Abstract

Internet of Things (IoT) integrated with Wireless Sensor Networks (WSNs) plays a critical role in remote monitoring and intelligent decision-making. However, energy conservation remains a major concern due to the limited battery life of sensor nodes. Efficient cluster head (CH) selection directly influences network lifetime and energy consumption. LEACH and fuzzy-based clustering are examples of classic methods that usually can't deal with nodes that act in complicated ways, environments that change, and trying to reach many goals at the same time. This research points to a new Deep Genetic Mechanism (DGM) that could help people make good decisions about CHs. This method uses a genetic algorithm (GA) and a fitness assessor that is based on deep learning. This allows you pick CHs that are stable and use less energy right now. A deep neural network looks at the current state of the network, the energy levels, and the placement of the nodes to discover the best ways to organize them. This network then informs genetic algorithms what to perform, like crossover, selection, and mutation. We utilize MATLAB to do tests on the suggested DGM with real WSN properties. Some of the methods that are compared to it are LEACH, PSO-based CH selection, and fuzzy C-means clustering. DGM is wonderful in many respects, such as how much energy it needs, how many packets it transmits, how long the network lasts, and how stable the nodes are. The network's lifetime went up by 27.4% compared to LEACH, and the number of nodes that failed because of unbalanced residual energy was reduced.

Authors

A. Sumithra¹, S. Gavaskar²
SNS College of Technology, India¹, Bharathiar University, India²

Keywords

Cluster Head Selection, IoT, Wireless Sensor Network, Deep Genetic Algorithm, Energy Efficiency