Emerging 5G and next generation 6G wireless are likely to involve myriads of connectivity, consisting of a huge number of relatively smaller cells providing ultra-dense coverage. Guaranteeing seamless connectivity and service level agreements in such a dense wireless system demands efficient network management and fast service recovery. However, restoration of a wireless network, in terms of maximizing service recovery, typically requires evaluating the service impact of every network element. Unfortunately, unavailability of real-time KPI information, during an outage, enforces most of the existing approaches to rely significantly on context-based manual evaluation. As a consequence, configuring a real-time recovery of the network nodes is almost impossible, thereby resulting in a prolonged outage duration. In this article, we explore deep learning to introduce an intelligent, proactive network recovery management scheme in anticipation of an eminent network outage. Our proposed method introduces a novel utilization-based ranking scheme of different wireless nodes to minimize the service downtime and enable a fast recovery. Efficient prediction of network KPI (Key Performance Index), based on actual wireless data demonstrates up to ~54% improvement in service outage.

中文翻译：

---

下一代无线网络中动态恢复的智能排序

新兴的 5G 和下一代 6G 无线可能涉及无数的连接，由大量提供超密集覆盖的相对较小的小区组成。在如此密集的无线系统中保证无缝连接和服务水平协议需要高效的网络管理和快速的服务恢复。然而，在最大限度地恢复服务方面，无线网络的恢复通常需要评估每个网络元素的服务影响。不幸的是，在中断期间无法获得实时 KPI 信息，这迫使大多数现有方法严重依赖基于上下文的手动评估。因此，配置网络节点的实时恢复几乎是不可能的，从而导致中断持续时间延长。在本文中，我们探索深度学习以引入智能、主动的网络恢复管理方案，以应对严重的网络中断。我们提出的方法引入了一种新颖的基于利用率的不同无线节点排名方案，以最大限度地减少服务停机时间并实现快速恢复。基于实际无线数据的网络 KPI（关键性能指标）的有效预测表明，服务中断最多可改善约 54%。