Wireless Sensor Network Multi-Hop Positioning Algorithm Based on Continuous Regression

Abstract

The traditional multi-hop positioning algorithm is easily affected by the network anisotropy, thus resulting in unstable positioning performance. The wireless sensor network multi-hop positioning algorithm based on continuous regression is put forwarded in the paper to address this problem. By utilizing the continuous regression model, the mapping relationship between the hop count and Euclidean distance is constructed so as to transform the positioning process model into regression prediction. Theoretical analysis and simulation results show that the improved algorithm improves the positioning accuracy, and avoids the influence of the network topology anisotropy on the performance of the algorithm. The algorithm requires little expenditure and few parameters so it can be adapted to wireless sensor networks with irregular nodes distribution, and can be of great engineering application value.