Background & Objective:
Location of sensors is an important information in wireless
sensor networks for monitoring, tracking and surveillance applications. The accurate and quick estimation
of the location of sensor nodes plays an important role. Localization refers to creating location
awareness for as many sensor nodes as possible. Multi-stage localization of sensor nodes using
bio-inspired, heuristic algorithms is the central theme of this paper.
Methodology:
Biologically inspired heuristic algorithms offer the advantages of simplicity, resourceefficiency
and speed. Four such algorithms have been evaluated in this paper for distributed localization
of sensor nodes. Two evolutionary computation-based algorithms, namely cultural algorithm and
the genetic algorithm, have been presented to optimize the localization process for minimizing the
localization error. The results of these algorithms have been compared with those of swarm intelligence-
based optimization algorithms, namely the firefly algorithm and the bee algorithm. Simulation
results and analysis of stage-wise localization in terms of number of localized nodes, computing time
and accuracy have been presented. The tradeoff between localization accuracy and speed has been
investigated.
Results:
The comparative analysis shows that the firefly algorithm performs the localization in the
most accurate manner but takes longest convergence time.
Conclusion:
Further, the cultural algorithm performs the localization in a very quick time; but, results
in high localization error.
Finding an Optimal Geometric Configuration for TDOA Location Systems With Reinforcement Learning
