Energy Enhancement and Optimization of WSN using Firefly Algorithm and Deep Learning

Wireless Sensor Network (WSN) is the interconnection of sensor nodes connected by wireless media on a network. All WSNs are under threat due to their short lifetime, reduced energy, decay, security issues, and more. The two main concerns in WSNs i.e., lifetime and energy, are due to multi-hop communication in WSN. To resolve this problem, this paper presents cluster based efficient data transmission using Firefly Optimization Algorithm (FOA) and Deep Learning based Multilayer Radial Neural Network (MRNN) algorithm. The proposed FOA algorithm is based on selecting the appropriate Cluster Head (CH) from sensor nodes. The purpose of selecting the correct CH is to decrease the energy consumption rate. Then, the proposed MRNN method employs the optimal path selection based on node weight, speed, and efficiency of data transfer performance. This paper highlights the optimal use of the proposed method to minimize the energy consumption of WSNs. In addition, the FOA-MRNN algorithm consumes significantly minimum energy, improves energy efficiency, and has less end-to-end latency performance results than those of the traditional methods.