An energy-efficient distributed adaptive cooperative routing based on reinforcement learning in wireless multimedia sensor networks

Abstract

Complex task processing and frequent data communication in Wireless Multimedia Sensor Networks (WMSN) demand for energy-efficient and Quality of Service (QoS) guarantee to support new applications especially in the sensing layer of Internet-of-Vehicles. However, the WMSN is heterogeneous and the energy distribution is not uniform, the current routing protocols do not take energy consumption into account while ensuring QoS. Therefore, to make energy distribution more efficiently while ensuring QoS has become a challenging problem. In this paper, we propose an energy-efficient distributed adaptive cooperative routing (EDACR) for WMSN, taking into account the constraints of QoS and energy consumption. Particularly, we design a reinforcement learning based mechanism to perform QoS and energy balanced routing according to the knowledge of reliability and delay. The simulation results show that the energy consumption is reduced while ensuring QoS compared with the traditional cooperative protocol and the distributed adaptive cooperative routing protocol.