Abstract:
Wireless Sensor Networks (WSNs) play a crucial role in various domains like environmental monitoring, agriculture, home automation, and healthcare. However, they face challenges such as limited resources, dynamic environments, data routing issues, scalability, unreliable wireless communication, mobility, security concerns, limited bandwidth, and fault tolerance. Machine Learning (ML) techniques have been utilized to address these challenges. Additionally, Multi Criteria Decision Analysis (MCDA), a tool for making decisions involving multiple criteria, is helpful in scenarios like cluster head selection in WSNs. This paper proposes a hybrid approach that combines ML for initial rounds, followed by MCDA based mechanisms in later rounds. The approach is evaluated using metrics like energy consumption, node degree, remaining energy, sink node location, and distance metrics and shows better performance compared to the ML technique alone.