Energy efficient and reliable routing in wireless body area networks based on reinforcement learning and fuzzy logic.

In Wireless Body Area Networks (WBANs), on the one hand, the energy of nodes is limited. On the other hand, the network topology often changes due to human movement or posture changes. Unstable network topology is easy to cause packet loss, and packet loss will cause inaccurate data collection. Therefore, how to effectively use energy to transmit data reliably becomes a key issue. For this problem, we propose an optimized routing protocol namely Energy Efficient and Reliable Routing based on Reinforcement Learning and Fuzzy Logic (EERR-RLFL). In EERR-RLFL, considering the heterogeneity of nodes in WBANs, we first establish a node rank division mechanism, by which sensor nodes are divided into different ranks from three aspects. Each rank is considered to be one of the factors that affect the link quality. Then, we propose the Fuzzy-Logic-based Link Quality Evaluation (FLLQE) algorithm. It makes use of the fuzzy evaluation method of fuzzy logic and considers the comprehensive influence of multiple factors to evaluate the link quality between two nodes, which will provide reference for routing path selection. In the process of data transmission, based on the FLLQE algorithm, we use a hybrid data transmission mode, in which the time when a forwarding node is needed is first determined, and then the Reinforcement Learning algorithm is used to select the global optimized routing path. Simulation results show that EERR-RLFL outperforms Single Hop Transmission and Optimized Cost Effective and Energy Efficient Routing in terms of network lifetime, packet loss ratio and energy efficiency. [ABSTRACT FROM AUTHOR]