Energy Consumption in Wireless Sensor Networks using Genetic Algorithm and Ant Colony Optimization

Now-a-days adaptive scheduling plays a crucial role to reduce energy consumption in Wireless Sensor Networks (WSNs) by adjusting network operations on real-time conditions that increasing the network lifespan. Even though, the existing approaches faced challenges limited battery life and during data transforming and while balancing the energy consumption. To overcome these challenges, this research proposed a robust model using with Genetic Algorithm and Ant Colony Optimization (GA-ACO) model. Initially, Soft Actor Critic (SAC) model is utilized for adjusting transmission power and sensing duration. Further, a hybrid approach using GA- ACO is incorporated to optimize data routing and energy efficient paths. Then, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is employed for handling noise, outlier especially anomalous energy consumption patterns caused by sensor failures. Finally, Bayesian Optimization (BO) is imposed to learns the best energy configurations dynamically. the proposed SAC-GA-ACO attained improved results in terms of Prevalence Threshold ( Pth ) (91.52%), Critical Success Index (CSI) (92.18%), Computation of Delta-P ΔP (95.21%), MCC (91.44%) and Fowlkes-Mallows Index (FMI) (93.82%) when compared to existing Enhanced Energy Optimization Model (EEOM).