发表机构
York University（约克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对车联网资源受限问题，提出结合强化学习与博弈论的自适应多判别器WGAN框架，在保持高预测准确率的同时提升了资源效率。
AI 中文摘要
将机器学习工作负载作为网络服务进行管理，会引入一种不同于传统模型训练的资源编排问题：应为任务分配哪些节点、如何在这些节点间划分通信与计算预算，以及如何在车联网的连通性和节点可用性随移动性变化时维持服务质量。在车联网（IoV）环境中部署生成对抗网络（GAN）是该问题的一个高要求实例；资源约束、动态网络拓扑以及相互竞争的优化目标，意味着传统GAN架构无法同时实现高准确率、高效的资源利用、低延迟和低通信开销。本文提出一种自适应多判别器Wasserstein GAN（MD-WGAN）框架，该框架整合了强化学习与博弈论协调机制，以联合应对这些挑战。在该框架中，路侧单元托管生成器，生成器与深度Q网络（DQN）智能体配对，DQN智能体负责选择判别器子集并管理移动车载节点间的分布式训练，同时博弈论协调步骤会在生成器与判别器之间分配训练轮次。统一优化目标将对抗学习质量与车辆约束下的资源效率、通信开销和延迟关联起来，使框架能够在网络条件变化时持续调整其训练行为。基于真实世界的NGSIM轨迹数据进行的评估显示，该框架达到了与最先进GAN基线相当的预测准确率——在所有评估方法中拥有最低的均方根误差（1.029）和平均绝对误差（0.894），同时显著提升了资源效率：平均CPU利用率降低约28%，平均内存使用量降低约6%，且通信开销和延迟处于可比水平。
英文摘要
Managing machine learning workloads as a network service introduces a resource-orchestration problem distinct from conventional model training; which nodes should be allocated to a task, how communication and computation budgets should be divided among them, and how service quality should be sustained as connectivity and node availability change with mobility. Deploying Generative Adversarial Networks (GANs) in Internet of Vehicles (IoV) environments is a demanding instance of this problem; resource constraints, dynamic network topologies, and competing optimization objectives mean that traditional GAN architectures cannot simultaneously achieve high accuracy, efficient resource use, low delay, and low communication overhead. This paper introduces an adaptive multi-discriminator Wasserstein GAN (MD-WGAN) framework that integrates reinforcement learning with game-theoretic coordination to address these challenges jointly. In our framework, roadside units host generators paired with Deep Q-Network (DQN) agents that select discriminator subsets and manage distributed training across mobile vehicular nodes, while a game-theoretic coordination step allocates training epochs between generators and discriminators. A unified optimization objective ties adversarial learning quality to resource efficiency, communication overhead, and latency under vehicular constraints, allowing the framework to continuously adapt its training behavior as network conditions change. Evaluation on real-world NGSIM trajectory data shows that the framework attains prediction accuracy comparable to state-of-the-art GAN baselines - the lowest RMSE (1.029) and MAE (0.894) among all evaluated methods - while markedly improving resource efficiency: average CPU utilization is reduced by roughly 28% and mean memory usage by roughly 6%, at competitive communication overhead and latency.
Comments15 pages
