WSN Location Method Based on BP Neural Network in NLOS Environment

Given to the non-line-of-sight (NLOS) error existing in the location of wireless sensor network (WSN), together with the strong anti-noise ability, good data approximation and flexible parallel data processing ability of BP neural network, the method of using BP neural network to optimize the location of WSN nodes is put forward in this paper. Firstly, the source of error is analyzed. Then the traditional BP neural network is optimized on the structure and the algorithm to improve the convergence speed. Finally reliable nodes are used to train the neural network. The trained neural network is applied to fulfill the location of unknown nodes. Meanwhile, the simulation results show that this method can effectively suppress NLOS error and its location precision is superior to the traditional Taylor algorithm and Chan algorithm.