Accelerating AIGC Services with Latent Action Diffusion Scheduling in Edge Networks

2024-12-24

AI Summary

To address high latency in edge-network AIGC services caused by model complexity and inefficient offloading decisions, this paper proposes LAD-TS, a reinforcement learning–based scheduling method leveraging latent action diffusion. LAD-TS innovatively integrates the conditional generative capability of diffusion models into an RL framework, designing a latent action diffusion policy that exploits historical action distributions to accelerate convergence toward near-optimal offloading decisions under resource constraints. By jointly modeling multi-edge collaborative offloading and incorporating lightweight AIGC deployment (implemented in the DEdgeAI prototype system), the approach enables end-to-end AIGC service delivery on real-world edge platforms. Experimental results demonstrate an average latency reduction of 29.18% compared to five state-of-the-art baselines. The source code is publicly available.

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

Artificial Intelligence Generated Content (AIGC) has gained significant popularity for creating diverse content. Current AIGC models primarily focus on content quality within a centralized framework, resulting in a high service delay and negative user experiences. However, not only does the workload of an AIGC task depend on the AIGC model's complexity rather than the amount of data, but the large model and its multi-layer encoder structure also result in a huge demand for computational and memory resources. These unique characteristics pose new challenges in its modeling, deployment, and scheduling at edge networks. Thus, 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. The LAD-TS generates a near-optimal offloading decision by leveraging the diffusion model's conditional generation capability and the reinforcement learning's environment interaction ability, thereby minimizing the service delays under multiple resource constraints. Meanwhile, a latent action diffusion strategy is designed to guide decision generation by utilizing historical action probability, enabling rapid achievement of near-optimal decisions. Furthermore, we develop DEdgeAI, a prototype edge system with a refined AIGC model deployment to implement and evaluate our LAD-TS method. DEdgeAI provides a real AIGC service for users, demonstrating up to 29.18% shorter service delays than the current five representative AIGC platforms. We release our open-source code at https://github.com/ChangfuXu/DEdgeAI/.

Problem

• AIGC system
• user experience
• edge AI deployment

Innovation

• LAD-TS
• Edge Computing
• AIGC Optimization