Multi-Layer Perceptron-Based Relay Node Selection for Next-Generation Intelligent Delay-Tolerant Networks

2025-09-14

AI Summary

In delay-tolerant networks (DTNs), static replication strategies suffer from poor adaptability in identifying high-quality relay nodes, resulting in low message delivery ratios and high end-to-end delays. To address this, this paper proposes a dynamic routing method integrating lightweight machine learning into the Spray and Wait framework. Specifically, we jointly incorporate Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), and Random Forest classifiers, trained on dynamic node features—including mobility patterns and contact frequency—extracted from simulation logs. A low-latency RESTful API service is implemented using Flask, augmented with caching to ensure real-time inference. Experimental results demonstrate that the MLP model achieves superior accuracy, generalization capability, and inference efficiency compared to SVM and Random Forest. It significantly improves message delivery ratio and reduces average end-to-end delay, thereby validating the effectiveness and practicality of machine learning–driven adaptive relay selection in DTNs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Delay Tolerant Networks (DTNs) are critical for emergency communication in highly dynamic and challenging scenarios characterized by intermittent connectivity, frequent disruptions, and unpredictable node mobility. While some protocols are widely adopted for simplicity and low overhead, their static replication strategy lacks the ability to adaptively distinguish high-quality relay nodes, often leading to inefficient and suboptimal message dissemination. To address this challenge, we propose a novel intelligent routing enhancement that integrates machine learning-based node evaluation into the Spray and Wait framework. Several dynamic, core features are extracted from simulation logs and are used to train multiple classifiers - Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), and Random Forest (RF) - to predict whether a node is suitable as a relay under dynamic conditions. The trained models are deployed via a lightweight Flask-based RESTful API, enabling real-time, adaptive predictions. We implement the enhanced router MLPBasedSprayRouter, which selectively forwards messages based on the predicted relay quality. A caching mechanism is incorporated to reduce computational overhead and ensure stable, low-latency inference. Extensive experiments under realistic emergency mobility scenarios demonstrate that the proposed framework significantly improves delivery ratio while reducing average latency compared to the baseline protocols. Among all evaluated classifiers, MLP achieved the most robust performance, consistently outperforming both SVM and RF in terms of accuracy, adaptability, and inference speed. These results confirm the novelty and practicality of integrating machine learning into DTN routing, paving the way for resilient and intelligent communication systems in smart cities, disaster recovery, and other dynamic environments.

Problem

• Adaptive relay node selection in dynamic delay-tolerant networks
• Machine learning integration for intelligent routing enhancement
• Improving message delivery ratio and reducing latency

Innovation

• MLP-based relay selection for adaptive routing
• Lightweight RESTful API for real-time predictions
• Caching mechanism to reduce computational overhead