Categorizing WSN´s sensory data using Self Organizing Maps

Wireless sensor networks suffer greatly from their limited battery power whose utilization is increased manifolds as a node has to transmit or receive fairly large amount of data. Several algorithms, some for scheduling battery power e.g. dynamic voltage scheduling, static voltage scheduling, dynamic power management etc and other with emphasis on designing efficient routing protocols have been designed in past. Some algorithms, however, address this very issue at software level by writing memory and CPU friendly programs. This paper proposes self organizing maps (SOM) based unsupervised artificial neural network learning technique to enhance average battery life. Proposed system allows all active nodes to transmit their sensory data to the base station node (BSN) which has a 2times3 SOM running on it. Sensor nodes start sending data to the BSN; it keeps on making categories and puts relevant data in appropriate categories/classes. SOM is trained after it has received a number of such transmissions from active nodes. Class definitions are then broadcast to all active nodes by BSN and from then onwards they transmit only the class definitions (that are fairly lesser in size) to BSN and hence significant battery power is conserved. We have showed an overall 48.5% battery power saving using the above technique.