Cluster Head Selection Strategy of WSN Based on Binary Multi-Objective Adaptive Fish Migration Optimization Algorithm

One of the hardest problems in deployed wireless sensor networks (WSNs) is how to effectively communicate data that sensor nodes have acquired while using a minimum amount of energy. This problem can be effectively solved with the right cluster head selection technique, but there are a number of things to take into account, including energy usage, cluster head node coverage, and cluster head node count. There exist conflicts among the factors that have a significant impact on wireless sensor network performance. This research offers a Binary Multi-Objective Adaptive Fish Migration Optimization (BMAFMO) algorithm to address the conflict of various parameters and achieve the optimal selection strategy of the cluster head node. The Pareto optimal solution storage approach is introduced by the algorithm to enhance the global search capability of the cluster head node selection problem by using the optimization method and converting the continuous solution into a binary solution in accordance with the sigmoid transformation function. A total of eight test issues and four test metrics were used to thoroughly test the new algorithm. The rank sum test is also used to evaluate the algorithm's dependability. When compared to other algorithms, the test results indicate that the BMAFMO algorithm performed the best in 78.13% of the test problems. Ultimately, the cluster head selection problem of WSN is solved by applying the BAMFMO method, and the simulation results demonstrate that the new approach outperforms other heuristic algorithms in terms of optimization.

Keywords— Binary Multi-Objective Adaptive Fish Migration Optimization (BMAFMO), Wireless Sensor Nodes (WSN), Clustering, Routing, Cluster Head.