Adaptive Multi-Discriminator WGAN Framework for Resource-Constrained Internet of Vehicles Using Reinforcement Learning and Game Theory
This framework manages machine learning workloads for Internet of Vehicles (IoV) by integrating reinforcement learning and game theory to optimize performance under resource constraints. It uses a multi-discriminator Wasserstein GAN where roadside units host generators, and vehicles act as discriminators. The system adapts training strategies dynamically based on network conditions, achieving better accuracy while significantly reducing CPU usage and memory consumption.