Learning Automata-Based Coverage Oriented Clustering in HWSNs

Now days Wireless Sensor Networks (WSNs) are very popular due to their uses in potential range of applications. A set of either random or predefined distributed tiny sensor nodes could perform the desired task as per need. A huge list of different parameters is available in the litrature that must required special attention while designing the WSN system. Energy saving of each node is one of the key issue as nodes are battery operated and replacement of battery is almost impossible. Network coverage partially or completely is also required to meet out the quality of sensing information. To address these issues, we propose a new Hybrid Hterrogeneous LEACH (HHE-LEACH) protocol for sensor nodes in WSNs. We have used the concepts of learning automata (LA) for the WSN in which every node has LA. Direct or indirect communication with base station (BS) will depends upon the distance-based thresholds which makes a partition of WSN. During this process, each LA may get a reward or penalty with respect to finite number of actions performed. Performance of the HHE-LEACH is evaluated using extensive simulations by selecting various metrics. The results obtained show that proposed scheme achieved better stability, network lifetime and partial network coverage in comparison to other existing protocols such as DD, LEACH and SEP.