Treffer: 面向无状态计算服务的算力网络技术研究.

Currently, in the information technology (IT) field, service mesh technologies lack collaborative scheduling capabilities with networks in cross-domain scenarios. In the communication technology (CT) field, computing power networks focused on resource-layer scheduling and network-layer solutions. When addressing the requirements of computing-network collaboration and routing scheduling for stateless computing services, issues such as the disconnection between computing resource scheduling and user application-layer functional demands, as well as protocol stack mismatches between network-layer connectivity solutions and service-oriented application program interface (API) interconnection requirements, remain unresolved. An analysis was conducted on the differentiated requirements of typical computing services for computing power networks and the scheduling and interconnection demands of stateless computing services. A novel computing power network architecture was proposed to support routing and scheduling for stateless computing services, with the overall architecture and key technologies outlined. Simulation results demonstrate that the proposed scheme uses URL-PATH as computing service identifiers to construct a service semantic routing plane, enabling API-granular computing-network resource collaborative scheduling and enhanced differentiated quality of service (QoS). This approach provides new insights for evolving computing power networks from "resource provisioning" to "service interconnection". [ABSTRACT FROM AUTHOR]

目前, 信息技术（IT）领域的服务网格技术在跨域场景中缺乏与网络的协同调度能力, 通信技术（CT） 领域的算力网络技术聚焦于资源层调度和网络层解决方案, 在面向无状态计算服务的算网协同与路由调度需求 时, 存在算力资源调度与用户应用层计算功能需求割裂、网络层连接方案与服务化应用程序编程接口（API）互 联需求协议栈错位等问题。分析了典型算力业务对算力网络的差异化需求以及无状态计算服务的调度互联要求, 提出了一种支持无状态计算服务路由调度的新型算力网络架构, 给出了总体架构和关键技术分析。仿真结果表 明, 所提方案采用URL-PATH作为算力标识构建服务语义路由平面, 可实现无状态计算服务的API 粒度算网资 源协同调度与差异化服务质量（QoS）保障能力提升, 为算力网络从"资源供给"向"服务互联"演进提供了新 的技术路线. [ABSTRACT FROM AUTHOR]

Copyright of Journal on Communication / Tongxin Xuebao is the property of Journal on Communications Editorial Office and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)