A New Localization Algorithm for Underwater Acoustic Sensor Networks

Localization is one of most important technologies in Underwater Wireless Sensor Networks (UWSNs) since it plays a critical role in many applications. The variable speed of sound and the long propagation delays under water in addition to bandwidth limitations all pose a unique set of challenges for localization in UWSN. Localization algorithms are divided under two subcategories: range-based and range-free schemes. Range-based scheme uses measure distances or angles for estimating position of unknown node. But Range-free scheme uses stage-count or area-based schemes to estimate position of unknown node and does not need additional hardware. Range-free scheme is less accurate. On the other hand, range-based localization algorithms are not suitable for underwater networks because it needs additional hardware and also it does not act well. In this paper an improved range-free localization method is introduced. First ASP schema is simulated that is a range-free schema. Its drawback is to be less accurate due to its accuracy depends on distance determination. After that an improved method is presented that is based on range-free schema. In the proposed method, average distance between sensor node and connected anchor nodes, position of anchor nodes are given to a neural network. This neural network determinates position of sensor nodes after training. Simulation results in two distributed and centralized techniques are shown that improved algorithm includes high accuracy, fast convergence, wide coverage, low communication costs and good scalability features.