ScalO-RAN:Open RAN 中能量感知的网络智能扩展
ScalO-RAN: Energy-aware Network Intelligence Scaling in Open RAN
AI总结:
本文提出 ScalO-RAN,一种作为 O-RAN rApp 的优化控制框架,用于在共享基础设施中分配和扩展 AI 类 O-RAN 应用,在满足严格时延要求的同时降低能耗,并通过原型实验证明扩展主要受推理时间约束而非资源约束。
摘要:
网络虚拟化、软件定义基础设施和编排是当代网络中的关键要素,为优化和新能力创造了新的途径。遵循这些原则,O-RAN 提供了一条绕过供应商锁定、规避垂直化配置、实现网络可编程性并促进集成人工智能(AI)支持的途径。此外,现代容器编排框架(例如 Kubernetes、Red Hat OpenShift)简化了蜂窝基站以及新引入的 RAN 智能控制器(RIC)的部署、管理和编排方式。虽然这通过基础设施共享降低了成本,但也使满足 O-RAN 控制时延要求变得更加困难,尤其是在资源利用率达到峰值时。为了解决这一问题,我们提出了 ScalO-RAN,这是一个基于优化并以 O-RAN rApp 形式设计的控制框架,用于分配和扩展基于 AI 的 O-RAN 应用(xApps、rApps、dApps),以:(i)遵守特定应用的时延要求,以及(ii)在降低能耗的同时实现共享基础设施的货币化。我们在一个 OpenShift 集群上对 ScalO-RAN 进行了原型实现,该集群中基站、RIC 以及一组基于 AI 的 xApps 均以微服务形式部署。我们从数值和实验两方面对 ScalO-RAN 进行了评估。结果表明,ScalO-RAN 能够在可用计算节点内最优地分配和分布 O-RAN 应用,以满足甚至严格的时延要求。更重要的是,我们表明扩展 O-RAN 应用主要是一个时间受限问题,而非资源受限问题,扩展策略必须考虑 AI 应用严格的推理时间,而不仅仅是它们消耗多少资源。
英文摘要:
Network virtualization, software-defined infrastructure, and orchestration are pivotal elements in contemporary networks, yielding new vectors for optimization and novel capabilities. In line with these principles, O-RAN presents an avenue to bypass vendor lock-in, circumvent vertical configurations, enable network programmability, and facilitate integrated Artificial Intelligence (AI) support. Moreover, modern container orchestration frameworks (e.g., Kubernetes, Red Hat OpenShift) simplify the way cellular base stations, as well as the newly introduced RAN Intelligent Controllers (RICs), are deployed, managed, and orchestrated. While this enables cost reduction via infrastructure sharing, it also makes it more challenging to meet O-RAN control latency requirements, especially during peak resource utilization. To address this problem, we propose ScalO-RAN, a control framework rooted in optimization and designed as an O-RAN rApp that allocates and scales AI-based O-RAN applications (xApps, rApps, dApps) to: (i) abide by application-specific latency requirements, and (ii) monetize the shared infrastructure while reducing energy consumption. We prototype ScalO-RAN on an OpenShift cluster with base stations, RIC, and a set of AI-based xApps deployed as micro-services. We evaluate ScalO-RAN both numerically and experimentally. Our results show that ScalO-RAN can optimally allocate and distribute O-RAN applications within available computing nodes to accommodate even stringent latency requirements. More importantly, we show that scaling O-RAN applications is primarily a time-constrained problem rather than a resource-constrained one, where scaling policies must account for stringent inference time of AI applications, and not only how many resources they consume.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。