On-Dyn-CDA: A Real-Time Cost-Driven Task Offloading Algorithm for Vehicular Networks with Reduced Latency and Task Loss

2025-09-06

AI Summary

To address the dual challenges of stringent latency requirements and high task drop rates in vehicular networks, this paper proposes a training-free, dataset-agnostic, dynamic cost-driven online offloading algorithm. The method leverages real-time task arrival models and edge computing infrastructure to design a lightweight online optimization mechanism that generates offloading decisions within milliseconds (0.05 seconds per execution), drastically reducing computational overhead. Compared to dynamic particle swarm optimization (PSO), it reduces execution time by 1330 seconds and improves performance by lowering task drop rate by 3.42% and average end-to-end latency by 29.22%. Its core innovation lies in unifying dynamic cost modeling with ultra-low-latency responsiveness, enabling joint optimization of task completion rate, latency, and packet loss. The algorithm is highly efficient, scalable, and deployment-friendly, requiring no offline training or labeled datasets.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Algorithm Configuration
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Real-time task processing is a critical challenge in vehicular networks, where achieving low latency and minimizing dropped task ratio depend on efficient task execution. Our primary objective is to maximize the number of completed tasks while minimizing overall latency, with a particular focus on reducing number of dropped tasks. To this end, we investigate both static and dynamic versions of an optimization algorithm. The static version assumes full task availability, while the dynamic version manages tasks as they arrive. We also distinguish between online and offline cases: the online version incorporates execution time into the offloading decision process, whereas the offline version excludes it, serving as a theoretical benchmark for optimal performance. We evaluate our proposed Online Dynamic Cost-Driven Algorithm (On-Dyn-CDA) against these baselines. Notably, the static Particle Swarm Optimization (PSO) baseline assumes all tasks are transferred to the RSU and processed by the MEC, and its offline version disregards execution time, making it infeasible for real-time applications despite its optimal performance in theory. Our novel On-Dyn-CDA completes execution in just 0.05 seconds under the most complex scenario, compared to 1330.05 seconds required by Dynamic PSO. It also outperforms Dynamic PSO by 3.42% in task loss and achieves a 29.22% reduction in average latency in complex scenarios. Furthermore, it requires neither a dataset nor a training phase, and its low computational complexity ensures efficiency and scalability in dynamic environments.

Problem

• Minimizing task loss and latency in vehicular network task offloading
• Optimizing real-time task execution with cost-driven dynamic algorithms
• Addressing computational efficiency for scalable vehicular network operations

Innovation

• Real-time cost-driven task offloading algorithm
• Dynamic optimization without dataset or training
• Low computational complexity for scalability