Self-organising map-based dynamic decision-making algorithm for heterogeneous wireless sensor network

ABSTRACT

Wireless sensor networks (WSNs) are applicable in most of the domains of engineering. Presently, Heterogeneous WSN (HWSN) is gaining more importance than homogeneous WSN. One of the major challenges of a HWSN is efficient deployment which can provide good coverage. The deployment strategy in WSN can be static or dynamic. It is found that there is a need of dynamic deployment that intelligently places the sensor nodes in the deployment area. This intelligence is possible by one of the artificial neural networks concept like self-organizing map (SOM). This work presents a dynamic decision-making algorithm (DDMA) for deployment of sensors using SOM such that the nodes will adjust their locations to uncovered area by failed sensor node in the changing sensing environment. The DDMA is compared with LEA2C and ECBS which are variants of LEACH. The results show that proposed DDMA performs better than the existing algorithm in-terms of decreased node depletion rate by 35% and 25% more coverage. The experimental analysis also show that SOM-based DDMA performs better than the non-SOM-based DDMA deployment for HWSN in terms of 5% better energy conservation, 30% better network lifetime, 75% more coverage in the deployment area and 90% reduced node depletion rate.

This work presents a dynamic decision-making algorithm (DDMA) for deployment of sensors using self-organising map (SOM) such that the nodes will adjust their locations to uncovered area by failed sensor node in the changing sensing environment. The DDMA is compared with variants of LEACH with existing LEA2C and ECBS. The results show that proposed DDMA performs better than the existing algorithm in-terms of decreased node depletion rate by 35% and 25% more coverage. The experimental analysis is performed between SOM-based and non-SOM-based DDMA algorithms. Results show that SOM-based DDMA performs better than the non-SOM-based DDMA deployment for heterogeneous WSN in terms of 5% better energy conservation, 30% better network lifetime, 75% more coverage in the deployment area and 90% reduced node depletion rate.

GRAPHICAL ABSTRACT

KEYWORDS:

• Dynamic decision-making algorithm (DDMA)
• wireless sensor network (WSN)
• neural network (NN)
• self-organising map (SOM)

Disclosure statement

No potential conflict of interest was reported by the author(s).