Towards Multi-Task Generative-AI Edge Services with an Attention-based Diffusion DRL Approach

TL;DR

This paper introduces ADSAC, an attention-based diffusion reinforcement learning algorithm, to improve AIGC service selection at edge devices, effectively handling diverse user demands and resource constraints.

Contribution

The paper proposes a novel ADSAC algorithm combining diffusion models and attention mechanisms for AIGC service selection in edge environments, addressing user demand diversity.

Findings

ADSAC reduces user utility loss by at least 58.3%.

ADSAC decreases server crash rate by at least 58.4%.

The approach outperforms existing methods in diverse AIGC scenarios.

Abstract

As an emerging paradigm of content creation, AI-Generated Content (AIGC) has been widely adopted by a large number of edge end users. However, the requests for generated content from AIGC users have obvious diversity, and there remains a notable lack of research addressing the variance in user demands for AIGC services. This gap underscores a critical need for suitable AIGC service selection mechanisms satisfying various AIGC user requirements under resource-constrained edge environments. To address this challenge, this paper proposes a novel Attention-based Diffusion Soft Actor-Critic (ADSAC) algorithm to select the appropriate AIGC model in response to heterogeneous AIGC user requests. Specifically, the ADSAC algorithm integrates a diffusion model as the policy network in the off-policy reinforcement learning (RL) framework, to capture the intricate relationships between the characteristics of AIGC tasks and the integrated edge network states. Furthermore, an attention mechanism is utilized to harness the contextual long-range dependencies present in state feature vectors, enhancing the decision-making process. Extensive experiments validate the effectiveness of our algorithm in enhancing the overall user utility and reducing the crash rate of servers. Compared to the existing methods, the proposed ADSAC algorithm outperforms existing methods, reducing the overall user utility loss and the server crash rate by at least 58.3% and 58.4%, respectively. These results demonstrate our ADSAC algorithm is a robust solution to the challenges of diverse and dynamic user requirements in edge-based AIGC application environments.