Adaptive K-Means Clustering for Energy Optimization in Wireless Sensor Networks Using Calinski-Harabasz Index

Abstract

Efficient energy management and reliable data transmission are crucial for extending the lifespan and improving the performance of wireless sensor networks (WSNs). This study proposes an advanced clustering approach aimed at enhancing network longevity while ensuring dependable data delivery. By integrating the Calinski-Harabasz index into the conventional K-Means clustering algorithm, the methodology evaluates cluster quality and determines the optimal number of clusters, resulting in improved node organization within the network. In addition, routing paths from cluster heads to the base station are strategically optimized to reduce energy consumption. Simulation results demonstrate that this dual enhancement technique outperforms traditional K-Means clustering in terms of energy efficiency, network reliability, and successful data delivery. Overall, the proposed improvements in cluster formation and routing significantly enhance the robustness, efficiency, and practical applicability of energy-constrained wireless sensor networks.