Abstract: The Wireless Sensor Network (WSN) is the type of Ad hoc network. WSN is the self configuring networks; any sensor node can join or leave the network when they want. In WSN the main issue is battery consumption so to conserve the network lifetime many protocols are designed. WSN’s are deployed in the far places like forests, deserts etc so it is very difficult to recharge or replace the battery of the sensor nodes. In these conditions, we focus to reduce the battery consumption of the sensor nodes. In this paper, we are proposing a new technique on enhancement of DRINA protocol, to reduce battery consumption and recover link failure. It will be based on the static clustering using relay nodes. Before data transmission sensor nodes form the cluster dynamically using the neural network and weights are adjust according to the situation and it also enhance the efficiency of the dynamic clustering. Experimental results show that new proposed technique is more efficient, reliable and provide more throughput as compare to the existing technique.
Keywords: Learning, Neural Networks Clusters, Boltzmann learning.