremes.Simulation experiments show that the algorithm significantly improves the positioning accuracy.