Title | SELF-HEALING AND RESILIENCE IN FUTURE 5G COGNITIVE AUTONOMOUS NETWORKS |
Publication Type | Conference Paper |
Year of Publication | 2018 |
Authors | Ali-Tolppa, J., Kocsis, S., Schultz, B., Bodrog, L., Kajo, M. |
Conference Name | 2018 ITU Kaleidoscope: Machine Learning for a 5G Future (ITU K) |
Date Published | nov |
Keywords | 5G mobile communication, anomaly detection, automated anomaly detection, Case-Based Reasoning, cognitive network management, composability, critical machine-type communication, degraded states, diagnosis function, future 5G cognitive autonomous networks, future cognitive autonomous mobile networks, future network deployments, gaussian distribution, key requirements, learning (artificial intelligence), Long Term Evolution, machine learning, managed network functions, mobile network self-healing, multidimensional statistical methods, Optimization, pubcrawl, radio access networks, reliability, resilience, self-healing, self-healing functions, self-healing networks, SON, SON self-healing, sophisticated machine learning methods, statistical analysis, telecommunication computing, ultra-high reliability |
Abstract | In the Self-Organizing Networks (SON) concept, self-healing functions are used to detect, diagnose and correct degraded states in the managed network functions or other resources. Such methods are increasingly important in future network deployments, since ultra-high reliability is one of the key requirements for the future 5G mobile networks, e.g. in critical machine-type communication. In this paper, we discuss the considerations for improving the resiliency of future cognitive autonomous mobile networks. In particular, we present an automated anomaly detection and diagnosis function for SON self-healing based on multi-dimensional statistical methods, case-based reasoning and active learning techniques. Insights from both the human expert and sophisticated machine learning methods are combined in an iterative way. Additionally, we present how a more holistic view on mobile network self-healing can improve its performance. |
DOI | 10.23919/ITU-WT.2018.8598115 |
Citation Key | ali-tolppa_self-healing_2018 |