Energy-Efficient Routing Protocol in Vehicular Opportunistic Networks: A Dynamic Cluster-based Routing Using Deep Reinforcement Learning

2025-11-24

AI Summary

In vehicular opportunistic networks, highly dynamic topologies, unpredictable contacts, and resource constraints lead to low transmission reliability, high end-to-end delay, and short node lifetime. To address these challenges, this paper proposes a deep reinforcement learning (DRL)-based dynamic clustering routing method. Innovatively integrating the Actor-Critic framework with domain-inspired heuristic functions, the approach enables adaptive overlapping cluster reconfiguration and real-time optimal relay selection—balancing connectivity enhancement and energy load balancing. Built upon the Store-Carry-Forward paradigm, it effectively suppresses redundant forwarding. Experimental results demonstrate a 10% improvement in delivery ratio, a 28.5% reduction in end-to-end delay, a 7% increase in throughput, and a 30% decrease in data transmission hops. Furthermore, node lifetime is extended by 21%, overall energy consumption reduced by 17%, and node active time increased by 15%.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Opportunistic Networks (OppNets) employ the Store-Carry-Forward (SCF) paradigm to maintain communication during intermittent connectivity. However, routing performance suffers due to dynamic topology changes, unpredictable contact patterns, and resource constraints including limited energy and buffer capacity. These challenges compromise delivery reliability, increase latency, and reduce node longevity in highly dynamic environments. This paper proposes Cluster-based Routing using Deep Reinforcement Learning (CR-DRL), an adaptive routing approach that integrates an Actor-Critic learning framework with a heuristic function. CR-DRL enables real-time optimal relay selection and dynamic cluster overlap adjustment to maintain connectivity while minimizing redundant transmissions and enhancing routing efficiency. Simulation results demonstrate significant improvements over state-of-the-art baselines. CR-DRL extends node lifetimes by up to 21%, overall energy use is reduced by 17%, and nodes remain active for 15% longer. Communication performance also improves, with up to 10% higher delivery ratio, 28.5% lower delay, 7% higher throughput, and data requiring 30% fewer transmission steps across the network.

Problem

• Dynamic topology changes and resource constraints degrade routing performance
• Unpredictable contact patterns compromise delivery reliability and increase latency
• Limited energy and buffer capacity reduce node longevity in networks

Innovation

• Dynamic cluster-based routing using deep reinforcement learning
• Actor-Critic framework with heuristic function integration
• Real-time relay selection and cluster overlap adjustment