Energy Efficient Hybrid Technique Based on Dynamic Clustering in Wireless Sensor Network

Wireless sensor network consists of many sensor nodes which are deployed in the well-organized network. It is a type of ad-hoc network. WSN is data centric and self-configuring network. We are using the neural network, genetic algorithm and dynamic clustering a new hybrid technique is proposed to enhance the energy efficiency and reduce the latency problem. Neural network, genetic algorithm and dynamic clustering are used and a new hybrid technique is proposed to enhance the energy efficiency and reduce the latency problem. Simulation results show that the proposed technique is more efficient, reliable and provide more throughput as compare to the existing technique. In WSN no central controller is present, data routing in the network is controlled by the sensor nodes only. WSN considered nearby environmental conditions for data collection like physical, seismic, temperature, pressure, humidity etc. WSN is deployed in such place where the network is not available like forests, deserts etc. As the sensor nodes are very small in size and have limited resource of power so that we cannot replace that battery. In such conditions, we focus on reducing the battery consumption of the sensor nodes. Energy, delay, throughput and packetloss is compared and the results shows that improvement using a new hybrid technique in the data aggregation.