Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services

TL;DR

This paper proposes a two-timescale deep reinforcement learning framework for efficient model caching and resource allocation in edge-enabled AI-generated content services, balancing quality and latency.

Contribution

It introduces a novel two-timescale DRL approach combining DDQN and diffusion-based D3PG algorithms for joint caching and resource management in edge AI services.

Findings

The proposed T2DRL algorithm outperforms baseline methods in simulations.

The diffusion-based D3PG effectively manages continuous resource allocation.

Joint optimization improves AIGC service quality and reduces latency.

Abstract

Generative AI (GenAI) has emerged as a transformative technology, enabling customized and personalized AI-generated content (AIGC) services. In this paper, we address challenges of edge-enabled AIGC service provisioning, which remain underexplored in the literature. These services require executing GenAI models with billions of parameters, posing significant obstacles to resource-limited wireless edge. We subsequently introduce the formulation of joint model caching and resource allocation for AIGC services to balance a trade-off between AIGC quality and latency metrics. We obtain mathematical relationships of these metrics with the computational resources required by GenAI models via experimentation. Afterward, we decompose the formulation into a model caching subproblem on a long-timescale and a resource allocation subproblem on a short-timescale. Since the variables to be solved are discrete and continuous, respectively, we leverage a double deep Q-network (DDQN) algorithm to solve the former subproblem and propose a diffusion-based deep deterministic policy gradient (D3PG) algorithm to solve the latter. The proposed D3PG algorithm makes an innovative use of diffusion models as the actor network to determine optimal resource allocation decisions. Consequently, we integrate these two learning methods within the overarching two-timescale deep reinforcement learning (T2DRL) algorithm, the performance of which is studied through comparative numerical simulations.