Machine Learning in FCAPS: Toward Enhanced Beyond 5G Network Management
Abdelkader Mekrache, Adlen Ksentini, Christos Verikoukis
Abstract
The increasing complexity of telecommunication networks has highlighted the need for robust network management frameworks. One such framework is FCAPS, which encompasses a wide range of functionalities, including fault management, configuration management, accounting management, performance management, and security management. To effectively address the complexities of modern networks, the integration of Artificial Intelligence (AI) techniques, particularly Machine Learning (ML) and Machine Reasoning (MR), has emerged as a pivotal strategy within FCAPS. ML provides networks with data-driven algorithms to recognize patterns and make informed predictions, while MR focuses on developing understandable AI systems that draw conclusions based on explicit knowledge. In this paper, we explore the field of MR and its usage within FCAPS. First, we present an overview of the FCAPS framework, including a categorization of FCAPS levels. Then, we provide a novel taxonomy of MR approaches, presenting both traditional and advanced MR. Next, we review MR techniques to address emerging concerns within FCAPS. Finally, we discuss open issues and future directions for further study toward 6G networks.