QoE-Aware Offloading and Resource Allocation for MEC-Empowered AIGC Services

Artificial Intelligence-Generated Content (AIGC) has emerged as a transformative paradigm, enabling the autonomous creation of diverse content. By offloading model inference tasks to the network edge that is closer to mobile users (MUs), Mobile Edge Computing (MEC) has the potential to significantly enhance the performance of AIGC services. In practice, however, it is challenging to optimally manage MEC-empowered AIGC services, due to the lack of well-defined AIGC-specific metrics, as well as the dynamic workload and computation-intensive nature of AIGC services. In this paper, we first define a novel AIGC metric based on extensive real data experiments, and then study the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">joint task offloading and resource allocation</i> problem in a generic MEC-empowered AIGC network, where MUs can offload model inference tasks to local or remote Base Stations (BSs), aiming at maximizing their Quality of Experience (QoE). The problem is challenging due to the fast and randomly changing of environments, as well as the necessity for real-time, asynchronous decision-making. To tackle these challenges, we propose two deep reinforcement learning algorithms based on the Proximal Policy Optimization (PPO) framework: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Single-Layer PPO (SL-PPO)</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-Layer PPO (ML-PPO)</i>, designed for slow-changing and fast-changing environments, respectively. In the SL-PPO algorithm, both task offloading and resource allocation decisions are made simultaneously when tasks arrive. In the ML-PPO algorithm, the task offloading decision is made immediately when tasks arrive, while the resource allocation decision is deferred until tasks are scheduled for processing or transmission in the corresponding queues. Simulation results show that (i) both algorithms outperform existing methods in the literature, and can increase the average utility by up to 47% and 48.8%; (ii) both algorithms can effectively manage the trade-off between latency and energy consumption.