Performance monitoring and diagnosis in mobile communication networks
Build an automated system based on machine learning to diagnose fault conditions in mobile communication networks.
Given the growing complexity of wireless mobile networks and the expanding user base, telecommunication operators and vendors face a considerable hurdle in delivering excellent quality of service (QoS) while also managing the upkeep of wireless network infrastructure. To address this challenge and simultaneously cut down on both capital spending and operational costs, the 3rd Generation Partnership Project (3GPP) has introduced the notion of self-organizing networks (SON) within the Long-Term Evolution (LTE) specification. SON is recognized as a fundamental guiding principle for the networks of the future. Self-healing is one of the main functionalities of SON to handle any performance degradation in automated manner. Based on collected key performance indicators (KPIs) and performance management counters, the self-healing function will be activated whenever a fault or failure occurs.
Goal
Build a machine learning based diagnosis system as a part of the self-healing functionality in mobile networks. The proposed system uses network condition indicators such as key performance indicators and performance management counters for network condition diagnosis.
Learning outcome
- Work with a datasets of mobile network KPIs for the normal condition and network faults.
- Machine learning in networking
Qualifications
- General understanding of wireless networks
- Python/ C++ Programming
- Knowledge about machine learning is an advantage
Supervisors
- Azza Hassan Mohamed Ahmed
