Performance Comparison of WSN &WSAN using Genetic Algorithm

Abstract A wireless sensor network (WSN) consists of two sets of nodes: sensors and actors, where the set of sensors performs all the sensing (data collection) from their surrounding environment. Since sensors operate by batteries, then they are limited with their processing and communication capabilities due to the short life-span of the batteries. On the other hand, the set of actors has more capabilities with extended life-span batteries, and their roles are to collect and process the raw data from the sensors to determine the next action for WSN. The actor placement problem is to select a minimal set of actors and their optimal locations in WSN keeping in mind the communication requirements between sensors and actors. We have encoded the actor placement problem into the evolutionary approach, where the objective function is to find the minimal total number of actors covering as many sensors as possible to improve the performance of WSN. The experimental results demonstrate the feasibility of our evolutionary approach in covering 77% of 61 sensors by three actors and its performance is compared for various parameters.

[1]  Sami J. Habib,et al.  Optimization of Actors Placement within Wireless Sensor-Actor Networks , 2007, 2007 12th IEEE Symposium on Computers and Communications.

[2]  Ian F. Akyildiz,et al.  Wireless sensor and actor networks: research challenges , 2004, Ad Hoc Networks.

[3]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[4]  Y.T. Hou,et al.  On energy provisioning and relay node placement for wireless sensor networks , 2005, IEEE Transactions on Wireless Communications.

[5]  Jiangchuan Liu,et al.  A real-time communication framework for wireless sensor-actuator networks , 2006, 2006 IEEE Aerospace Conference.

[6]  D.B. Jourdan,et al.  Layout optimization for a wireless sensor network using a multi-objective genetic algorithm , 2004, 2004 IEEE 59th Vehicular Technology Conference. VTC 2004-Spring (IEEE Cat. No.04CH37514).

[7]  Roger L. Wainwright,et al.  A genetic algorithm applied to graph problems involving subsets of vertices , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[8]  Olivier L. de Weck,et al.  Multi-objective genetic algorithm for the automated planning of a wireless sensor network to monitor a critical facility , 2004, SPIE Defense + Commercial Sensing.