Abstract:
Monitoring real world phenomenon with the help of wireless sensors network is very popular. These networks comprises of a large number sensors working together to accomplish the dedicated task. As these networks are usually very disperse and dense so sensors are positioned randomly. The location of a few sensors is known a priori rest of sensors nd their location by using localization methods. For a sensor knowing its position is very important. If the positions are not known how they will transmit the information to other in the network. Finding the accurate possible location using lesser energy and resources is very important. A lot of work has been done by the researchers in this era. All try to resolve localization problem but still there are some gaps to be lled. Range base and Range free are the two basic paradigms of localization. Research is conducted by researchers on these two paradigms. Using GPS for locating a sensor is very costly and increases the size of sensor. That's why e ort is made to use less GPS enabled sensors and nding the location of others using the coordinates of GPS enabled sensors. Computational Intelligence based techniques have been used for optimization as well as for localization in past and present. These techniques have shown better results over some existing techniques. Genetic Algorithm, Swarm Intelligence, Ant Colony Optimization, Bio-Inspired Algorithms, and some others fall under the category of Computational Intelligence. These techniques are used over measured locations to optimize the locations of the nodes. Optimization algorithms can provide higher accuracy, lower estimation error and high probability of localization of those nodes having few neighbors. Genetic algorithm, simulated annealing, particle swarm optimization, bacterial foraging algorithm, ant colony etc have been used widely in past for localization. Although lots of e orts are made by the researchers even then there are some gaps to be lled. Genetic algorithm is combined with bacterial foraging algorithm to get better localization accuracy within less localization time. The proposed algorithm is iterative and distributed multidimensional optimization algorithm. The proposed algorithm is used for di erent noise levels and Anchor node densities. It is also compared with Bacterial Foraging Algorithm.
