cs.LGDec 24, 2024

Accelerating AIGC Services with Latent Action Diffusion Scheduling in Edge Networks

Authors: Changfu Xu, Jianxiong Guo, Wanyu Lin, Haodong Zou, Yuzhu Liang, Xiaowen Chu, Jiannong Cao, Tian Wang

Organizations: BNU-HKBU United International College, Zhuhai 519087, China, and the Hong Kong Baptist University, Hong Kong. · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, China, and the Guangdong Key Lab of AI and Multi-Modal Data Processing, BNU-HKBU United International College, Zhuhai 519087, China. · Department of Computing, Hong Kong Polytechnic University, Hong Kong. · Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China. · 

Abstract

Artificial Intelligence Generated Content (AIGC) has gained significant popularity for creating diverse content. However, current AIGC models primarily focus on content quality within a centralized framework, resulting in a high service delay and negative user experiences. The workload of an AIGC task is determined by model complexity and multi-layered encoder architectures, posing significant challenges for its modeling, deployment, and scheduling within resource-constrained edge networks. We model an offloading problem among edges for providing real AIGC services and propose LAD-TS, a novel Latent Action Diffusion-based Task Scheduling method that orchestrates multiple edge servers for expedited AIGC services by leveraging the diffusion model's conditional guidance capability and the reinforcement learning's environment interaction ability. We first design an innovative Latent Action Diffusion Network (LADN) model based on traditional diffusion models. We then incorporate the LADN model into deep reinforcement learning, forming an effective LAD-TS method for task scheduling in distributed edge networks. Meanwhile, we design a latent action diffusion strategy to achieve near-optimal decisions quickly by utilizing historical action probabilities instead of Gaussian noise. Furthermore, we implement a refined AIGC model and develop DEdgeAI, a prototype edge system with the refined AIGC model deployment to evaluate our LAD-TS method. DEdgeAI provides a real AIGC service for users, demonstrating up to 7.36%−18.11%7.36\%-18.11\% and 34.07%−94.96%34.07\%-94.96\% shorter service delays than the state-of-the-art methods and representative commercial platforms, respectively. We release our open-source code at https://github.com/ChangfuXu/DEdgeAI/

Figures & tables

Explore similar work

CardsList
  1. A-MADiff: Attention-Guided Multi-Agent DRL with Diffusion Policies for Memory-Aware Task Orchestration in Mobile AIGC Networks

    Aug 29, 2026Chongzhi Wu, Zhengtao Li, Jiawen Kang +4Multi-Agent OrchestrationEdge AI

  2. Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks

    Feb 6, 2026Haiyuan Li, Hari Madhukumar, Shuangyi Yan +2Efficient Multimodal InferenceLLM Inference Scheduling

  3. End-to-End Latency-Minimizing and Load-Balanced Request Scheduling for Edge LLM Inference in Agentic AI Services

    Sep 15, 2026Zhen Li, Jun Cai, Haoran Gao +2LLM Inference SchedulingLLM Request Scheduling