A Systematic Literature Review on Machine Learning for Network Reliability in Telecommunications Industry

Abstract

System reliability is essential for improving operational efficiency and increasing revenue in the telecommunications sector. Recently, Machine Learning (ML) methodologies have shown significant promise in addressing system failures, network interruptions, and overall reliability challenges. Despite growing interest in this area, the broad scope of existing research can be overwhelming, making it difficult for novice researchers to identify key patterns, techniques, and gaps in the literature. This paper presents a comprehensive Systematic Mapping Study (SMS), covering 1,647 retrieved articles, revealed that research is heavily concentrated on fiber-based technologies (FTTH, PON, broadband) with limited focus on linking ML to enhance system reliability and to business outcomes such as churn and revenue. The Systematic Literature Review (SLR) applied a PRISMA-guided selection, resulting in 14 high-quality studies that were analyzed in depth. This review covers the period from 2019 to 2025, with particular attention to ML applications in network churn prediction, fault diagnosis, FTTH (Fiber to the Home) demand forecasting, system dependability, network optimization, and predictive maintenance. From the results of the SMS and SLR, we proceeded to the Latent Dirichlet Allocation (LDA) stage, where we categorized the findings into 10 emerging topics. Among these, four topics—Topic 2, Topic 3, Topic 6, and Topic 10—show notable upward trends. The paper concludes by focusing on High-Performance PON Systems and User-Centric Optical Networks. The taxonomy from this paper identified methodologies and an exploration of promising future research directions in ML for system dependability and network development, providing valuable insights for both scholars and practitioners.