Enhancing QoE in Collaborative Edge Systems with Feedback Diffusion Generative Scheduling

doi:10.1109/TMC.2025.3587744

科研成果详情

题名	Enhancing QoE in Collaborative Edge Systems with Feedback Diffusion Generative Scheduling
作者	Xu，Changfu 1,2; Guo，Jianxiong 3,4; Liang，Yuzhu 3; Zou，Haodong 1,2; Zeng，Jiandian 3; Dai，Haipeng 5; Jia，Weijia 3,4; Cao，Jiannong 6; Wang，Tian 3
发表日期	2025
发表期刊	IEEE Transactions on Mobile Computing
ISSN/eISSN	1536-1233
摘要	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 for a higher QoE than state-of-the-art methods.
关键词	Deep reinforcement learning Edge computing Feedback diffusion Generative task scheduling
DOI	10.1109/TMC.2025.3587744
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-105010952594
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13730
专题	北师香港浸会大学
通讯作者	Wang，Tian
作者单位	1.Beijing Normal-Hong Kong Baptist University,Zhuhai,519087,China 2.Hong Kong Baptist University,Hong Kong 3.Beijing Normal University,Institute of Artificial Intelligence and Future Networks,Zhuhai,519087,China 4.Beijing Normal-Hong Kong Baptist University,Guangdong Key Lab of AI and Multi-Modal Data Processing,Zhuhai,519087,China 5.Nanjing University,Department of Computer Science and Technology,Nanjing,210023,China 6.Hong Kong Polytechnic University,Department of Computing,Hong Kong
第一作者单位	北师香港浸会大学
推荐引用方式 GB/T 7714	Xu，Changfu,Guo，Jianxiong,Liang，Yuzhuet al. Enhancing QoE in Collaborative Edge Systems with Feedback Diffusion Generative Scheduling[J]. IEEE Transactions on Mobile Computing, 2025.
APA	Xu，Changfu., Guo，Jianxiong., Liang，Yuzhu., Zou，Haodong., Zeng，Jiandian., .. & Wang，Tian. (2025). Enhancing QoE in Collaborative Edge Systems with Feedback Diffusion Generative Scheduling. IEEE Transactions on Mobile Computing.
MLA	Xu，Changfu,et al."Enhancing QoE in Collaborative Edge Systems with Feedback Diffusion Generative Scheduling". IEEE Transactions on Mobile Computing (2025).