Enhancing AIGC Service Efficiency with Adaptive Multi-Edge Collaboration in A Distributed System

2025-12-18

AI Summary

To address high latency in centralized AIGC services and the limitations of existing MEC coordination mechanisms—such as single-server offloading or fixed edge server (ES) interactions, which hinder dynamic adaptation to heterogeneous computation and network requirements—this paper proposes AMCoEdge, an Adaptive Multi-Edge Collaborative architecture. AMCoEdge introduces a novel dynamic task offloading and resource orchestration mechanism enabling flexible, network-wide collaboration among edge servers. It further designs an online distributed algorithm based on deep reinforcement learning, achieving near-linear time complexity and theoretical convergence guarantees. Simulation results demonstrate reductions of ≥11.04% in task completion time and 44.86% in failure rate. Evaluations on a real prototype system show service latency improvements of 9.23%–31.98% over state-of-the-art approaches, significantly enhancing the responsiveness and reliability of edge-based AIGC services.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Multiagent Systems: Mechanism Design
• Search and Optimization: Learning to Search

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
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The Artificial Intelligence Generated Content (AIGC) technique has gained significant traction for producing diverse content. However, existing AIGC services typically operate within a centralized framework, resulting in high response times. To address this issue, we integrate collaborative Mobile Edge Computing (MEC) technology to reduce processing delays for AIGC services. Current collaborative MEC methods primarily support single-server offloading or facilitate interactions among fixed Edge Servers (ESs), limiting flexibility and resource utilization across all ESs to meet the varying computing and networking requirements of AIGC services. We propose AMCoEdge, an adaptive multi-server collaborative MEC approach to enhancing AIGC service efficiency. The AMCoEdge fully utilizes the computing and networking resources across all ESs through adaptive multi-ES selection and dynamic workload allocation, thereby minimizing the offloading make-span of AIGC services. Our design features an online distributed algorithm based on deep reinforcement learning, accompanied by theoretical analyses that confirm an approximate linear time complexity. Simulation results show that our method outperforms state-of-the-art baselines, achieving at least an 11.04% reduction in task offloading make-span and a 44.86% decrease in failure rate. Additionally, we develop a distributed prototype system to implement and evaluate our AMCoEdge method for real AIGC service execution, demonstrating service delays that are 9.23% - 31.98% lower than the three representative methods.

Problem

• Reduces AIGC service delays via adaptive multi-edge collaboration
• Optimizes resource use across edge servers for dynamic workloads
• Minimizes task offloading make-span and failure rates efficiently

Innovation

• Adaptive multi-server collaborative MEC approach
• Deep reinforcement learning online distributed algorithm
• Dynamic workload allocation across edge servers