ML-MaxProp: Bridging Machine Learning and Delay-Tolerant Routing for Resilient Post-Disaster Communication

In disaster-stricken and large-scale urban emergency scenarios, ensuring reliable communication remains a formidable challenge, as collapsed infrastructure, unpredictable mobility, and severely constrained resources disrupt conventional networks. Delay-Tolerant Networks (DTNs), though resilient through their store-carry-forward paradigm, reveal the fundamental weaknesses of classical protocols - Epidemic, Spray-and-Wait, and MaxProp - when confronted with sparse encounters, buffer shortages, and volatile connectivity. To address these obstacles, this study proposes ML-MaxProp, a hybrid routing protocol that strengthens MaxProp with supervised machine learning. By leveraging contextual features such as encounter frequency, hop count, buffer occupancy, message age, and time-to-live (TTL), ML-MaxProp predicts relay suitability in real time, transforming rigid heuristics into adaptive intelligence. Extensive simulations in the ONE environment using the Helsinki SPMBM mobility model show that ML-MaxProp consistently surpasses baseline protocols, achieving higher delivery probability, lower latency, and reduced overhead. Statistical validation further shows that these improvements are both significant and robust, even under highly resource-constrained and unstable conditions. Overall, this work shows that ML-MaxProp is not just an incremental refinement but a lightweight, adaptive, and practical solution to one of the hardest challenges in DTNs: sustaining mission-critical communication when infrastructure collapses and every forwarding decision becomes critical.