The autonomous placement of Virtual Network Functions (VNFs) is a key aspect of Zero-touch network and Service Management (ZSM) in Fifth Generation (5G) networking. Therefore, current orchestration frameworks need to be enhanced, accordingly. To address this need, this work presents an Adapted REinforcement Learning VNF Performance Prediction module for Autonomous VNF Placement, namely AREL3P. Our solution design bears a dual novelty. First, it leverages end-to-end service-level performance predictions for placing VNFs. Second, whereas the majority of other Machine Learning efforts in the literature use Supervised Learning (SL) techniques, AREL3P is based on a particular form of Reinforcement Learning adapted to predictions. This makes placement decisions more resilient to dynamic conditions, as well as portable to other network nodes, and able to generalize in heterogeneous network environments. Backed by a meticulous performance evaluation over a real 5G end-to-end testbed, we verify the above properties after integrating AREL3P to Open Source Management and Orchestration (OSM MANO) decisions. Among other highlights, we show increased VNF performance predictions accuracy by 40–45%, and an overall improved VNF placement efficiency against other SL benchmarks reflected by near-optimal decision scores in 23 out of a total of 27 investigated scenarios.

中文翻译：

---

采用强化学习的端到端基于性能的自主 VNF 放置

虚拟网络功能 (VNF) 的自主放置是第五代 (5G) 网络中零接触网络和服务管理 (ZSM) 的一个关键方面。因此，需要相应地增强当前的编排框架。为了满足这一需求，这项工作提出了一个用于自主 VNF 放置的自适应强化学习 VNF 性能预测模块，即 AREL3P。我们的解决方案设计具有双重新颖性。首先，它利用端到端服务级别性能预测来放置 VNF。其次，尽管文献中的大多数其他机器学习工作都使用监督学习 (SL) 技术，但 AREL3P 是基于适应预测的特定形式的强化学习。这使得放置决策对动态条件更具弹性，并且可移植到其他网络节点，并且能够在异构网络环境中进行泛化。在对真实 5G 端到端测试平台进行细致的性能评估的支持下，我们在将 AREL3P 集成到开源管理和编排 (OSM MANO) 决策后验证了上述属性。在其他亮点中，我们展示了 VNF 性能预测准确性提高了 40-45%，以及相对于其他 SL 基准的整体改进 VNF 放置效率，在总共 27 个调查场景中的 23 个中反映了接近最佳的决策分数。