Experimental Evaluation of a Cognitive Routing Strategy for Efficient Energy Management in DTN

Abstract

This study conducts an experimental evaluation of a decentralized cognitive routing approach to improve the performance of Delay Tolerant Networks (DTNs) in challenging environments, particularly in space. The primary goal is to minimize latency while concurrently extending the operational lifetimes of nodes by strategically avoiding bundle transmission through low-charged relay nodes. The approach addresses multi-objective routing through a reinforcement learning formulation that considers either the delay or path length to the destination, jointly with the residual energy levels of nodes along the transmission path. It also defines suitable networking mechanisms to obtain accurate estimates of delay-energy metrics associated with node contacts. The paper provides details of the implementation strategy for the High-Rate Delay Tolerant Networking (HDTN) framework and the design of a battery emulation system that provides precise control over experimental conditions, ensuring test reproducibility. The results demonstrate significant reductions in bundle losses and extended network lifetimes while maintaining either delay or path lengths within reasonable bounds compared to what can be achieved with the current routing standard. The proposed approach holds the promise of significantly improving the reliability of DTN communications in space.