Intelligent Task Offloading in VANETs: A Hybrid AI-Driven Approach for Low-Latency and Energy Efficiency

TL;DR

This work tackles latency-sensitive, energy-constrained task offloading in VANETs where dynamic topology and intermittent connectivity hinder local processing. It introduces a hybrid AI framework that integrates supervised learning for prediction, reinforcement learning for adaptive offloading, and Particle Swarm Optimization for resource allocation, complemented by federated learning for privacy-preserving collaboration. The optimization objective is to minimize $\min \sum_{i=1}^{n} (T_{offload} + \lambda E_{tx})$, balancing $T_{offload}$ and $E_{tx}$ across vehicles, RSUs, and MEC servers. Extensive simulations demonstrate substantial reductions in latency and energy, higher task offloading ratios and throughput, and lower failure rates compared with traditional offloading methods, indicating practical impact for real-time autonomous and connected-vehicle applications.

Abstract

Vehicular Ad-hoc Networks (VANETs) are integral to intelligent transportation systems, enabling vehicles to offload computational tasks to nearby roadside units (RSUs) and mobile edge computing (MEC) servers for real-time processing. However, the highly dynamic nature of VANETs introduces challenges, such as unpredictable network conditions, high latency, energy inefficiency, and task failure. This research addresses these issues by proposing a hybrid AI framework that integrates supervised learning, reinforcement learning, and Particle Swarm Optimization (PSO) for intelligent task offloading and resource allocation. The framework leverages supervised models for predicting optimal offloading strategies, reinforcement learning for adaptive decision-making, and PSO for optimizing latency and energy consumption. Extensive simulations demonstrate that the proposed framework achieves significant reductions in latency and energy usage while improving task success rates and network throughput. By offering an efficient, and scalable solution, this framework sets the foundation for enhancing real-time applications in dynamic vehicular environments.

Figures (6)

• Figure 1: Overview of the proposed system for intelligent task offloading in VANETs. The system integrates reinforcement learning and Particle Swarm Optimization (PSO) for optimal task distribution between vehicles and RSUs, ensuring low latency and energy efficiency.
• Figure 2: Latency and Energy Consumption Comparison
• Figure 3: Task Offloading Ratio and Throughput
• Figure 4: Task Failure Rate and Channel Utilization
• Figure 5: Reward Convergence in Reinforcement Learning