Optimal Routing in Wireless Sensor Networks for Advancing IoT Efficiency and Sustainability using Enhanced Ant Colony Algorithm with machine learning approaches

Abstract

This research study aims to investigate the incorporation of machine learning tools, such as Q-learning, Genetic Algorithms, Unsupervised Learning, and Ensemble Learning, into Enhanced Ant Colony Algorithm to assess the impacts of such incorporation on the WSN’s performance. Ten experimental trials were conducted on each to analyze the accuracy, precision, and F1 score results. It was observed that Q-learning achieves an average accuracy of 0.867; precision of 0.842; and F1 score of 0.854, making it highly adaptable and efficient in making routing decisions. The GA presented average accuracy of 0.833; precision of 0.812; and F1 score of 0.821 which show that the tool is highly robust in evolutionary optimization. Unsupervised learning machine performances indicate that the mean accuracy, precision, and F1 score for the model are 0.875, 0.856, and 0.865, respectively . As for ES with multi source models, the model showed the highest performance of 0.898, 0.882, and 0.891 in accuracy, precision, and F1 score, respectively . This study is thus very valuable in the backend regarding application of machine learning tools into routing optimization algorithms and efforts geared towards WSN efficiencies and sustainability..