Learning reward functions via GNNs for multi-agent task placement in edge–cloud LLM services

With the advantage of being close to the network, edge cloud-enabled computing mode brings flexibility to task scheduling. However, with the heterogeneity of computing resources between cloud and edge cloud, and the complexity of computing and communication processes between multi-edge cloud, challenges have been brought to the deployment and computing of tasks in cloud-edge collaborative environments. In order to solve this challenge, firstly a deep reinforcement learning controller based cloud-edge collaborative computing framework has been proposed. Then a system QoS model has been estab-lished considering both the user benefits and the service provider benefits. By using deep Q-network, a deep reinforcement learning based collaborative task placement algorithm has been proposed for dynamically optimizing the target system utility. Finally, the experimental results show that the proposed method has a good learning ability for the computing cost of cloud and edge cloud as well as the communication cost between multi-edge cloud. In addition, compared with Q-table learning, random computing and cloud computing, a 10% improvement of system utility has been achieved with the proposed method.

The rapid proliferation of large-scale artificial intelligence (AI) applications has led to unprecedented demand for distributed, efficient, and highly scalable computing infrastructures. Traditional communication networks have evolved to support cloud–edge–end collaborative computing. However, they remain fundamentally communication-centric and lack native mechanisms for coordinating widespread computing resources. Computing power networks (CPNs) address these limitations by adopting a computation-first design that treats computing power as a unified, schedulable network resource. CPNs enable on-demand computing resource scheduling. This allows heterogeneous tasks to be dynamically matched with the most suitable cloud, edge, or terminal nodes based on real-time workload conditions, device capabilities, and network states. Moreover, CPNs achieve deep computing–network collaboration through joint optimization of routing, task placement, data exchange, and resource orchestration, providing performance gains beyond traditional decoupled architectures. Their unified and programmable control framework further supports seamless integration across heterogeneous devices, enabling flexible resource virtualization and efficient management of diverse network environments. Motivated by these unique characteristics, this survey provides a comprehensive overview of CPN technologies, their architectural foundations, resource allocation mechanisms, and their emerging role in supporting large-scale distributed AI training and inference. We highlight key challenges, discuss open research problems, and provide insights into future directions for advancing computation-centric networked intelligence.

With the development of recent innovative applications (e.g., augment reality, self-driving, and various cognitive applications), more and more computation-intensive and data-intensive tasks are delay-sensitive. Mobile edge computing in ultra-dense network is expected as an effective solution for meeting the low latency demand. However, the distributed computing resource in edge cloud and energy dynamics in the battery of mobile device makes it challenging to offload tasks for users. In this paper, leveraging the idea of software defined network, we investigate the task offloading problem in ultra-dense network aiming to minimize the delay while saving the battery life of user’s equipment. Specifically, we formulate the task offloading problem as a mixed integer non-linear program which is NP-hard. In order to solve it, we transform this optimization problem into two sub-problems, i.e., task placement sub-problem and resource allocation sub-problem. Based on the solution of the two sub-problems, we propose an efficient offloading scheme. Simulation results prove that the proposed scheme can reduce 20% of the task duration with 30% energy saving, compared with random and uniform task offloading schemes.