Enhancing Energy Efficiency in Wireless Sensor Networks via Adaptive Sparse Bayesian Learning
Mustafa Abdul-Rahman Al-Zurfi, Ahmed Al Hilli, Mohanad Al-Ibadi · 2024
In this research study, we offer an energy-efficient technique to reduce energy consumption in Wireless Sensor Networks (WSNs). In addition to using the Bayesian model in conjunction with adaptive compressive sensing (A-CS), our methodology presents a novel approach to minimise the number of sensors needed for successful target detection. During the initial stage, a small number of sensors are chosen at random. Depending on our procedure approach, the base station (BS) calls the sensors’ measurements that obtain the highest values in the Error bars. This methodology not only improves resource utilization and enhances overall network performance, but it also increases the energy efficiency of WSNs. Our research results show how successful and efficient this approach is at resolving the energy consumption issue that arises in WSNs where the energy consumed in the proposed approach is substantially lower than that consumed by other approaches especially when there were few targets. Our approach solves the energy consumption issue in WSNs by reducing the number of sensors used and preserving exemplary target detection levels, which will further wireless sensor technology.