Mobile computing force network architecture and quality of service (QoS) mechanism towards network-computing integration

The sixth generation mobile network (6G) is expected to achieve multi-component integration of communication, sensing, intelligence and computing. As an important infrastructure that enables emerging scenarios such as network for artificial intelligence (AI), AI for network and large model services, computing force networks need to be deeply integrated with mobile networks to satisfy the 6G multi-component integration service requirements. Towards 6G network-computing integration, this paper proposes a mobile computing force network architecture based on the traditional Service-based Architecture (SBA). Computing Policy Control Function (CPCF) is introduced to achieve the converged network-computing perception, on-demand service orchestration, integrated network-computing control and scheduling. Network-computing session management procedure with a novel Quality of Service (QoS) decision-making mechanism is proposed, which achieves the unified carrying of network-computing service session and Protocol Data Unit (PDU) session. Network-computing services such as AI model training are deployed on the prototype. Prototype experiments verify that the proposed scheme can implement converged QoS decision-making and integrated scheduling based on service requirements, and satisfy the end-to-end Quality of Experience (QoE) required by user.