Outlier detection based energy efficient and reliable routing protocol using deep learning algorithm

Wireless sensor network have also played a vital role in the observation and management of agricultural land in terms of climate, water usage, crops, etc. Due to the open communication system and low battery power of sensors, the agricultural sector still faces issues with energy consumption, information forwarding, and privacy. Thus, an energy-efficient routing during transmission in WSN-based smart agriculture is suggested in this study applying a feed-forward neural network to detect outliers. Outlier identification, CH-selection, and Relay Node (RN) selection are the three phases of this suggested method. Outlier detection is performed in the deployed nodes for categorises attack nodes from the normal nodes. CH-selection is performed using a chaotic moth-flame optimization technique according to distance, node degree, centrality factor and residual energy level, these parameters determine which node will become a Cluster Head. Then reliable routing protocol is designed using NB-based probability method for RN selection. MATLAB software is used to test the proposed Outlier Detection based Energy Efficient and Reliable Routing Protocol and verify its performance. The effectiveness of the proposed-model is tested with some prior wireless sensor network routing protocols environment-fusion multipath routing protocol, dynamic Multi-hop Energy Efficient Routing Protocol, SEMantic CLustering, and Reliable and energy efficient routing protocol. Outlier Detection based Energy Efficient and Reliable Routing Protocol algorithm attained a 0.91 (%)Packet Delivery ratio, 0.08% of packet loss, 0.91% of Average residual energy, 2.8 (Mbps) throughput, and 26 (sec) Delay.