Energy Optimization in Wireless Sensor Networks using Machine Learning Algorithms
With the evolution from Fifth Generation towards Beyond 5G and 6G (Sixth Generation), achieving energy efficiency has become an important objective in the design of wireless communication systems. The rise in the network density and complexity call for low-energy approaches to facilitate sustainability and longer lifetimes for networks, particularly for Wireless Sensor Networks (WSN). Present work is initiated for energy optimization based on Ant Colony Optimization, that is motivated by the natural behavior of ants. To cope with dynamic and resource-aware settings, Machine Learning (ML) mechanisms are embedded for smart decision-making and optimization. Tree based algorithms like Decision Trees, and Machine learning algorithms like K-Nearest Neighbor have been successfully implemented for wireless applications. ACO was selected for its low computational complexity and distributed and adaptive routing mechanism and has been tested previously in various WSN experiments for increased data delivery and energy efficiency. The findings presented are based on these experiences aligning with the changing demands of 5G and B5G.