The fast-paced utilization of innovative Internet of Things (IoT) applications emphasizes the critical role that routing protocols play in designing an efficient communication system between network nodes. In this context, the lack of adaptive routing mechanisms in the standard Routing Protocol for Low-power and Lossy Networks (RPL), such as load balancing and congestion mechanisms, especially under heavy load scenarios, causes significant degradation of network performance. In this regard, integrating innovative and effective learning abilities, such as Reinforcement Learning, into an efficient routing policy has demonstrated promising solutions for future networks. Hence, this paper introduces Aris-RPL, an adaptive routing policy for the RPL protocol. Aris-RPL utilizes a multi-objective Q-learning algorithm to learn optimal paths. Each node translates neighboring node information into a Q-value representing a composite multi-objective metric, including Buffer Utilization, Energy Level, Received Signal Strength Indicator (RSSI), Overflow Ratio, and Child Count. Furthermore, Aris-RPL operates effectively during the exploitation and exploration phases and continuously monitors the network overflow ratio during exploitation to respond to sudden changes and maintain performance. The extensive Contiki OS 3.0/COOJA simulator experiments have verified Aris-RPL efficiency. It enhanced Control Overhead, Packet Delivery Ratio (PDR), End-to-End Delay (E2E Delay), and Energy Consumption results compared to other counterparts for all scenarios on average by 39%, 25%, 7%, and 38%, respectively.
Halloum et al. (Sat,) studied this question.