AN ENERGY-EFFICIENT QOS-AWARE CLUSTERED ROUTING PROTOCOL USING REINFORCEMENT LEARNING FOR WIRELESS SENSOR NETWORKS; [使用无线传感器网络强化学习的节能服务质量感知集群路由协议]

Wireless sensor networks (WSNs) consist of small sensor nodes difficult to replace and with low-energy capacity and have been applied to various fields such as environmental monitoring and surveillance. However, there are many problems that need to be solved regarding the energy-efficient use of sensor nodes, extending the lifetime of the entire network, and efficient packet transmission. The clustering method supports efficient packet transmission by dividing sensor nodes into small groups called clusters. In this method, it is crucial to achieve the above objectives depending on how the cluster head (CH) in charge of transmitting and receiving packets within the cluster is selected. The purpose of this paper is to propose a routing mechanism that can support the required quality of service (QoS) while increasing the lifetime of the entire network through efficient energy use at each node in the WSN. In this paper, we propose not only a CH selection algorithm that improves energy efficiency using reinforcement learning but also a routing mechanism that can support QoS from the source node to the sink node, which is the destination node. The results of the simulation showed that the method proposed in this paper improved the lifetime of the entire network by an average of 24% and the average transmission delay of priority packets by 36% compared with the existing clustering method, the LEACH method. © 2024 by the authors.