GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing
For 6G network operators, it improves resource allocation efficiency by addressing semantic blindness and training diversity, though incremental over DDPG.
The paper tackles resource allocation in 6G network slicing, achieving 22% URLLC, 20% eMBB, and 25% mMTC spectral efficiency gains (p<0.001) with 18% latency and 31% packet loss reduction using a GAN-enhanced DDPG framework.
Sixth-generation (6G) wireless networks must support heterogeneous services: enhanced Mobile Broadband (eMBB) requiring 1 Tbps data rates, massive Machine-Type Communications (mMTC) supporting 10 million devices per km, and Ultra-Reliable Low-Latency Communications (URLLC) with 0.1-1 ms latency. Current resource allocation suffers from three limitations: (1) semantic blindness wasting 35% bandwidth on redundant data, (2) discrete action quantization, and (3) limited training diversity. This paper proposes GAN-DDPG, a Generative Adversarial Network-enhanced Deep Deterministic Policy Gradient framework integrating conditional GANs for traffic synthesis, continuous action DDPG, and semantic-aware reward optimization. Extensive simulations with statistical validation demonstrate significant improvements: 22% URLLC, 20% eMBB, 25% mMTC spectral efficiency gains (all p < 0.001) compared to baseline DDPG, with 18% latency and 31% packet loss reduction.