ELDC: An Artificial Neural Network Based Energy-Efficient and Robust Routing Scheme for Pollution Monitoring in WSNs

Abstract

The range of applications of Wireless Sensor Networks (WSNs) is increasing continuously despite of their serious constraints of the sensor nodes’ resources such as storage, processing capacity, communication range and energy. The main issues in WSN are the energy consumption and the delay in relaying data to the Sink node. This becomes extremely important when deploying a big number of nodes, like the case of industry pollution monitoring. We propose an artificial neural network based energy-efficient and robust routing scheme for WSNs called ELDC. In this technique, the network is trained on huge data set containing almost all scenarios to make the network more reliable and adaptive to the environment. Additionally, it uses group based methodology to increase the life-span of the overall network, where groups may have different sizes. An artificial neural network provides an efficient threshold values for the selection of a group's CN and a cluster head based on back propagation technique and allows intelligent, efficient, and robust group organization. Thus, our proposed technique is highly energy-efficient capable to increase sensor nodes’ lifetime. Simulation results show that it outperforms LEACH protocol by 42 percent, and other state-of-the-art protocols by more than 30 percent.