Computing Power Networks (CPNs) represent an innovative, collaborative architecture that integrates resources via the communication network, optimizing resource allocation to support service demands. Due to the increased need for services powered by artificial intelligence across various domains, CPNs are increasingly required to allocate users efficiently to appropriate servers to meet the low-latency needs of service computing. However, challenges such as users' dynamic mobility, weak communication paths, and high-dimensional solution spaces persist in optimizing user allocation in CPNs. In this context, we propose a diffusion-driven optimization approach for mobility-aware user allocation. To tackle the challenge of users' dynamic mobility, we adopt a user location prediction approach incorporating the users' movement patterns to forecast future movement, calledCAMPE. To tackle the challenge of weak communication paths, we establish the new transmission path by reconfigurable intelligent surface and enhance the quality of the communication link by adjusting the phase configurations. Moreover, faced with the challenge of high-dimensional solution spaces associated with phase adjustment and user allocation decisions, we devise an action-generation strategy based on diffusion models namedDiffUser. This approach motivates the generation of optimal solutions even in complex and dynamic environments. Finally, we conduct extensive simulations in user location prediction and system latency optimization. Compared with other solutions, the superiority of our approach has been demonstrated.

The rapid development of Artificial Intelligence Generated Content (AIGC) technology has led to a strong demand for elastic computing resources. The crowdsourced edge cloud system builds a flexible resource pool by integrating heterogeneous idle servers and even personal devices to meet the dynamic computing requirements of AIGC services. The system relies on the serverless architecture to realize the dynamic scheduling of resources, which needs to trade off resource benefits and energy consumption costs to improve the overall social welfare, resource efficiency, and environmental sustainability. However, challenges such as unfair resource pricing, dynamic resource availability, and the complexity of strategy optimization remain unresolved for green and efficient resource management. In this paper, we propose a resource management framework named ReFluid. We introduce a game-theoretical pricing model to ensure fair pricing, a fluid model-based analysis for promoting a more sustainable management of computing resources, and a diffusion-based optimization mechanism to enhance model stability and adaptability. The evaluation shows that ReFluid significantly improves average social welfare and reduces energy consumption.

While diffusion models have demonstrated remarkable success in computer vision tasks, their deployment in Internet of Things environments remains challenging. Edge devices face significant constraints in computational resources and must adapt to dynamic operating conditions. To address these limitations, we propose a novel system that accelerates AIgenerated content (AIGC) collaborative inference in dynamic edge networks. The proposed system introduces a multi-exit vision transformer-based U-Net architecture that enables efficient processing through adaptive exit point selection during the diffusion process, optimizing the trade-off between inference accuracy and computational efficiency. To optimize device-level operations, we develop an innovative generative AI-assisted reinforcement learning framework that determines optimal exit selection and offloading strategies to maximize generation quality and inference speed. Furthermore, we design a fine-tuning approach with policy reuse mechanisms that facilitates rapid reinforcement learning algorithm deployment across diverse environments. Extensive experimental evaluations demonstrate that our system outperforms existing algorithms in terms of balancing inference latency and generation quality, while also exhibiting improved adaptability to environmental variations.

The escalating demands for Artificial Intelligence-generated content (AIGC) services greatly require computing resources. The edge-cloud market offers an effective solution for AIGC services by integrating, managing, and trading distributed computing resources. Within this novel service market, participants contribute idle resources to support AIGC services to earn income, creating a more flexible market environment. Meanwhile, the generation quality and computing resource requirements of AIGC services are related to input prompts. Therefore, this relationship introduces new challenges, such asthe information uncertainty in input prompts, the inability to model resource continuity, and high-dimensional complexity for optimization.In this paper, we propose a resource fluid equilibrium management strategy for supporting AIGC services within edge-cloud market, termedFluE. To address the challenge of information uncertainty in user prompts, we measure the content value of AIGC prompts by information entropy and introduce a redundancy reduction approach to focus on meaningful information in prompts. To tackle the challenge of the inability to model the continuity provision of computing resources, we utilize the fluid model to ensure seamless resource provision and facilitate a more balanced management of computing resources. To address the challenge of high-dimensional complexity of strategy optimization, we develop a diffusion-based algorithm namedReDiffto reconstruct the target strategy distribution and generate precise and effective optimization decisions. We evaluate our proposed scheme under a dynamic resource provisioning environment. Based on the DiffusionDB dataset, the publicly available real trace of AIGC service prompt, ourReDiffalgorithm achieves up to 69.8% and 77.4% improvements in average social welfare compared to LySAC and CD-PPO, respectively.

Massive device connections in upcoming 6G networks have led to a sharp increase in network traffic volume, posing significant challenges in providing reliable performance guarantees, e.g., low latency. The Computing Power Network (CPN) is a new framework for resource integration involving multiple parties. It integrates the resources of various owners via the network, providing users with efficient and adaptable services. Due to the uncertainty of the signal quality, the majority of existing studies do not adequately organize the topology of user allocation in CPNs when optimizing network resources. Reconfigurable Intelligent Surface (RIS) is a new type of network node for constructing future smart radio environments with high spectral efficiency and nearly zero energy consumption that can offer new access options for user allocation in CPNs. In this paper, we investigate the user access allocation in a RIS-assisted Ad Hoc Edge (RAHE) scenario where the users are with service-intensive demands. To maximize the overall service tasks of the system constrained by a service time threshold, we propose a RIS-assisted interval scheduler strategy (RS3) approach to balancing the whole system service completion and total latency. Specifically, RS3is a graph-theoretic optimization method based on the interval scheduling problem. The numerical simulation results demonstrate that our proposed RS3approach is superior to commonly utilized methods in terms of the number of serves given the service time constraint.