Joint Communication and Computation Scheduling for MEC-enabled AIGC Services: A Game-Theoretic Stochastic Learning Approach
- 25 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (16) , 1
Abstract
Artificial Intelligence Generated Content (AIGC) powered by Generative Diffusion Models (GDMs) has emerged as a transformative paradigm for automated content creation. To satisfy the stringent latency requirements of AIGC services in many edge intelligence scenarios (e.g., smart cities), Mobile Edge Computing (MEC) provides critical computational support by deploying GDMs at edge servers (ES) close to end users. This paper investigates an MEC-enabled AIGC network comprising multiple ES, wireless access points (APs), and mobile users (UEs) with heterogeneous latency and accuracy demands. We formulate a Joint Communication Association and Computation Offloading (JCACO) game, where each UE strategically selects its serving AP, ES, and inference steps to minimize the overall service completion time while meeting accuracy constraints. The problem is challenging due to the network dynamics and the incomplete information. We prove that the JCACO game is a potential game under both complete and stochastic information settings, ensuring the existence of Nash Equilibrium (NE) in both cases. To derive the NE efficiently, we develop a distributed Multi-Agent Stochastic Learning (MASL) algorithm that provably converges to the NE with strict performance guarantees. Unlike conventional best-response schemes, MASL requires neither the knowledge of other players’ strategies nor global network information, making it fully distributed and adaptive to dynamic environments. We further provide a strict theoretical convergence analysis for MASL by using Ordinary Differential Equations (ODEs). Simulation results demonstrate that MASL significantly reduces service completion time compared with benchmark methods while satisfying accuracy constraints, confirming its effectiveness and practicality for real-world MEC-enabled AIGC networks.Keywords
All Related Versions
Funding Information
- Natural Science Foundation of Guangdong Province (2024A1515010178)
- Shenzhen Science and Technology Program (GXWD20231129103946001)
- National Natural Science Foundation of China (62472367)
This publication has 46 references indexed in Scilit:
- Joint Optimization of Model Inferencing and Task Offloading for MEC-Empowered Large Vision Model Services2025
- Diffusion-Model-Based Incentive Mechanism With Prospect Theory for Edge AIGC Services in 6G IoTIEEE Internet of Things Journal, 2024
- Online AI-Generated Content Request Scheduling with Deep Reinforcement Learning2024
- A Truthful Incentive Mechanism for Movement-Aware Task Offloading in Crowdsourced Mobile Edge Computing SystemsIEEE Internet of Things Journal, 2024
- Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC ServicesIEEE Communications Surveys & Tutorials, 2024
- Versatile Diffusion: Text, Images and Variations All in One Diffusion Model2023
- Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Potential GamesGames and Economic Behavior, 1996
- Decentralized learning of Nash equilibria in multi-person stochastic games with incomplete informationIEEE Transactions on Systems, Man, and Cybernetics, 1994