Enhancing QoE in Collaborative Edge Systems With Feedback Diffusion Generative Scheduling

Collaborative edge computing is a promising approach for delivering low-delay services to computation-intensive Internet of Things applications. Deep Reinforcement Learning (DRL) has become an effective way to solve task scheduling decisions in edge systems due to its adaptive learning ability to interact with the environment. However, current DRL-based task scheduling methods still face several challenges, such as limited exploration, sample inefficiency, and performance instability, which can lead to degraded user Quality of Experience (QoE). To address these challenges, we observe that diffusion models, famous for their performance in image generation, exhibit strong exploration, data efficiency, and performance stability. This inspires us to propose FDEdge, a novel feedback diffusion generative scheduling method for enhancing user QoE in collaborative edge systems. We first design an innovative Feedback Diffusion (FDN) model by leveraging historical action probability information during the denoising process. We then incorporate the FDN model into DRL, forming an effective and efficient framework for task scheduling in collaborative edge systems. We also present a probability derivation to ensure the FDEdge's rationality. Extensive experimental results demonstrate that our FDEdge method significantly reduces service delays by $45.42\%$ to $87.57\%$ and speeds up training episode durations by $2.5\times$ times for a higher QoE than state-of-the-art methods. We release our open-source code at https://github.com/ChangfuXu/FDEdge.