Adaptive fuzzy-based node communication performance prediction with hybrid heuristic Cluster Head selection framework in WSN using enhanced K-means clustering mechanism

Abstract

Listen

Translate article

The “Wireless Sensor Networks (WSN)” has gained a lot of interest among research scholars and has been utilized in various advanced applications in distinct fields. Along with the load balancing techniques, the clustering scheme also prolongs the network’s overall lifespan. The “Cluster Head (CH)” performs the task of load balancing between the nodes in the “Clustering algorithm”; hence, the CH selection procedure is regarded as a critical task in the case of the clustering algorithms. Depending on the CH selection and cluster nodes, the rate of energy consumed by these CHs will be reduced in the wireless sensor. CH selection is a promising solution for the transmission of information within various parameters. Thus, CH selection leads to an increase in the duration of the system and a reduction in the energy utilization by the nodes. Therefore, an “optimization-based CH selection” mechanism in WSN is developed in this paper along with an enhanced node communication performance prediction strategy to provide better communication between the “Sensor Nodes (SNs)” with limited energy expenditure. The node’s communication performance is predicted using the Adaptive Fuzzy, in which metrics such as bit rate, latency, throughput, loss, and packet delivery ratio are specified as the input to the network. Here, the parameters within the fuzzy network are tuned with the help of the recommended “Hybrid Position of Heap and African Buffalo Optimization (HP-HABO)”. Then, to perform efficient node clustering, the “Optimal K-Means Clustering (OKMC)” approach is executed and the CHs are formed using the developed HP-HABO. The objective function depends on the constraints like energy, distance, and predicted communication performance attained by forming these CHs. The performance of the developed CH selection mechanism is verified by analyzing the experimental outcome of the proposed technique with different optimization algorithms and previous works concerning the objective constraints.