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

2025-07-14

AI Summary

To address the challenges of high QoS requirements, resource heterogeneity, cold-start latency, and the inherent trade-off between inference delay and generation quality in AIGC tasks at the edge, this paper proposes a collaborative scheduling algorithm based on attention-guided diffusion reinforcement learning. It is the first work to incorporate diffusion models into AIGC task scheduling: an attention mechanism dynamically perceives real-time load and queue states across heterogeneous edge servers, guiding a policy network to perform fine-grained task partitioning and cross-server collaborative inference, while enabling model reuse and adaptive load balancing. Experiments demonstrate that our approach reduces inference latency by up to 56% over baseline methods, significantly improves resource utilization and system throughput, and maintains high generation fidelity. This work establishes a novel paradigm for efficient, quality-aware AIGC service delivery in heterogeneous edge computing environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Diffusion Models for Vision

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Minimizing AIGC task delays for edge users with high QoS demands
• Optimizing edge server resource utilization and task scheduling efficiency
• Balancing inference latency and quality in heterogeneous edge environments

Innovation

• Edge-collaborative AIGC task scheduling algorithm
• Attention-guided diffusion reinforcement learning
• QoS-aware gang scheduling for edge servers