Survivability development of wireless sensor networks using neuro fuzzy-clonal selection optimization

Wireless Sensor Networks (WSN) are a kind of wireless network, transmitting data utilizing the multi-hop radio relaying technique, and with no fixed infrastructure. WSN has the ability to function as network host for transmission and reception of data. The unique characteristics of WSN include distributed routing; frequent path breaks due to mobility, packet switching, and self-organization. The energy restriction is an important aspect to consider while designing a sensor network in order to increase the network's survivability. Clustering is an essential approach for overcoming energy limits and increasing network longevity. In the LEACH-technique, simulated annealing optimization is employed to generate the optimal cluster construction. This approach consumes more energy in order to build the best clustering, and the sensor nodes quickly lose energy, reducing the network's survivability. So, Neuro Fuzzy-Clonal Selection Optimization (NF-CSO) model is constructed for minimizing the energy consumption, to identify the optimal position for multi-sink placement and to improve the network survivability. Initially Clonal Selection (CSO) algorithm does the task of determining the optimal position for placing the multi-sink and the Neuro Fuzzy algorithm were utilized to determine the best cluster head, resulting in less energy usage and an increase in network survivability. WSN's energy consumption has been decreased by about 58%, and the network life cycle has been increased by 65% compared to LEACH. The network simulator is used to implement the existing and proposed techniques. From the simulation analysis, it has been proven that the proposed NF- CSO algorithm performs better in selecting the optimal position of the multi-sink, and also reduces the energy consumption and increases network survivability. The proposed approach outperforms the existing LEACH, PSO and BFO techniques.