Energy Efficient Machine learning based Self Organizing Fuzzy Clustering and Optimal Multipath Routing (SOFuCR) for IoT enabled Wireless Sensor Network

Abstract:- Wireless Sensor Networks (WSNs) have become instrumental in a wide range of applications, including Internet of Things (IoT) and environmental monitoring. Efficient data communication and resource management are critical for optimizing the performance and longevity of WSNs. In this context, we propose a novel Self-Organizing Fuzzy Clustering and Routing (SOFuCR) model that combines fuzzy logic, clustering, and optimal multipath routing techniques to enhance the overall performance of WSNs.The SOFuCR model begins with an initialization phase, where network parameters are set, and potential cluster heads are selected based on predefined criteria. Subsequently, the nodes calculate their distances to the potential cluster heads and evaluate fuzzy membership values, indicating the strength of their relationship with each cluster head. Based on these fuzzy membership values, nodes join the cluster of the nearest cluster head, leading to the formation of robust and adaptive clusters.The model further employs fuzzy logic to dynamically update the fuzzy weights of nodes within each cluster. These fuzzy weights represent the significance of individual nodes in their respective clusters. Additionally, the SOFuCR model leverages fuzzy-based optimal multipath routing to establish efficient data transmission routes from the cluster heads to the base station. The routing decision- making considers parameters such as residual energy, packet loss, and end-to-end delay to select the most reliable and energy- efficient paths. Through simulation and experimentation, The SOFuCR model outperforms traditional routing protocols in network lifetime, energy consumption, end-to-end delay, packet loss, and throughput, thanks to adaptive clustering and optimized routing mechanisms, resulting in better resource utilization and data delivery efficiency.