A Q-Learning-Aware Optimal Routing Innovation Using Intelligent Neighbor Node Detection (Q-ORIGIN) in Wireless Body Area Networks

In recent years, wireless body area networks have gained significant attention for their potential applications in healthcare, sports, and entertainment. However, the performance of such networks is limited due to the challenges posed by the human body, including the variability in signal propagation, energy consumption, and node mobility. In this paper, A Q-learning, a popular reinforcement learning technique, finds the optimal path by detecting the optimal node to forward the packets from a node belonging to the inter-body area network cluster to the sink to improve the network performance for inter-wireless body area networks. The proposed approach considers input parameters such as remaining energy, distance, sensor coordinates, a sink node, routing, Q-value, and reward function to enable nodes to learn optimal actions based on the current state of the network. Through simulations, we demonstrate that Q-learning can significantly improve network performance metrics, including throughput, number of dead nodes, and packet loss ratio. Our results show that the proposed approach outperforms other state-of-the-art methods, indicating its potential for real-world applications in inter-wireless body area networks.