EAT: QoS-Aware Edge-Collaborative AIGC Task Scheduling via Attention-Guided Diffusion Reinforcement Learning

TL;DR

This paper presents EAT, a reinforcement learning-based, attention-guided diffusion algorithm for QoS-aware AIGC task scheduling across edge servers, significantly reducing inference latency and improving resource utilization.

Contribution

It introduces a novel gang scheduling approach for AIGC tasks on edge servers, utilizing an attention-guided diffusion RL model for efficient task distribution and resource management.

Findings

Reduces inference latency by up to 56% compared to baselines.

Effectively balances inference quality and latency in heterogeneous edge environments.

Demonstrates improved resource utilization and task scheduling efficiency.

Abstract

The growth of Artificial Intelligence (AI) and large language models has enabled the use of Generative AI (GenAI) in cloud data centers for diverse AI-Generated Content (AIGC) tasks. Models like Stable Diffusion introduce unavoidable delays and substantial resource overhead, which are unsuitable for users at the network edge with high QoS demands. Deploying AIGC services on edge servers reduces transmission times but often leads to underutilized resources and fails to optimally balance inference latency and quality. To address these issues, this paper introduces a QoS-aware \underline{E}dge-collaborative \underline{A}IGC \underline{T}ask scheduling (EAT) algorithm. Specifically: 1) We segment AIGC tasks and schedule patches to various edge servers, formulating it as a gang scheduling problem that balances inference latency and quality while considering server heterogeneity, such as differing model distributions and cold start issues. 2) We propose a reinforcement learning-based EAT algorithm that uses an attention layer to extract load and task queue information from edge servers and employs a diffusion-based policy network for scheduling, efficiently enabling model reuse. 3) We develop an AIGC task scheduling system that uses our EAT algorithm to divide tasks and distribute them across multiple edge servers for processing. Experimental results based on our system and large-scale simulations show that our EAT algorithm can reduce inference latency by up to 56\% compared to baselines. We release our open-source code at https://github.com/zzf1955/EAT.