Design And Optimization Of Indoor Location Algorithm For Wireless Sensor Networks Based On RSSI

With the development of Internet of Things technology,the application of indoor positioning has gradually become the focus of attention in the fields of environmental monitoring,target tracking,and security monitoring.There are two methods for locating common indoor objects: two-point distance measurement geometry calculation and space-model model matching.The method for measuring the distance between two points generally obtains the estimated distance by means of Received Signal Strength Indication(RSSI),TOA,TDOA,and AOA,and then obtains the position of unknown node by a specific location calculation method.The method for creating a space model is based on a mapping library that prestored a relationship between measurement acquisition signal and actual distance,and uses a matching strategy and a related positioning algorithm to determine the location of an unknown node.Obviously,positioning technology without distance measurement has a significant advantage with low cost.But the collection of RSSI is easily disturbed by random factors such as environment and human measurement.Combining the above two kinds of positioning methods,it is hoped that collecting RSSI from different locations on the basis of a low coat of hardware can avoid accidental interference in the collection environment and establish a positioning method based on Elman neural network mapping to obtain higher positioning accuracy.Considering the uncertainty of the actual RSSI value collected,the uncertainty data collected by the array is represented and evaluated.Kalman filtering is applied to the collected RSSI to establish a wireless signal attenuation model between the RSSI value and the corresponding distance.In order to improve the positioning accuracy,Elman neural network is used to establish mapping matching strategy between actual coordinates and RSSI array.Analyze and evaluate the accuracy and influencing factors of the mapping output positioning results,focusing on improving the accuracy of indoor positioning results.