GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910118145163264 |
|---|---|
| author | John, Daniel Benniah |
| author_facet | John, Daniel Benniah |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08576 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing John, Daniel Benniah Networking and Internet Architecture Artificial Intelligence Machine Learning 68M10, 68T05 C.2.1; I.2.6; I.2.11 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. |
| title | GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing |
| topic | Networking and Internet Architecture Artificial Intelligence Machine Learning 68M10, 68T05 C.2.1; I.2.6; I.2.11 |
| url | https://arxiv.org/abs/2604.08576 |