PASTOR-Adaptive: a Bounded Feedback-Control Framework for Joint Utility and Token-Governed Forwarding-Rate Adaptation in Delay Tolerant Networks

Abstract

Delay Tolerant Networks (DTNs) operate under intermittent connectivity, dynamic topology, and resource-constrained nodes, making efficient routing a persistent challenge. Many existing DTN routing protocols—including probabilistic, social-aware, and utility-based approaches—rely on static or semi-static control parameters that do not adjust to changing network conditions. In our earlier work, PASTOR-DTN introduced a five-signal utility framework integrating encounter predictability, social trust, centrality, buffer headroom, and TTL urgency with token-bucket–based forwarding control. However, the utility weights and token refill rate in PASTOR-DTN remain fixed, limiting responsiveness to time-varying network dynamics. This paper presents PASTOR-Adaptive, a bounded feedback-control framework that extends PASTOR-DTN through joint online adaptation of utility weights and forwarding rate. Rather than employing learning-based optimization with large state spaces and convergence delays, the proposed framework applies a lightweight deterministic control law that adjusts parameters according to locally observable network phase (sparse, normal, or dense) and congestion state. Stability properties are maintained through bounded update increments, normalized weight projection, and negative feedback regulation. An ablation study on five different network settings (sparse, normal, dense, high mobility, heavy traffic) reveals that token rate adaptation is the main adaptive component, reducing the overhead by 29% for dense settings and increasing forwarding activity by 42% for sparse settings. Sensitivity analysis demonstrates robustness, with delivery probability varying by less than 0.5% across a tenfold parameter range. Comparative evaluation against Epidemic, PRoPHET, Spray-and-Wait, MaxProp, and PASTOR-DTN over 18 scenarios indicates that PASTOR-Adaptive achieves 84–98% delivery with overhead ratios between 1.3 and 4.1. These results demonstrate that bounded deterministic adaptation can maintain stable delivery–overhead trade-offs across heterogeneous DTN conditions.