Reinforcement Learning Based Routing Protocol for Wireless Body Sensor Networks

Patients must be continuous and consistent way links to their doctors to control continuous health status. Wireless Body Sensor Network (WBSN) plays an important role in communicating the patient's vital information to any remote healthcare center. These networks consist of individual nodes to collect the patient's physiological parameters and communicate with the destination if the sensed parameter value is beyond normal range. Therefore, they can monitor patient's health continuously. The nodes deployed with the patient form a WBSN and so the network send data from source node to the remote sink or base station by efficient links. It is necessary to extend the life of the system by selecting optimized paths. This paper presents a cluster-based routing protocol by new Q-learning approach (QL-CLUSTER) to find best routes between individual nodes and remote healthcare station. Simulations are made with a set of mobile biomedical wireless sensor nodes with an area of 1000 meters x 1000 meters flat space operating for 600 seconds of simulation time. Results show that the QL-CLUSTER based approach requires less time to route the packet from the source node to the destination remote station compared with other algorithms.