Autonomous Maintenance in IoT Networks via AoI-driven Deep Reinforcement Learning
This work aims to reduce resource waste in IoT network maintenance for network operators by automating maintenance decisions.
This paper addresses the challenge of autonomous maintenance in IoT networks by formulating it as a Partially Observable Markov Decision Process. It utilizes Deep Reinforcement Learning with Age of Information (AoI) as a reward signal to train agents that decide on the necessity and type of maintenance, demonstrating that AoI effectively informs the training process.
Internet of Things (IoT) with its growing number of deployed devices and applications raises significant challenges for network maintenance procedures. In this work, we formulate a problem of autonomous maintenance in IoT networks as a Partially Observable Markov Decision Process. Subsequently, we utilize Deep Reinforcement Learning algorithms (DRL) to train agents that decide if a maintenance procedure is in order or not and, in the former case, the proper type of maintenance needed. To avoid wasting the scarce resources of IoT networks we utilize the Age of Information (AoI) metric as a reward signal for the training of the smart agents. AoI captures the freshness of the sensory data which are transmitted by the IoT sensors as part of their normal service provision. Numerical results indicate that AoI integrates enough information about the past and present states of the system to be successfully used in the training of smart agents for the autonomous maintenance of the network.