Cooperative Coevolution Design of Multilevel Fuzzy Logic Controllers for Media Access Control in Wireless Body Area Networks

Abstract

Fuzzy logic techniques have been successfully employed in wireless body area networks (WBANs) for media access control (MAC). However, most of the existing research work considered only single-level fuzzy logic controls (FLCs) for either contention-based or contention-free MAC, neglecting the importance of utilizing both contention-based and contention-free MAC to improve the reliability and performance of the network. This paper introduces a two-level FLC control scheme at both the coordinator level and the sensor level to further enhance communication quality in WBANs. The sensor-level FLC controls contention-based channel access and the coordinator-level FLC controls contention-free channel access. This two-level FLC architecture can effectively improve the cooperation between sensors and the coordinator such that both the performance and reliability of the network can be significantly improved. We also proposed a cooperative coevolutionary approach to design of our proposed two-level control scheme automatically. With the goal of effectively designing useful FLCs, we have particularly developed two new collaborator selection methods for our cooperative coevolutionary approach, which enable us to effectively select collaborators while evaluating the candidate FLC design in each subpopulation. Specifically, we demonstrate that, by employing network knowledge, our collaborator selection methods can judge the suitability of potential collaborator designs and notably improve the effectiveness of our evolutionary design approach. Empirically the FLCs designed by our approach clearly outperformed several state-of-the-art MAC schemes from recent literature and the IEEE 802.15.4 standard.