An Improved Fuzzy Based Clustering Algorithm for MANETs
Abstract
Mobile Ad Hoc Networks (MANETs) are dynamic, self-configuring networks with nodes that can move freely, making traditional clustering challenging due to frequent topology changes. This paper proposes an enhanced clustering algorithm for MANETs by integrating fuzzy logic and Markov Random Field (MRF) principles. The proposed algorithm aims to address the limitations of existing clustering approaches in terms of adaptability and accuracy. The algorithm leverages fuzzy logic to capture the uncertainty and imprecision inherent in the dynamic nature of MANETs. Fuzzy membership functions are employed to assign nodes to multiple clusters simultaneously, reflecting the gradual and overlapping nature of node affiliations. This approach enhances the robustness of cluster formation, ensuring more accurate representation of network dynamics. Furthermore, the incorporation of Markov Random Field introduces a probabilistic modeling framework, allowing the algorithm to consider spatial dependencies between nodes. By exploiting contextual information and neighboring relationships, the proposed algorithm improves the accuracy of cluster head selection and inter-cluster communication. This not only enhances the overall efficiency of the clustering process but also contributes to better adaptability in the face of frequent topology changes