ADAPTER: A DRL-Based Approach to Tune Routing in WSNs

As an essential part of the Internet of Things, Wireless Sensor Networks (WSNs) require high energy efficiency and Quality of Service (QoS). Most routing algorithms used in WSNs suffer from two significant limitations: the inability to accommodate multiple optimization objectives and to quickly adjust to dynamically changing environments. In order to address these limitations, we propose an adaptive selection approach of routing algorithm based on Deep Reinforcement Learning, called ADAPTER. This approach allows the system to intelligently select among various routing algorithms in response to changes in the system state, resulting in improved dual optimization of energy efficiency and QoS metrics. Our experiments demonstrate that ADAPTER outperforms a single routing algorithm in terms of network lifetime, average end-to-end delay, and packet loss rate.