Probabilistic Knowledge-Graph based Workflow Recommender for Network Management Automation
Erik Aumayr, Mingxue Wang, Anne-Marie Bosneag · 2019
The move towards more complex and dynamic telecommunication networks renders the need for more automation in the management system stringent. This is especially true in the context of 5G networks, where understanding context for providing the right management recommendations is crucial. Our work focuses on gathering context from the current status of the network and correlating it with useful information from existing documents in the network provider and operator's domain. We propose an architecture that, based on collected and interlinked information, can provide automatic recommendations for addressing existing problems in the network. More specifically, our approach is based on creating a knowledge-graph to direct workflow recommendations for network incidents. We implemented this system using the actual OSS product documentation and real network events and we show that our approach adds new value for automated network management, including improved efficiency and customer experience.